JP2017224007A - Image processing sensor, image processing method, image processing program and computer readable recording medium - Google Patents

Abstract

PROBLEM TO BE SOLVED: To easily determine whether a threshold value to be used for quality discrimination is appropriate.SOLUTION: An image processing sensor comprises a differential image generation part for generating a high-quality/background differential image from a registered high-quality image and a background image. The image processing sensor also comprises a display control part 58f for performing two indication in a first display format that a threshold value calculated by a threshold value calculation part 56c based on the high-quality/background differential image and a degree of matching a latest input image to a pattern model are numerically displayed and the latest input image is displayed on a display screen 43, and a second display format that the threshold value calculated by the threshold calculation part 56c, the degree of matching the latest input image to the pattern model and a maximum and/or minimum matching degree in the past during operation are numerically displayed on the display screen 43, and for performing format switching control between the first display format and the second display format.SELECTED DRAWING: Figure 12

Description

  The present invention relates to an image processing sensor, an image processing method, an image processing program, and a computer-readable recording medium that can easily determine whether a threshold value used for pass / fail determination is appropriate.

  The image processing sensor is installed in various modes as a member for inspecting the appearance of the inspection object, such as being incorporated in the vicinity of a conveyance line where the inspection object is conveyed or in an inspection apparatus. For example, a workpiece passing through a production line is imaged as an inspection object, and the quality of the workpiece is determined by detecting the presence or absence of a workpiece defect based on the obtained image. The user needs to acquire an image obtained by imaging a non-defective work in advance and register the image as a model image. This operation is called so-called teaching (see, for example, Patent Document 1). When teaching is completed, the mode is shifted to the operation mode, and when the matching degree between the model image and the inspection image exceeds a threshold value, an OK determination is made.

JP-A-11-31249

  However, it is not easy for the user to determine whether the threshold set during teaching is appropriate during driving. For example, when the degree of coincidence calculated from the past to the present is distributed in the vicinity of the threshold, if the degree of coincidence fluctuates due to some influence such as ambient light, the inspection accuracy such as erroneously setting the place that should originally be NG as OK. There was a risk of lowering.

  The present invention has been made to solve such conventional problems. An object of the present invention is to provide an image processing sensor and an image processing method that can easily determine whether or not a threshold value used for pass / fail judgment is appropriate, and that can prevent deterioration in inspection accuracy and improve usability. And an image processing program and a computer-readable recording medium.

Means for Solving the Problems and Effects of the Invention

  The image processing sensor according to the first aspect of the present invention is an image processing sensor for detecting that an inspection object is a non-defective product or a defective product by performing image processing on the image of the inspection object. Then, the quality of the inspection object is determined based on the imaging unit that images the inspection target, the display unit that displays the input image acquired by the imaging unit, and the input image acquired by the imaging unit. The image including the inspection object to be determined to be non-defective by the quality determining unit and the quality determining unit is acquired by the imaging unit and registered as a first non-defective image, and the characteristic part of the inspection target as a non-defective product is removed An image registration unit that acquires the background image obtained by the imaging unit and registers it as a first background image, a first non-defective image registered by the image registration unit, and a first image registered by the image registration unit A background picture From the difference image generation unit that generates the first non-defective background difference image and the first non-defective background difference image generated by the difference image generation unit, the first non-defective background difference image Based on the degree of coincidence calculated by the degree of coincidence calculated by the degree of coincidence calculated by the degree of coincidence calculated by the degree of coincidence calculated by the degree of coincidence calculated by the degree of coincidence of the first background image with respect to the pattern model. A threshold calculation unit that calculates a threshold value, and a first unit that displays the threshold value calculated by the threshold calculation unit and the degree of coincidence of the latest input image with the pattern model in the display unit, and displays the latest input image. Display format, the threshold calculated by the threshold calculation unit, the degree of coincidence of the latest input image with the pattern model, and the past maximum and / or the past minimum during driving A display control unit that performs two switching control of the display form of the second display format to degrees numeric display may comprise a. With the above configuration, the user can perform teaching by two points of a non-defective image and a background image, and from the first display format, the user can check the degree of coincidence between the live image of the inspection object and the non-defective image with a threshold value, From the second display format, it is possible to determine the suitability of the threshold setting from the maximum value and the minimum value of the calculated degree of coincidence, and to switch between these display formats.

  In addition, according to the image processing sensor of the second aspect of the present invention, image processing for detecting whether the inspection object is a non-defective product or a defective product by performing image processing on the image of the inspection object. An image sensor that images the inspection object, a display unit that displays the input image acquired by the image sensor, and the quality of the inspection object based on the input image acquired by the image sensor An image including a pass / fail determination unit to be determined and an inspection object to be determined as a non-defective product by the pass / fail determination unit is registered as a second non-defective image, and an inspection target to be determined as a defective product by the pass / fail determination unit An image registration unit that registers an image including the image as a defective product image, acquires a background image from which a characteristic part as a non-defective product of the inspection object is removed, and registers it as a second background image; and the image registration By part A second good product background difference image is registered from the recorded second good product image and the second background image registered by the image registration unit by the defective product image registered by the image registration unit and the image registration unit. A difference image generation unit for generating a defective product background difference image from the generated second background image and a pattern model corresponding to the second non-defective background difference image generated by the difference image generation unit. Based on the degree of coincidence calculated by the degree of coincidence calculated by the degree of coincidence calculating unit and the degree of coincidence calculated by the coincidence degree calculating unit, a threshold value used for the pass / fail determination by the pass / fail determination unit is calculated. In the threshold value calculation unit and the display unit, the threshold value calculated by the threshold value calculation unit and the degree of coincidence of the latest input image with the pattern model are numerically displayed, and the latest input image is displayed. A second display for numerically displaying a first display format for displaying the threshold, a degree of coincidence of the latest input image with respect to the threshold calculated by the threshold calculation unit and the pattern model, and a past maximum or past minimum coincidence during driving And a display control unit that performs switching control between the two display formats. With the above configuration, the user performs teaching by three points of a non-defective image, a defective product image, and a background image, and compares the matching degree between the live image of the inspection object and the non-defective image with the threshold value from the first display format. From the second display format, it is possible to determine the suitability of the threshold setting from the maximum value and the minimum value of the calculated coincidence, and to switch between the display formats.

  Furthermore, according to the image processing sensor of the third aspect of the present invention, the threshold calculation unit further calculates a threshold value used for quality determination by the quality determination unit, and the setting mode An operation / setting mode switching unit that switches between an operation mode in which the quality determination unit determines the quality of the inspection object using the calculated threshold value, and the display control unit is switched by the operation / setting mode switching unit. The threshold value calculated in the setting mode can be numerically displayed in the operation mode switched by the operation / setting mode switching unit. According to the above configuration, the operation for calculating the threshold for determining the quality of the inspection object and the operation for determining the quality of the inspection object based on the threshold are associated with different modes, and can be arbitrarily switched. Can be displayed.

  The image processing sensor according to the fourth aspect of the present invention further includes a casing having a rectangular outer shape and a plurality of outer surfaces, and the display unit is provided on one surface of the rectangular casing. The display control unit can display the past maximum and the past minimum coincidence during operation on the display unit in parallel.

  Furthermore, according to the image processing sensor of the fifth aspect of the present invention, the display control unit can alternately switch and display the past maximum coincidence during driving and the past minimum coincidence during driving. .

  Still further, according to the image processing sensor of the sixth aspect of the present invention, the display control unit includes, as a third display format, the display unit, the threshold value calculated by the threshold value calculation unit, and the pattern. The degree of coincidence of the latest input image with respect to the model is displayed numerically, and the size of the number constituting the number representing the degree of coincidence of the latest input image is the number constituting the number representing the threshold calculated by the threshold calculation unit. A display format larger than the size is displayed, and in addition to the display by the first display format and the display by the second display format, switching control to the display by the third display format can be performed.

  Furthermore, according to the image processing sensor of the seventh aspect of the present invention, the display control unit has a threshold value calculated by the threshold value calculation unit during operation on the display unit as a fourth display format. Display the display format that numerically displays the past maximum or the past minimum coincidence in the degree of coincidence exceeding, in addition to the display by the first display format and the display by the second display format, It is possible to control switching to display in the fourth display format.

  Furthermore, according to the image processing sensor of the eighth aspect of the present invention, the display control unit is registered in the display unit by the image registration unit as the fifth display format. Display in a display format for displaying the non-defective image and the latest input image, in addition to the display in the first display format and the display in the second display format, to the display in the fifth display format Switching control can be performed.

  Furthermore, according to the image processing sensor of the ninth aspect of the present invention, the threshold value calculation unit calculates a first threshold value and a second threshold value with respect to the coincidence degree calculated by the coincidence degree calculation unit. The image processing sensor is further configured to further include a first determination result and a second determination result by the pass / fail determination unit based on a comparison between the degree of coincidence of the input image and the first threshold and the second threshold. Can be provided, and a channel selector for selecting the two channels can be provided. According to the said structure, the discrimination | determination result in a different threshold value can be output to the channel corresponding to each.

  Furthermore, according to the image processing sensor of the tenth aspect of the present invention, the image processing sensor further associates with the first or second non-defective image registered by the image registration unit and the threshold value calculated by the threshold value calculation unit. A bank setting storage unit that stores a plurality of bank settings, and a bank switching unit that switches to any of the plurality of bank settings stored in the bank setting storage unit. With the above-described configuration, a plurality of bank settings corresponding to registered images and threshold values can be stored, and each bank setting can be read by a bank setting switching operation, so that it is not necessary to perform the setting for each setup change.

  Furthermore, according to the image processing sensor of the eleventh aspect of the present invention, when the coincidence degree is calculated by the coincidence degree calculation unit, the posture rotation of the input image acquired by the imaging unit is allowed. A rotation allowable range setting unit for setting an angle range to be performed can be provided. With the above configuration, the input image can be rotated when calculating the degree of coincidence.

  Furthermore, according to the image processing method of the twelfth aspect of the present invention, an image processing method for detecting whether an inspection object is a non-defective product or a defective product by performing image processing on the image of the inspection object. In addition, a process of registering an image including an inspection object to be determined as a non-defective product as a first non-defective image, and a background image from which a characteristic part of the inspection object to be determined as a non-defective product is removed. From the step of acquiring by the imaging unit and registering as a first background image, the first non-defective image registered by the image registration unit, and the first background image registered by the image registration unit, A first background for a pattern model corresponding to the first non-defective background difference image based on the first non-defective background difference image generated by the difference image generating unit; Special image A step of calculating a degree of coincidence indicating a degree of coincidence, a step of calculating a threshold value used for pass / fail judgment based on the calculated degree of coincidence, and a display unit including a latest value for the calculated threshold value and the pattern model. A first display format for displaying the degree of coincidence of the input image numerically and displaying the latest input image, the degree of coincidence of the latest input image with respect to the calculated threshold value and the pattern model, and the past maximum during operation and / or Alternatively, it is possible to include a step of performing switching control of the two display formats with the second display format in which the past minimum matching degree is numerically displayed. With the above configuration, the user can perform teaching by two points of a non-defective image and a background image, and from the first display format, the user can check the degree of coincidence between the live image of the inspection object and the non-defective image with a threshold value, From the second display format, it is possible to determine the suitability of the threshold setting from the maximum value and the minimum value of the calculated degree of coincidence, and to switch between these display formats.

  Furthermore, according to the image processing method of the thirteenth aspect of the present invention, an image processing method for detecting whether an inspection object is a non-defective product or a defective product by performing image processing on the image of the inspection object. A step of registering an image including an inspection object to be determined as a non-defective product as a second non-defective image, and a step of registering an image including the inspection target to be determined as a defective product as a defective image. A step of acquiring an image of a background from which a characteristic part as a non-defective product of the inspection object is removed by the imaging unit and registering it as a second background image; and a second non-defective image registered by the image registration unit; From the second background image registered by the image registration unit, a second non-defective background difference image from the second background image registered by the image registration unit and the second background image registered by the image registration unit Defective product background A step of generating each of the partial images, a step of calculating a degree of coincidence indicating a feature matching degree of the defective product background difference image with respect to the pattern model corresponding to the generated second non-defective background difference image, and the calculated Based on the degree of coincidence, a step of calculating a threshold value used for pass / fail judgment, and the display unit numerically displays the degree of coincidence of the latest input image with the calculated threshold value and the pattern model, and the latest input image is displayed. A first display format to be displayed, a second display format for numerically displaying a degree of coincidence of the latest input image with respect to the calculated threshold value and the pattern model, and a past maximum and / or a past minimum coincidence during operation. And a step of performing switching control between the two display formats. With the above configuration, the user performs teaching by three points of a non-defective image, a defective product image, and a background image, and compares the matching degree between the live image of the inspection object and the non-defective image with the threshold value from the first display format. From the second display format, it is possible to determine the suitability of the threshold setting from the maximum value and the minimum value of the calculated coincidence, and to switch between the display formats.

  Furthermore, according to the image processing program of the fourteenth aspect of the present invention, an image processing program for detecting whether an inspection object is a non-defective product or a defective product by performing image processing on the image of the inspection object. In addition, a function for registering an image including an inspection object to be determined as a non-defective product as a first non-defective image and a background image from which a characteristic part of the inspection object to be determined as a non-defective product is removed. From the function acquired by the imaging unit and registered as a first background image, the first good image registered by the image registration unit, and the first background image registered by the image registration unit, A first non-defective background difference image and a first model for a pattern model corresponding to the first good background difference image based on the first good background difference image generated by the difference image generation unit; A function for calculating a matching degree indicating a feature matching degree of a scene image, a function for calculating a threshold value used for pass / fail discrimination based on the calculated matching degree, and a display unit configured to calculate the threshold value and the pattern The degree of coincidence of the latest input image with respect to the model is numerically displayed, the first display format for displaying the latest input image, the degree of coincidence of the latest input image with respect to the calculated threshold value and the pattern model, and during operation It is possible to cause a computer to realize a function of performing switching control between two display formats, that is, a second display format in which a past maximum and / or a past minimum coincidence is numerically displayed. With the above configuration, the user can perform teaching by two points of a non-defective image and a background image, and from the first display format, the user can check the degree of coincidence between the live image of the inspection object and the non-defective image with a threshold value, From the second display format, it is possible to determine the suitability of the threshold setting from the maximum value and the minimum value of the calculated degree of coincidence, and to switch between these display formats.

  Furthermore, according to the image processing program of the fifteenth aspect of the present invention, an image processing program for detecting whether an inspection object is a non-defective product or a defective product by performing image processing on the image of the inspection object. A function for registering an image including an inspection object to be determined as a non-defective product as a second non-defective image, and a function for registering an image including an inspection object to be determined as a defective product as a defective image. A function of acquiring an image of a background from which a characteristic part as a non-defective product of an inspection object is removed by the imaging unit and registering it as a second background image, and a second non-defective image registered by the image registration unit The second non-defective background difference image from the second background image registered by the image registration unit, the defective product image registered by the image registration unit, and the second background image registered by the image registration unit, etc. A function of generating a defective product background difference image, a function of calculating a matching degree indicating a feature matching degree of the defective product background difference image with respect to the pattern model corresponding to the generated second non-defective background difference image, and Based on the calculated degree of coincidence, a function for calculating a threshold value used for pass / fail judgment, and the display unit numerically displays the degree of coincidence of the latest input image with respect to the calculated threshold value and the pattern model. First display format for displaying an input image, second display for numerically displaying the degree of coincidence of the latest input image with respect to the calculated threshold value and the pattern model, and the past maximum and / or the past minimum coincidence during driving And a function of performing switching control of two display formats, that is, a format, can be realized in a computer. With the above configuration, the user performs teaching by three points of a non-defective image, a defective product image, and a background image, and compares the matching degree between the live image of the inspection object and the non-defective image with the threshold value from the first display format. From the second display format, it is possible to determine the suitability of the threshold setting from the maximum value and the minimum value of the calculated coincidence, and to switch between the display formats.

  Furthermore, a computer-readable recording medium storing a program according to the sixteenth aspect of the present invention stores the program. CD-ROM, CD-R, CD-RW, flexible disk, magnetic tape, MO, DVD-ROM, DVD-RAM, DVD-R, DVD + R, DVD-RW, DVD + RW, Blu-ray (registered) Trademark), BD-R, BD-RE, HD DVD (AOD), and other magnetic disks, optical disks, magneto-optical disks, semiconductor memories, and other media that can store programs. The program includes not only a program stored in the recording medium and distributed but also a program distributed by download through a network line such as the Internet. Further, the recording medium includes a device capable of recording a program, for example, a general purpose or dedicated device in which the program is implemented in a state where it can be executed in the form of software, firmware, or the like. Furthermore, each process or function included in the program may be executed by program software that can be executed by a computer, or each part of the process or function may be executed by hardware such as a predetermined gate array (FPGA, ASIC), or program software. And a partial hardware module that realizes a part of hardware elements may be mixed.

It is a schematic diagram which shows the image processing sensor which concerns on Embodiment 1 of this invention. It is a schematic diagram which shows the image processing sensor which concerns on Embodiment 2 of this invention. It is a block diagram of an image processing sensor. FIG. 4A is a diagram illustrating an internal configuration of an integrated image processing sensor, and FIG. 4A is a diagram illustrating a state in which the main substrate is attached, and FIG. 4A is a diagram in which the main substrate is removed and the optical base is exposed. FIG. FIG. 5A is a diagram of the casing as viewed from the upper surface side, and FIG. 5B is a diagram of the casing as viewed from the lower surface side. It is a schematic diagram which shows one surface of the casing of an image processing sensor. It is a block diagram which shows the function of an image processing sensor. It is a flowchart which shows the procedure of two-point teaching which registers a quality product image and a defective product image. It is an image figure which shows the driving | running screen of a display part. It is an image figure which shows the example of the 1st registration screen at the time of two-point teaching. It is an image figure which shows the state which displayed the good quality image in FIG. It is an image figure which shows the driving | operation screen of a display part, Comprising: FIG. 12A is a display by a 3rd display format, FIG. 12B is a display by a 1st display format, FIG. 12C is by a 2nd display format. FIG. 12D is a display according to the fourth display format, and FIG. 12E is a display according to the fifth display format. It is explanatory drawing of the 2nd display format which switches and displays the maximum coincidence degree and the minimum coincidence degree alternately. It is a figure which shows the relationship between a coincidence degree and a sampling period for demonstrating the maximum / minimum coincidence degree. It is a figure which shows the relationship between a coincidence degree and a sampling period for demonstrating coincidence degree statistical values, such as a peak maximum value at the time of ON. FIG. 16A is an image diagram showing an operation screen of the display unit, in which FIG. 16A is a display in which a live image and a non-defective image are juxtaposed in the fifth display format, and FIG. This is a display in which non-defective images are arranged in parallel. It is an image figure which shows the operation screen of a display part, Comprising: FIG. 17A is a display by a 2nd display format, FIG. 17B is a display by the modification of a 2nd display format, FIG. FIG. 17D is a display according to a modification of the fourth display format, FIG. 17E is a display according to the fifth display format, and FIG. 17F is a modification of the fifth display format. It is a display by. It is the figure which expanded and showed the display format shown to FIG. 17B. It is an image figure which shows the driving | operation screen of a display part, Comprising: FIG. 19A is a display by the modification of the display format shown to FIG. 17B, FIG. 19B is a display by the modification of the display format shown to FIG. It is the figure which expanded and showed the display format shown to FIG. 17D. It is the figure which expanded and showed the display format shown to FIG. 17F. FIG. 22A is a diagram illustrating a screen table for explaining the output channel setting unit, and FIG. 22B is a diagram illustrating a relationship between a threshold value and pass / fail judgment for each output channel. It is explanatory drawing about a bank setting. It is explanatory drawing about a rotation permissible range setting part. It is an image figure which shows the driving | running screen of a display part, Comprising: FIG. 25A is (1) default display, FIG. 25B is (2) 90 degree rotation display, FIG. 25C is (3) 180 degree rotation. FIG. 25D is a display rotated by (4) 270 °. It is an image figure which shows the operation screen of a display part, Comprising: FIG. 26A has shown the operation screen displayed by (1) the 1st display format without rotation, and a 5th display format, FIG. ) The operation screens displayed in the first display format and the fifth display format rotated 180 ° are shown. For explaining the screen inversion function, FIG. 27A shows the screen display before the reverse display, and FIG. 27B shows the screen display reversely displayed by the screen reverse function. It is an image figure which shows the expansion / contraction function of an image. FIG. 29A is a setting screen for performing registered image processing, and FIGS. 29B and 29C are operation screens displayed in the first display format and the third display format, respectively. FIG. 10 is an image diagram of a selection screen for selecting whether a non-defective image is operated as a master image or a defective image is operated as a master. It is an image figure which shows the example of the 2nd registration screen at the time of two-point teaching. It is an image figure which shows the example which displayed the background image except the workpiece | work from FIG. It is a flowchart which shows the procedure of two-point teaching which registers a quality product image and a background image. It is an image figure which shows the 2nd registration screen which registers a "no detection workpiece" image at the time of two-point teaching. FIG. 34A is a schematic diagram showing a state in which a simple difference image for extracting only a non-defective work is generated by removing a background image from a non-defective image, and FIG. It is a schematic diagram which shows a mode that the simple difference image which extracts only this is produced | generated. It is a flowchart which shows the procedure of three-point teaching. It is a flowchart which shows the procedure of three-point teaching. It is an image figure which shows the example of the 1st registration screen at the time of three-point teaching. It is an image figure which shows the example of the 2nd registration screen at the time of three-point teaching. It is an image figure which shows the example of the 3rd registration screen at the time of three-point teaching. It is a flowchart which shows the procedure of one point teaching which registers a quality product image or a background image. It is an image figure which shows a background image. It is an image figure which shows a mode that an evaluation area | region is set with respect to the background image of FIG. It is a flowchart which shows the operation | movement procedure of a setting when a discrimination | determination object is inferior goods workpiece | work. It is a table which shows an example of threshold setting. It is an image figure which shows the other example of the 1st registration screen at the time of two-point teaching. It is an image figure which shows the other example of the 2nd registration screen at the time of two-point teaching. It is an image figure which shows the further another example of the 1st registration screen at the time of two-point teaching. It is an image figure which shows the further another example of the 2nd registration screen at the time of two-point teaching. It is an image figure which shows the example which switches and displays a 1st registration screen. It is an image figure which shows the example which switches and displays a 2nd registration screen. It is an image figure which shows the example which switches and displays the candidate image which is going to register and the registered good quality image on the 2nd registration screen. It is an image figure which shows the example which switches and displays the candidate image which is going to register and parallel display in a 2nd registration screen. It is an image figure which shows the example which made the 2nd registration screen at the time of three-point teaching the parallel display screen. It is a flowchart which shows the procedure of a still image and live image simultaneous display. It is an image figure which shows the example which made the 3rd registration screen at the time of three-point teaching the parallel display screen. It is an image figure which shows the example which overlapped the image display area and the description display area partially. It is an image figure which shows the example which made the image display area and the description display area overlap completely. It is a flowchart which shows the procedure which increases / decreases the display magnification of an image. It is a flowchart which shows the procedure which performs the setting of a 1st threshold value and a 2nd threshold value in setting mode. It is a schematic diagram which shows a mode that an operation mode and setting mode are switched. It is a flowchart which shows the procedure which increases / decreases a threshold value. It is a flowchart which shows the operation | movement procedure at the time of the bank setting change during driving | operation. It is a flowchart which shows the calculation procedure of the maximum coincidence degree and the minimum coincidence degree among the coincidence degree statistics during driving. It is a flowchart which shows the operation | movement procedure at the time of a driving | operation in case a discrimination | determination object is inferior goods workpiece | work. It is an image figure which shows the state in which the quality goods workpiece and the inferior goods workpiece | work flow on the manufacturing line. FIG. 65A is an image diagram illustrating the flow of a work, and FIG. 65B is an image diagram of a time-series change of the first degree of coincidence for explaining the output state when the master image is a non-defective image. FIG. FIG. 65D is an image diagram showing a time-series change of output, and FIG. 65D says that the output logic is inverted with respect to the time-series change of output shown in FIG. It is an image figure which shows the time-sequential change of the output at the time of setting. FIG. 66A is an image diagram showing a work flow, and FIG. 66B is an image diagram of a time-series change of the second degree of coincidence, for explaining an output state when the master image is a defective product image. 66C is an image diagram showing a time-series change in output. It is a screen display during a driving | running | working, Comprising: It is a figure which shows a mode that a screen display switches in order of the screen A, the screen B, the screen C, and the screen D. It is a flowchart which shows the operation | movement procedure of the normal driving | operation process which does not replace a registration image. It is a flowchart which shows the operation | movement procedure of replacement of the registered image in two-point teaching. It is a flowchart which shows the operation | movement procedure of replacement of the registered image in three-point teaching. It is an image figure which shows the example of the screen transition of an operation mode. It is an image figure which shows the example of the screen transition of an operation mode. It is a flowchart which shows operation | movement of the setting mode including the process of adjusting the display magnification of an image. It is a flowchart which shows operation | movement of the operation mode including the process of adjusting a threshold value. It is a block diagram which shows the internal process of the conventional image processing sensor. It is a block diagram which shows the internal process of the image processing sensor which concerns on embodiment. It is a schematic diagram which shows a mode that the resolution of an image is reduced. It is a schematic diagram which shows a mode that image data is averaged and compressed. It is a schematic diagram which shows a mode that image data is thinned out and compressed. It is a flowchart which shows the procedure of a setting and a driving | operation in the case of performing a difference image generation process after a resolution reduction process in the two-point teaching of a good product image and a background image. It is a flowchart which shows the procedure of the setting and driving | operation in the case of performing resolution reduction processing after difference image generation processing in two-point teaching of a non-defective image and a background image. It is a flowchart which shows the setting and operation | movement procedure in the case of performing a difference image generation process after a resolution reduction process in the three-point teaching of a quality product image, a defective product image, and a background image. It is a flowchart which shows the setting and operation | movement procedure in the case of performing resolution reduction processing after difference image generation processing in three-point teaching of a non-defective product image, a defective product image, and a background image. It is a flowchart which shows the procedure of the one point teaching which registers the background image containing a resolution reduction process. It is a schematic diagram which shows the procedure which determines the optimal brightness condition of an image when response time can be set. It is a schematic diagram which shows the procedure which determines the optimal brightness condition of an image when response time is made into a default value. It is a flowchart which shows the procedure which finds suitable registration setting conditions from the candidate group of registration setting conditions, and performs image registration. 86A is a flowchart showing a series of image processing before replacing the image processing algorithm, FIG. 86B is a flowchart showing a series of image processing after replacing some image processing algorithms from FIG. 86A, FIG. 86C is a non-defective image, FIG. 86D is a defective image, FIG. 86E is a background image, FIG. 86F is an evaluation image, FIG. 86G is an image of a work, FIG. 86H is an image obtained by cutting out a work from the evaluation image of FIG. 86F, and FIG. 86E is an image obtained by cutting out the work area by the difference processing of the background image of 86E, and FIG. 86J is an image diagram showing the work area cut out from the evaluation image of FIG. 86H. 87A is a flowchart showing a series of image processing before replacing the image processing algorithm, FIG. 87B is a flowchart showing a series of image processing after replacing some image processing algorithms from FIG. 87A, and FIG. 87C is a non-defective image, FIG. 87D is a defective product image, FIG. 87E is a background image, FIG. 87F is an evaluation image, FIG. 87G is an image of a work, FIG. 87H is an image obtained by cutting out a work from the evaluation image of FIG. 87F, and FIG. 87E is an image obtained by cutting out the work area by the difference processing of the background image of 87E, and FIG. 87J is an image diagram showing the work area cut out from the evaluation image of FIG. 87H. 88A is a schematic diagram showing SobelX of the Sobel filter, FIG. 88B is SobelY, and FIG. 88C is an X and Y component of the edge multiplied by SobelX and SobelY. 89A is RobertsX of the Roberts filter, FIG. 89B is RobertsY, and FIG. 89C is a schematic diagram showing the X and Y components of the edge multiplied by RobertsX and RobertsY. 6 is a flowchart illustrating a procedure for resetting brightness conditions according to the first embodiment. FIG. 91 is a flowchart showing a detailed procedure of registration processing in FIG. 90. FIG. It is a flowchart which shows the operation | movement procedure in the case of changing response time after a teaching process. It is a flowchart which shows the procedure of the registration process in the combination of ON / OFF of HDR and exposure time. It is a flowchart which shows the operation | movement procedure in the case of changing response time after a teaching process.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings. However, the embodiment described below is an example for embodying the technical idea of the present invention, and the present invention is not limited to the following. Moreover, this specification does not specify the member shown by the claim as the member of embodiment. In particular, the dimensions, materials, shapes, relative arrangements, and the like of the component parts described in the embodiments are not intended to limit the scope of the present invention only to specific examples unless otherwise specifically described. Only. Note that the size, positional relationship, and the like of the members shown in each drawing may be exaggerated for clarity of explanation. Furthermore, in the following description, the same name and reference sign indicate the same or the same members, and detailed description will be omitted as appropriate. Furthermore, each element constituting the present invention may be configured such that a plurality of elements are constituted by the same member and the plurality of elements are shared by one member, and conversely, the function of one member is constituted by a plurality of members. It can also be realized by sharing.

An image processing sensor 1 according to Embodiment 1 of the present invention is shown in FIG. 1, and an image processing sensor 11 according to Embodiment 2 is shown in FIG. FIG. 1 shows a separate image processing sensor 1 having a sensor unit 2 and a controller unit 3, and FIG. 2 shows an integrated image processing sensor 11 in which the sensor unit 2 and the controller unit 3 are integrated. The sensor unit 2 includes an imaging unit 21 such as a camera 211 and an illumination 212, while the controller unit 3 is a member that performs image processing on an image of a work WK that is an inspection target imaged by the imaging unit 21. is there. Such sensor unit 2 and controller unit 3 can be stored in different casings (housings) or in a common casing.
(Hardware block diagram)

  A block diagram of such image processing sensors 1 and 11 is shown in FIG. As shown in this figure, the hardware configuration of the image processing sensors 1 and 11 mainly includes a display substrate 31, a power supply substrate 32 (24) for supplying power to each connected part, and a main substrate 33 ( 25), the illumination substrate 22, and the imaging substrate 23. In FIG. 3, broken lines are marks for functionally separating the block of the sensor unit 2 and the block of the controller unit 3, the right side in the drawing is the block of the sensor unit 2, and the left side in the drawing is the controller unit 3. Shows the block. In the case of the separation type image processing sensor 1, the casing of the sensor unit 2 accommodates the illumination board 22, the imaging board 23, the power supply board 24 including the LED driver 241, and the main board 25 including the DSP 251 and the memory 252. The display substrate 31, the power supply substrate 32, and the main substrate 33 are accommodated in the casing of the controller unit 3.

  The operation of the camera 211 in the imaging unit 21 is controlled by the main board 33 (25) via the CMOS 231 of the imaging board 23. The operation of the illumination 212 in the imaging unit 21 is controlled by the main board 33 (25) via the LED 221 on the illumination board 22 and the LED driver 241 on the power supply board 32 (24). For example, a focus control unit (not shown) is driven by driving a motor (not shown) of the imaging unit 21 in accordance with a control signal for controlling an autofocus operation from the main board 33 (25). Move back and forth to control autofocus operation. Then, the workpiece WK is imaged according to the imaging instruction signal from the main board 33 (25).

  The image pickup substrate 23 includes a CMOS 231. An image picked up by the CMOS 231 is subjected to filter processing by the DSP 251, for example, and image data after image processing is output. In the case of the separation type image processing sensor 1, the DSP 251 is provided on the sensor unit 2 side in the above description. However, the present invention is not limited to this. For example, the DSP 251 is provided on the main board 33, that is, the controller unit 3 side. Also good. In this case, since image conversion processing or the like with a large calculation processing load is not executed by the sensor unit 2, the semiconductor device provided in the sensor unit 2 can be downsized, or the necessity of arranging in consideration of heat radiation is relatively high. Therefore, the sensor unit 2 can be reduced in size.

  The main board 33 (25) controls the operation of each part to which the DSP 251 and the MCU 331 are connected. The DSP 251 basically performs processing up to imaging the workpiece WK and image processing. The MCU 331 receives an image processing result from the DSP 251, and an ON / OFF signal indicating the presence / absence of the work WK indicating whether the work WK has been detected, or an OK / NG signal (determination signal) indicating whether the work WK is good Is output to the outside or displayed on the OLED 311 of the display substrate 31.

  The DSP 251 transmits a control signal for controlling lighting / extinguishing of the LEDs 221 to the LED board 241 of the power supply board 32 (24). The LED driver 241 adjusts, for example, lighting / extinguishing of the LED 221 and the amount of light according to a control signal from the DSP 251. Further, the DSP 251 sends a control signal for controlling the autofocus operation to a motor (not shown) of the imaging unit 21 via a motor driver (not shown) of the main board 33 (25). The imaging instruction signal and the like are transmitted to the imaging board 23, respectively.

  There are two types of memory 252, a nonvolatile memory and a volatile memory, in association with the DSP 251, in order to store captured images or to store various settings. .

The MCU 331 mainly controls external output and display. The OLED 311 displays, for example, a still image (details will be described later) used for setting in addition to the result of image processing such as the degree of coincidence (details will be described later) as a variable for comparison with a threshold value. Further, the MCU 331 receives an ON / OFF signal indicating whether or not the work WK is detected as a result of the image processing via the external communication 321 of the power supply board 32 (24), and indicates whether or not the work WK is present. An OK / NG signal (determination signal) indicating good / bad is output. An ON / OFF signal and an OK / NG signal are respectively transmitted from an I / O connector (not shown) provided in the controller unit 3 via an external communication 321 of the power supply board 32 (24) to an I / O cable (see FIG. (Not shown) and output to an external PLC or the like.
(Lighting 212)

The illumination 212 is a member for irradiating illumination light when the imaging unit 21 captures an image of the workpiece WK. As a light source of illumination light, an LED, an organic EL, an incandescent bulb, a halogen lamp, or the like can be used. The illumination light may be of any color when a monochrome image is captured as an optical image. For example, when the line transport speed is high, the exposure time that can be taken to capture a single optical image is also shortened, so a light source with a large amount of light should be used to ensure sufficient brightness in a short time. Is preferred. From such a viewpoint, a red light source that is inexpensive and can easily obtain a light amount can be suitably used. Note that white light is used when capturing a color optical image. That is, the illumination color may be a parameter as a brightness condition according to the color or material to be determined.
(Structure of the integrated image processing sensor 11)

  FIG. 4 is a structural diagram showing an internal configuration of the integrated image processing sensor 11, FIG. 4A is a diagram showing a state in which the main board 25 is attached, and FIG. 4B is a diagram in which the main board 25 is removed. The optical base 403 is exposed. As shown in these drawings, the rear case 404 is fixed to the heat insulating case 402 with four metal screws. The heat insulating case 402 is fixed to the front case 401 with four metal screws. The optical base 403 is fixed to the front case 401.

The front case 401 and the rear case 404 are made of, for example, zinc die casting, and the front case 401 includes a connector 48 in a casing. The optical base 403 is a part in which an illumination reflector and a lens barrel are integrated, and the illumination board 22 and the imaging board 23 are fixed. The heat insulating case 402 is made of, for example, resin, and the front / rear temperature difference can be set by adjusting the cross-sectional shape (cross-sectional area) / material / height. The heat insulating case 402 is individually fixed to the front / rear for heat insulation (not fastened together).
(Case 4 of integrated image processing sensor 11)

  The casing 4 of the integrated image processing sensor 11 is formed in a hexahedron shape including upper and lower surfaces, left and right surfaces, and front and rear surfaces. Among these, the upper surface is the first main surface, and the lower surface facing the upper surface is the second main surface. As shown in FIGS. 5A and 5B, a camera 211 and an illumination 212 are provided on the second main surface on the lower surface side. On the other hand, a display screen 43 (corresponding to an example of a “display unit” in claims) and an operation button 4C are provided on the first main surface on the upper surface side. Thus, the second main surface on the lower surface side is the imaging surface 4b, and the first main surface on the upper surface side is the display surface 4a, so that the image captured on the imaging surface 4b is displayed on the display surface 4a, The layout and layout of the image processing sensor 11 can be matched.

The camera 211 is arranged in parallel to the imaging surface 4b, and is configured so that the optical axis of the imaging element is substantially orthogonal to the imaging surface 4b. Thereby, an orthogonal image of the workpiece WK at the imaging position below the image processing sensor 11 can be captured. On the other hand, the illumination 212 slightly tilts the light projection surface with respect to the imaging surface 4b. By making the optical axis of the illumination light oblique to the optical axis of the image sensor, an image can be captured with a natural shadow. In the example of FIG. 5A, the light source of the illumination light is one, but a plurality of them can be provided. For example, illumination light sources are provided at the four corners of the imaging surface so as to surround the imaging unit 21. As a result, an image with less shadow can be obtained.
(Display surface 4a of casing 4)

The display surface 4a of the casing 4 of the image processing sensor 11 is shown in the schematic diagram of FIG. As shown in this figure, the display surface 4a of the casing 4 includes a determination result display lamp 41 for displaying a determination result, a SET key 42 for registering an image, an image processing result, a setting instruction, and the like. A display screen 43 for displaying, an up / down key 44 for adjusting a threshold value and enlarging / reducing an image, a BACK key 45 for re-setting, a screen display layout change, and a detailed setting change A MODE key 46 for performing the operation and an output state indicator lamp 47 for displaying the state of the determination output.
(Cover 3B)

  Moreover, you may provide the cover part 3B in the display surface 4a. By providing the cover portion 3B, it is possible to avoid a situation in which the user's hand or the like accidentally touches the operation button 4C and the setting of the coincidence threshold value is changed unintentionally. In the example of FIG. 1, a cover 3 </ b> B that covers the display screen 43 is provided to be openable and closable. In this example, the cover portion 3B is pivotably connected to one end in the longitudinal direction of the display surface 4a so as to be opened and closed. Moreover, the cover part 3B is comprised with the member which has translucency, and even if the cover part 3B is closed, the display screen 43 can be visually recognized. The cover portion 3B can be made of resin or the like.

Moreover, it is good also as a structure which does not provide a cover part. FIG. 2 shows an example of the image processing sensor 11 that is not provided with a cover portion. The operation button 4C may be provided with a key lock function in case the cover portion is not provided. By using the key lock function, even if the operation button 4C is touched, there is no response, and an unintended setting change can be avoided. When performing an operation, a specific release operation is performed to release the key lock function. Such a release operation can be performed, for example, by long pressing a specific key.
(Judgment result indicator lamp 41)

The determination result display lamp 41 is a member that displays whether the work WK is a non-defective product or a defective product by, for example, lighting in green or red with a difference in lighting color. The determination result display lamp 41 indicates the result determined in the operation mode by lighting. For example, if a good product is detected, it is lit in blue, and if a defective product is detected, it is displayed in red. For such an output indicator lamp, a light emitter such as an LED can be used. Further, it is preferable that the emission color can be changed. For example, a multi-color LED having a red LED and a blue LED or having a variable color can be used.
(SET key 42)

The SET key 42 is a member for registering a display image as a registered image. When this button is pressed in the setting mode, the display image is registered. Further, when setting a registered image, the screen can be changed by pressing the SET key 42.
(Display screen 43)

The display screen 43 is a member for displaying an image of the workpiece WK imaged by the imaging unit 21. As the display screen 43, an organic EL (OLED), a liquid crystal (LCD), or the like can be used. The display screen 43 is different from a photoelectric sensor that employs a 7-segment display, and displays a still image such as a registered image, a live image LVI, and first registration guidance information, and there is a need for downsizing. Resolution is preferable, and for example, organic EL is employed.
(Up / Down key 44)

The up / down key 44 is a member for adjusting a threshold and enlarging / reducing an image. After registration of an image such as a non-defective image OKI is completed, in the operation mode, a threshold value is displayed together with the degree of coincidence of the registration screen every time the SET key 42 is pressed and the registration screen is changed. The up / down key 44 can manually increase or decrease the threshold value. In addition, the up / down key 44 has a function of enlarging or reducing the image in a setting mode for registering an image such as a non-defective image OKI.
(BACK key 45)

The BACK key 45 is a member for redoing the setting. In the setting mode for registering an image such as a non-defective image OKI, even if it is not a desired display image, the display image is registered by pressing the SET key 42, and the setting of the next registered image is prompted. In such a case, it is possible to return to the registration of the display image that was not desired and register again.
(MODE key 46)

The MODE key 46 is a member for changing the display layout of the display screen 43. The MODE key 46 can be switched to the detailed setting mode. In the operation mode, the display image is switched by pressing the MODE key 46, and the mode is switched to the detailed setting mode by long pressing.
(Output status indicator 47)

The output state indicator lamp 47 is a member for displaying the state of the determination output, and an LED or the like can be used. The output status indicator 47 does not display the determination result but displays an output status indicating whether the image processing sensors 1 and 11 are ON or OFF. The operation button 4C, the determination result display lamp 41, and the output state display lamp 47 described above can be configured virtually on the display in addition to the physical buttons and lamps. For example, the display surface 4a is configured by a touch panel, and the display screen 43, the operation buttons 4C, the determination result display lamp 41, and the output state display lamp 47 are displayed as images on the display surface 4a to function as virtual buttons and lamps. You can also
(Connector 48)

Moreover, the connector 48 which connects a cable is arrange | positioned in any one of the front surface or the back surface among the surfaces which comprise the hexahedron shape of the casing 4. FIG. In the example of FIG. 5A, FIG. 5B, etc., the cylindrical connector 48 is provided in the back side (right side in a figure). As shown in FIG. 1, in the case of the sensor unit 2 and the separation-type image processing sensor 1, a sensor unit side connector 3A for connecting the sensor unit 2 is provided on the front side.
(Function block diagram)

Further, FIG. 7 shows a detailed block diagram taken from the functional aspects of the image processing sensors 1 and 11. As shown in this figure, the image processing sensors 1 and 11 receive an operation instruction from the user, and an operation unit 51 for transmitting the operation instruction to the main control unit 61, an image is captured, and the captured image is subjected to main control. An imaging unit 52 for delivery to the unit 61, a display unit 53 for displaying the current sensor state and the instruction content to the user, and an image / setting storage unit 54 for storing images and settings. , A condition assigning unit 55 for performing adjustment for determining an optimum registration condition by changing the registration condition pattern, and set image processing for performing image processing registration based on the image so that the target image can be evaluated Based on the information input from the operation unit 51, the operation unit 51, and the imaging unit 52, the image / setting storage unit 54, the condition allocation unit 55, setting image processing unit 6, and controls the driving image processing unit 57, and a setting managing unit 58 for displaying on the display unit 53. The role of each block will be described below.
(Operation unit 51)

  The operation unit 51 is a member that receives an operation instruction from a user and transmits the operation instruction to the main control unit 61. Specifically, the operation unit 51 includes at least a SET key 42, an up / down key 44, a MODE key 46, a BACK key 45, and a touch panel. For example, according to a button operation of the SET key 42, an operation state, that is, a display content on the display screen 43. The main control unit 61 is instructed for various corresponding operation instructions. For example, on the first registration screen shown in FIG. 11 to be described later, by pressing the SET key 42 included in the operation unit 51, the live image LVI displayed at this point in the image display area PD is registered as a non-defective image OKI. A non-defective image OKI registration instruction is given. In the second registration screen shown in FIG. 33, when the SET key 42 is pressed, a background image BGI registration instruction for registering the live image LVI displayed in the image display area PD as the background image BGI is given.

  Furthermore, the operation unit 51 can give a plurality of operation instructions. For example, when the SET key 42 is pressed on the first registration screen in FIG. 11, the display screen 43 is changed from the first registration screen to the second registration screen in addition to the above-described non-defective image OKI registration instruction for registering the non-defective image OKI. The main control unit 61 is instructed to make a screen transition instruction for transition. By assigning a plurality of such operation instructions to the SET key 42 included in the operation unit 51, user operability is improved. In other words, by performing a plurality of operations by one operation of the operation unit of pressing the SET key 42, an advantage that the user can smoothly perform the registration work without being aware of switching of the registration screen or the like is obtained.

More specifically, in the operation unit 51, the user's operation is performed by the non-defective product image setting unit 51a, the defective product image setting unit 51b, and the background image setting unit 51c, and the setting management unit 58 stores the image to be registered. From the number and order, the live image LVI displayed at the time of setting is registered in association with any of the non-defective product image OKI, the defective product image NGI, and the background image BGI.
(Non-defective image setting unit 51a)

The non-defective image setting unit 51 a is a member that receives an operation instruction for registering a non-defective image OKI from the user and transmits the operation instruction to the main control unit 61. The guidance display control unit 58a of the setting management unit 58 displays the non-defective image OKI registration instruction read from the registration identification instruction information storage unit 54h of the image / setting storage unit 54 on the display screen 43 by the operation instruction display unit 53f. The live image display unit 53a displays the live image LVI captured by the image acquisition unit 52 on the display screen 43 while updating it repeatedly. When the SET key 42 is pressed under this situation, the non-defective image setting unit 51a transmits this operation instruction to the image access unit 58c of the setting management unit 58. Based on this operation instruction, the image access unit 58c saves the live image LVI when pressed down in the non-defective image storage unit 541a of the image / setting storage unit 54 as a non-defective image OKI.
(Defective product image setting unit 51b)

  The defective product image setting unit 51 b is a member that receives an operation instruction for registering a defective product image NGI from the user and transmits the operation instruction to the main control unit 61. The guidance display control unit 58a of the setting management unit 58 displays the defective product image NGI registration instruction read from the registration identification instruction information storage unit 54h of the image / setting storage unit 54 on the display screen 43 by the operation instruction display unit 53f. At the same time, the live image display unit 53a displays the live image LVI captured by the image acquisition unit 52 on the display screen 43 while updating it repeatedly. When the SET key 42 is pressed in this situation, the defective product image setting unit 51b transmits this operation instruction to the image access unit 58c of the setting management unit 58. Based on this operation instruction, the image access unit 58c stores the live image LVI when pressed down in the defective product image storage unit 542a of the image / setting storage unit 54 as a defective product image NGI.

When setting the defective product image NGI, the still image display unit 53b of the display unit 53 is stored in the non-defective product image storage unit 541a of the image / setting storage unit 54 via the image access unit 58c of the setting management unit 58. The non-defective product image OKI is displayed on the display screen 43. Thus, the user can set the defective product image NGI while comparing with the non-defective product image OKI when setting the defective product image NGI.
(Background image setting unit 51c)

The background image setting unit 51 c is a member that receives an operation instruction for registering the background image BGI from the user and transmits the operation instruction to the main control unit 61. The guidance display control unit 58 a of the setting management unit 58 displays on the display screen 43 the background image BGI registration instruction read out from the registration identification instruction information storage unit 54 h of the image / setting storage unit 54 by the operation instruction display unit 53 f. In this situation, when the SET key 42 is pressed, the background image setting unit 51c transmits this operation instruction to the image access unit 58c of the setting management unit 58. Based on this operation instruction, the image access unit 58c saves the live image LVI when pressed down in the background image storage unit 543a of the image / setting storage unit 54 as the background image BGI.
(Registration mode switching unit 51k)

The registration mode switching unit 51k has a three-point teaching mode in which the state is transitioned between the first registration screen, the second registration screen, and the third registration screen by a screen transition unit 58b described later, and the first registration by the screen transition unit 58b. It is a member for selecting to switch between the two-point teaching mode for changing the state between the screen and the third registration screen. Note that the registration mode switching unit 51k may be able to switch to a one-point teaching mode in which, for example, only one image is acquired and the presence / absence of the object is determined. As will be described later, for example, when the SET key 42 is short-pressed, a progress bar for starting the two-point teaching setting mode is displayed using the entire surface of the display screen 43 as shown in FIG. 72B. Switches to the 2-point teaching setting mode. Further, for example, when the SET key 42 is pressed and held, a progress bar for starting the three-point teaching setting mode is displayed using the entire surface of the display screen 43 as shown in FIG. 72C. Switch to teaching setting mode.
(Screen display switching unit 51f)

The screen display switching unit 51f is a member for switching between screen display in the first display format and screen display in the second display format. In the display unit 53, the display control unit 58f performs various displays in the first display format or the second display format switched by the screen display switching unit 51f. The screen display to be switched by the screen display switching unit 51f may be, for example, the third to fifth display formats in addition to the first display format and the second display format, and is limited to these. Nor. FIG. 12A is a screen display that is displayed in a preset standard state during operation after the teaching is completed.
(First display format: live image LVI and degree of matching and threshold)

The first display format is, for example, as shown in FIG. 12B, on the display screen 43, a live image LVI and an explanation display area for displaying an explanation in an image display area PD (Picture Display Area) for displaying an image. In ED (Explanation Display Area), a threshold value 4314a that is a numerical value display of the threshold value calculated by the threshold value calculation unit 56c, and a matching degree 4313a that is a numerical value display of the matching degree of the live image LVI with respect to a pattern model such as a difference image or an edge Is a display format for displaying. As described above, the live image LVI, the threshold value 4314a, and the coincidence degree 4313a are displayed in the first display format on the operation screen that is a display screen in the operation mode in which the quality determination of the work WK is performed. In the comparison between the image LVI and the threshold value, it is possible to determine whether or not the degree of coincidence between the work WK and the non-defective image OKI is appropriate.
(Second display format: maximum / minimum match and match and threshold)

  For example, as shown in FIG. 12C, the second display format includes a threshold value 4314a that is a numerical value display of the threshold value calculated by the threshold value calculation unit 56c on the display screen 43, and a live image for a pattern model such as a difference image or an edge. The coincidence 4313a which is a numerical display of the LVI coincidence, the maximum coincidence 4319a which is the numerical display of the maximum past coincidence during driving, and the minimum coincidence 4320a which is a numerical display of the past minimum coincidence during driving. Is a display format for displaying. In the second display format, as shown in FIG. 13, for example, the maximum matching degree 4319a and the minimum matching degree 4320a are alternately switched and displayed by a user operation or automatically every predetermined time (for example, several seconds). You may be able to do it. In the present specification, the overall statistical values of the degree of coincidence such as the maximum peak value at the ON time described later including the maximum / minimum degree of coincidence are defined as coincidence degree statistical values.

  FIG. 14 is a diagram illustrating the relationship between the degree of coincidence and the sampling period for explaining the maximum / minimum degree of coincidence. Assuming that the sampling period is 3 ms, for example, the degree of coincidence is picked up by the image acquisition unit 52 and calculated by the degree of coincidence calculation unit 57c every 3 ms, as will be described later. Therefore, the degree of coincidence is indicated by a broken line in this figure, but actually takes a discontinuous value that is updated every 3 ms. Here, the degree of coincidence becomes a waveform when, for example, the work WK flows at a constant speed, the coincidence starts to increase at the same time as the work WK starts to enter the imaging field of view, and the work WK completely enters the imaging field of view. This is because the degree of coincidence is the highest and the degree of coincidence decreases as the work WK moves out of the imaging field of view. As shown in this figure, the past maximum value of the degree of coincidence changes to the value of the degree of coincidence if the degree of coincidence updated every 3 ms exceeds the past maximum value. Similarly, the past minimum value of the degree of coincidence changes to the value of the degree of coincidence at this time if the degree of coincidence updated every 3 ms falls below the past minimum value.

  In order to perform the pass / fail judgment with high accuracy, it is desirable to set a value between the maximum value and the minimum value of the matching degree as a threshold value. For example, when the threshold value is 600 and the maximum and minimum values of the matching degree are 909 and 222, respectively, the threshold value is larger than 565.5 which is an intermediate value between the maximum value and the minimum value. It can be seen that the good judgment is not performed with some margin. In this way, the threshold 4314a, the coincidence 4313a, the maximum coincidence 4319a, and the minimum coincidence 4320a are displayed in this second display format on the operation screen, so that the non-defective image OKI of the workpiece WK during operation is displayed. While confirming the degree of coincidence, it is possible to give an idea as to whether or not the threshold is appropriate.

As described above, from the first display format, (1) the user must determine whether or not the degree of coincidence with the non-defective image OKI of the work WK is appropriate in comparison with the live image LVI and the threshold value. From the second display format, (2) the user can determine whether or not the threshold value is appropriate while confirming the degree of coincidence with the non-defective image OKI of the workpiece WK in operation. In addition, in the present embodiment, the screen display switching unit 51f can switch between the first display format and the second display format, so that (3) the user can calculate the coincidence calculated during driving. The degree of coincidence variation after the start of driving can be known while checking the threshold and the threshold set before driving, and it is possible to determine whether resetting or adjustment is necessary.
(Third display format: Enlarged matching level and threshold)

For example, as shown in FIG. 12A, the third display format is a display screen 43 in which the number size of the coincidence 4313a, which is a numerical display of the coincidence of the live image LVI with respect to a pattern model such as a difference image or an edge, is set as a threshold value. This is a display format in which the value is displayed larger than the numerical value of the threshold value 4314a which is the numerical value display of the threshold value calculated by the calculation unit 56c. Thereby, information can be displayed simply and clearly during driving. In FIG. 12A, the large display in the upper right indicates the matching degree 4313a of the live image LVI currently captured. Further, the lower right display in the figure shows the threshold value 4314a. On the right side of the threshold 4314a, there is an upper / lower display 4315a for increasing / decreasing the threshold, and the threshold can be increased / decreased by pressing the upper / lower display 4315a on the operation screen.
(Fourth display format: ON peak)

  For example, as shown in FIG. 12D, the fourth display format is a past maximum value (hereinafter referred to as “ON peak maximum value” in the matching degree exceeding the threshold value calculated by the threshold value calculation unit 56 c on the display screen 43. ON peak maximum value 4321a, which is a numerical display, and a past minimum value (hereinafter referred to as “ON peak minimum value”) in the degree of coincidence exceeding a threshold value. This is a display format for displaying the minimum peak value 4322a. The display in the fourth display format can be switched to other display formats, for example, the display in the first display format and the display in the second display format. In the fourth display format, the ON peak maximum value 4321a and the ON peak minimum value 4322a may be alternately switched and displayed.

  FIG. 15 is a diagram illustrating the relationship between the degree of coincidence and the sampling period for explaining the degree of coincidence statistical value such as the peak maximum value when ON. In this figure, when the degree of coincidence takes a value that exceeds the threshold value, it is ON when it is determined to be a non-defective product, and when it takes a value that is less than the threshold value, it is OFF when it is not determined to be non-defective. First, paying attention to the ON period of (1) among the sampling periods of (1) to (3), the degree of coincidence at the start of the sampling period of (1) exceeds the threshold value. However, the maximum value of the coincidence in the sampling period (the peak maximum value at the ON time) is not fixed until the sampling of (1) is completed, so at the end of the sampling period of (1) , (1) (C) The ON-time peak value associated with the set threshold value is determined. Accordingly, the ON peak maximum value 4321a is displayed at the end of the sampling period (1), that is, when the sampling period is switched to OFF. At this time, since there is no past maximum value of the degree of coincidence to be compared, there may be a mode in which the ON peak maximum value 4321a is not displayed. Similarly, the ON peak minimum value is determined at the end of the sampling period (1), and the ON peak minimum value associated with the set threshold value (1) is determined. At this time, since there is no past minimum value of the degree of coincidence to be compared, the ON peak minimum value is the same as the ON peak maximum value.

  Similarly, when ON in (2), the ON-time peak value associated with the (C) set threshold value in the sampling period in (2) is determined when the sampling period in (2) ends, that is, when it is switched to OFF. . As shown in FIG. 15, the ON-time peak value associated with the (C) setting threshold value in the sampling period (1) is larger than the ON-time peak value associated with the (C) setting threshold value in (2). , (1) (C) The ON peak value associated with the set threshold value is maintained as it is as the ON peak maximum value. On the other hand, the ON peak value associated with the (C) setting threshold value in the sampling period (2) is smaller than the ON peak value associated with the (C) setting threshold value in (1). ) At the end of the sampling period, the ON-time peak value associated with the (C) setting threshold in the sampling period of (2) is determined as the ON-time peak minimum value.

As shown in FIG. 15, even when the sampling period (3) is ON, the ON peak value associated with the (C) set threshold in the sampling period (3) is the end of the sampling period (3), that is, Confirm when switching to OFF. Since the ON peak value associated with the threshold value (C) in the sampling period (3) is larger than the ON peak maximum value at the end of the sampling period (2), the ON peak maximum value is ( At the end of the sampling period of 3), it is updated to the ON-time peak value associated with the (C) setting threshold value of (3). On the other hand, as shown in FIG. 15, the ON-time peak value associated with the (C) setting threshold in the sampling period (3) is smaller than the ON-time peak minimum value at the end of the sampling period (2). , (2) the ON peak minimum value at the end of the sampling period is maintained as it is as the ON peak minimum value.
(Bottom when OFF)

  Up to this point, the ON-time peak in the fourth display format has been described in detail. However, with respect to the ON-time peak, on the display screen 43, the past maximum in the degree of coincidence below the threshold value calculated by the threshold value calculation unit 56c. It is also possible to display a value (hereinafter referred to as “OFF bottom maximum value”) and a past minimum value (hereinafter referred to as “OFF bottom minimum value”) that is below the threshold. As shown in FIG. 15, the OFF bottom maximum value and the OFF bottom minimum value store the OFF bottom value associated with the threshold value (F) in the sampling period (1) to (3). ) To (3), when it is statistically maximum / minimum at the start of the sampling period, it is updated to the maximum / minimum value at that time.

In this fourth display format embodiment, the ON peak maximum value 4321a and the ON peak minimum value 4322a are displayed. As a modification, the ON peak minimum value 4322a and the OFF bottom maximum value are displayed. You may make it do. The peak minimum value at ON and the bottom maximum value at OFF are the degree of coincidence statistics indicating whether the threshold value was exceeded or the threshold value was exceeded with a margin in relation to the degree of coincidence after starting operation and the threshold value. This means that if the peak minimum value at ON is close to the threshold value, the value of the degree of coincidence to be calculated as a non-defective product is also close to the threshold value, and if the bottom maximum value at OFF is close to the threshold value, it should be calculated as a defective product Since the degree value also means that the threshold value is close to the threshold value, the user can use this statistical value of coincidence to determine whether or not the threshold value needs to be adjusted, or to reference when manually adjusting the threshold value.
(Fifth display format)

  For example, as shown in FIG. 12E, the fifth display format includes a live image LVI in an image display area PD for displaying an image and a non-defective image in an explanation display area ED for displaying an explanation on the display screen 43. This is a display format for displaying the non-defective image OKI stored in the storage unit 541a. The display in the fifth display format can be switched to other display formats, for example, the display in the first display format and the display in the second display format. In this manner, the live image LVI and the non-defective image OKI are displayed in the fifth display format on the operation screen, so that the determination result by the determination result display lamp 41, the live image LVI, and By comparing the non-defective image OKI, it is possible to determine whether or not the quality determination of the work WK is normally performed.

The fifth display format includes a display format for displaying the live image LVI and the non-defective product image OKI, as well as a display format for displaying the live image LVI and the defective product image NGI in the case of teaching with three points, for example. Good. FIG. 16A shows the former display format, and FIG. 16B shows the latter display format. In the present embodiment, for example, the former display format and the latter display format can be switched. ing. Thereby, the quality determination of the work WK is normally performed by comparing the live image LVI with the non-defective product image OKI or the defective product image NGI while referring to the determination result by the determination result display lamp 41 during operation. You can make an idea of whether or not
(Modification of the second display format)

  As described above, the second display format for displaying the threshold value 4314a, the coincidence degree 4313a, the maximum coincidence degree 4319a, and the minimum coincidence degree 4320a on the display screen 43 has been described by taking the display form shown in FIG. 17A as an example. Instead, it can be displayed in the display format shown in FIG. 17B, for example. The display format shown in FIG. 17B is configured to display the live image LVI and display the threshold value, the degree of coincidence, the maximum degree of coincidence, and the minimum degree of coincidence so as to be intuitively understandable to the user. FIG. 18 is an enlarged view of the display format shown in FIG. 17B. As shown in the display format of FIG. 18, a bar 4323 is displayed at the left end of the operation screen so that the longitudinal direction is vertically oriented, and in this bar 4323, a coincidence degree 4313b of a wide horizontal line that is an icon display of the degree of coincidence. And a threshold value 4314b of a narrow horizontal line that is an icon display of the threshold value is displayed. On the right side of the threshold value 4314b, there is an upper / lower display 4315b for increasing / decreasing the threshold value. By pressing the upper side of the upper / lower display 4315b on the operation screen, the threshold value increases, and the threshold value 4314b increases by the increased amount. Is displayed. In addition, when the lower side of the upper and lower display 4315b is pressed on the operation screen, the threshold value is reduced, and the threshold value 4314b is lowered and displayed by the reduced amount. In the bar 4323, a matching level 4313b which is an icon display of the matching level is further displayed. If the matching level increases, the matching level 4313b increases and displayed. If the matching level decreases, The degree of coincidence 4313b is lowered and displayed.

  Further, the maximum coincidence 4319b and the minimum coincidence 4320b, which are icon displays of the maximum coincidence and the minimum coincidence, are displayed on the right side of the bar 4323, respectively. The degree of coincidence 4319b and the minimum degree of coincidence 4320b are displayed to be increased, and when the values of the maximum degree of coincidence and the minimum degree of coincidence are reduced, the maximum degree of coincidence 4319b and the minimum degree of coincidence 4320b are displayed to be lowered.

  Furthermore, the maximum coincidence degree 4319a and the minimum coincidence degree 4320a are displayed in the explanation display area ED on the right side of the operation screen, and the maximum coincidence degree 4319b and the minimum coincidence degree 4320b which are respective icon displays are displayed on the left side thereof. The

  Furthermore, the live image LVI is displayed in the image display area PD on the left side of the operation screen. The image displayed in the image display area PD is not limited to the live image LVI. For example, as shown in FIG. 19A, an image 4325 having a maximum coincidence / minimum coincidence may be displayed. Also, the display shown in FIG. 17A and the display shown in FIG. 17B can be switched alternately by a user operation or automatically every predetermined time (for example, several seconds).

According to this modification, the matching degree, the maximum matching degree, and the minimum matching degree are displayed according to their values, the corresponding icons are moved up and down, and the live image LVI is displayed. Since the threshold value 4314b can be compared, the suitability of the threshold value can be determined visually and sensibly, and the driving situation can also be grasped. Further, when adjustment of the threshold value is necessary, the threshold value 4314b is displayed by moving up and down by pressing the up and down display 4315b on the operation screen, so that the threshold value can be adjusted visually and sensibly.
(Modification of the fourth display format)

  In addition, the fourth display format has been described by taking the display format shown in FIG. 17C as an example, but instead of this, for example, the display format shown in FIG. 17D can also be displayed. The display format shown in FIG. 17D is configured to display the live image LVI and display the threshold value, the degree of coincidence, the ON peak maximum value, and the ON peak minimum value in a graph so that the user can easily understand it. . FIG. 20 is an enlarged view of the display format shown in FIG. 17D. As shown in the display format of FIG. 20, a bar 4323, a coincidence degree 4313b, a threshold value 4314b, and an upper / lower display 4315b are displayed. Since these are described in the item of the modified example of the second display format, description thereof is omitted here.

  In the display format of FIG. 20, on the right side of the bar 4323, an ON peak maximum value 4321b and an ON peak minimum value 4322b, which are icon displays of the ON peak maximum value and the ON peak minimum value, are displayed, respectively. If the maximum value and the ON peak minimum value increase, the ON peak maximum value 4321b and the ON peak minimum value 4322b are increased and displayed, and the ON peak maximum value and ON peak minimum value are displayed. If it becomes smaller, the ON peak maximum value 4321b and the ON peak minimum value 4322b are displayed in a lowered manner.

  Furthermore, the ON peak maximum value 4321a and the ON peak minimum value 4322a are displayed in the explanation display area ED on the right side of the operation screen, and the ON peak maximum value 4321b and ON are displayed on the left side thereof. The hour peak minimum value 4322b is displayed.

  Furthermore, the live image LVI is displayed in the image display area PD on the left side of the operation screen. Note that the image displayed in the image display area PD is not limited to the live image LVI. For example, as shown in FIG. 19B, an image 4326 in which the ON peak maximum value / ON peak minimum value is displayed is displayed. Also good. Also, the display shown in FIG. 17C and the display shown in FIG. 17D can be switched alternately by a user operation or automatically every predetermined time (for example, several seconds). Also in this modification, instead of displaying the ON peak maximum value 4321a and the ON peak minimum value 4322a, the ON peak minimum value 4322a and the OFF bottom maximum value may be displayed.

According to this modification, the matching level, the peak maximum value at ON time, and the peak minimum value at ON time are displayed according to these values, and the corresponding icon is displayed while moving up and down, and the live image LVI is displayed. Since these displays can be compared with the threshold value 4314b, the suitability of the threshold value can be judged visually and sensory, and the driving situation can also be grasped. Further, when adjustment of the threshold value is necessary, the threshold value 4314b is displayed by moving up and down by pressing the up and down display 4315b on the operation screen, so that the threshold value can be adjusted visually and sensibly.
(Modification of the fifth display format)

  In addition, the fifth display format has been described by taking the display format shown in FIG. 17E as an example, but instead of this, for example, the display format shown in FIG. 17F can also be displayed. This modification is the same as the fifth display format with respect to the display of images, but instead of a bank display 4311 and an output channel display 4312 which will be described later displayed on the left end of the operation screen, a matching degree 4313b and a threshold 4314b are displayed. Is displayed so that the user can easily understand it. Also, the display shown in FIG. 17E and the display shown in FIG. 17F can be switched alternately by a user operation or automatically every predetermined time (for example, several seconds).

  FIG. 21 is an enlarged view of the display format shown in FIG. 17F. As shown in the display format of FIG. 21, the live image LVI is displayed in the image display area PD for displaying an image, and the non-defective image OKI stored in the non-defective image storage unit 541a is displayed in the description display area ED for displaying the description. Is displayed. In addition, a bar 4323, a matching degree 4313b, a threshold 4314b, and an up / down display 4315b are displayed at the left end of the operation screen. Since these are described in the modification of the second display format and the items of the fifth display format, description thereof is omitted here.

According to this modified example, the live image LVI and the non-defective image OKI are displayed, and the matching degree 4313b and the threshold value 4314b are displayed at the left end of the operation screen. In addition, it is possible to determine whether the work WK is properly judged by comparing the judgment result by the judgment result display lamp 41, the live image LVI, and the non-defective image OKI. You can make a point.
(Output channel setting unit 51m)

  The output channel setting unit 51m can set the first threshold value and the second threshold value with respect to the matching degree, and based on the comparison between the matching degree of the input image and the first threshold value and the second threshold value, This is a member for setting the output channel 1 and the output channel 2 for outputting the determination result and the second determination result, respectively. FIG. 22 is a diagram for explaining the output channel setting unit 51m. 22A is a diagram showing a screen display, and FIG. 22B is a diagram showing a relationship between a threshold value and pass / fail judgment for each output channel. In FIG. 22A, OUT1 or OUT2 indicates an output channel, and OUT1 indicates that a determination result is output from the output channel 1.

  In the left diagram in FIG. 22A, 600 is set as the threshold value for OUT1, and in the right diagram in FIG. 22A, 808 is set as the threshold value for OUT2. If a work WK having a matching degree of 700 is to be inspected, the output channel 1 outputs ON, but the output channel 2 does not output ON. As shown in the upper diagram of FIG. 22B, assuming that the first threshold value, the second threshold value, and the degree of coincidence take the values shown in the graph, the determination result is as shown in the lower diagram of FIG. 1) Output channel 1: OFF, Output channel 2: OFF, (2) Output channel 1: ON, Output channel 2: OFF, (3) Output channel 1: ON, Output channel 2: ON Since the first threshold value is smaller than the second threshold value, the output channel 1 outputs ON earlier than the output channel 2 and outputs ON until the output channel 2 is later.

As a result, different threshold values can be set for the output channel 1 and the output channel 2. For example, even if the accuracy of the degree of coincidence is lowered by operating for a long time, there is a margin in the output channel where the threshold value is set low. Since it can be turned on, it can be used for predictive maintenance by switching to an output channel with a low threshold value on the assumption that maintenance will be performed soon.
(Bank switching unit 51l)

  The bank switching unit 51l is a member for performing a switching operation between a plurality of banks. FIG. 23 is a diagram for explaining bank setting. In this figure, the bank displayed at the left end of the operation screen may require a setup change that allows a plurality of workpieces WK to flow through one production line, and teaching does not have to be performed again at each setup change. For example, four settings such as BNK1 to BNK4 can be stored in the bank setting storage unit 54f, and it is displayed which of the settings is BNK1 to BNK4.

For example, the BNK 1 registers a screw, and when the registered screw is detected, teaching is performed so as to turn on and determine a threshold value. The BNK 2 determines that the screw is a non-defective product if it has a nut, and the BNK 3 registers a screw with a cap, and is set to turn on when a registered screw with a cap is detected. In this way, the bank switching unit 51l sets in advance, and when the setup is changed, the operation is performed by switching between BNK1 to BNK4. Banks can be switched by simultaneously pressing the MODE key 46 and the down key 44b of the up / down key 44 simultaneously. During operation, the bank can be automatically switched by performing sequence control on the external input signal.
(Rotation allowable range setting unit 51j)

  The rotation allowable range setting unit 51j is a member that sets an angle for rotating and displaying the posture of a captured image. For example, as shown in FIG. 24, it may be installed as (A) on the left side in the drawing or may be installed as (B) with respect to the flow direction of the work WK. Due to physical restrictions at the work site, the mounting direction of the sensor unit 2 of the image processing sensor 1 varies. If the live image LVI displayed on the display screen 43 when installed as shown in (A) is (a) on the right side of the figure, the live image LVI displayed on the display screen 43 when installed as shown in (B) is It is displayed as (b) on the right side of the figure. For example, even if it is installed as shown in (B), when it is desired to be displayed on the display screen 43 as shown in (a), it is displayed on the display screen 43 by specifying the rotation angle with the rotation allowable range setting unit 51j. The display posture of the live image LVI to be played is rotated. The operation by the rotation allowable range setting unit 51j is performed on the detailed setting screen displayed by pressing and holding the MODE key 46 in the setting mode.

  In this embodiment, regarding the designation of the rotation angle, (1) no rotation (default) shown in FIG. 25A, (2) 90 ° rotation shown in FIG. 25B, (3) 180 ° rotation shown in FIG. 25C, FIG. 25D (4) 270 ° rotation can be selected. In the setting mode, as shown in FIG. 25, the live image LVI is displayed in the image display area PD, and in the explanation display area ED, the wording of “View-finder” indicating the input image and the default are displayed. The rotation angle from the state is displayed. On the right side of the rotation angle display, there is an upper / lower display 4315c for increasing / decreasing the rotation angle. By pressing the lower side or upper side of the upper / lower display 4315c on the setting screen, the rotation angle is increased / decreased by 90 °. The live image LVI is rotated and displayed in the order of (1) to (4) or in the reverse order (clockwise or counterclockwise).

FIG. 26A shows (1) the operation screen displayed in the first display format and the fifth display format without rotation. FIG. 26B shows (3) the operation screen displayed in the first display format and the fifth display format of 180 ° rotation. As shown in these drawings, in the operation mode, the live image LVI, the non-defective product image OKI, and the defective product image NGI are displayed at the specified rotation angle when the rotation angle is specified by the rotation allowable range setting unit 51j. . On the other hand, the degree of coincidence 4313a, the threshold 4314a, and the upper / lower display 4315a displayed in the explanation display area ED are not rotated. In the above-described embodiment, the first display format and the fifth display format are exemplified. However, the present invention is not limited to this. For example, the same applies to modified examples of the second, third, and fourth display formats.
(Reverse display function)

The image processing sensor 11 can be set to display in reverse the display content other than the input image. FIG. 27A shows the screen display before the reverse display, and FIG. 27B shows the screen display reversely displayed by the screen reverse function. This reverse display function can improve operability when the direction in which the user faces the setting screen is changed. Specifically, the posture of the image processing sensor 11 when it is incorporated into the production line is flexibly changed according to the pulling direction of the cables, and the display itself on the display screen 43 depends on the direction in which the user visually recognizes. The situation can be avoided such that the display is upside down and difficult to discriminate. Such a change of the display mode on the display screen 43 can be performed by the display control unit 58f described later.
(Reverse display interlocking increase / decrease function)

Further, in this case, when the display on the display screen 43 is inverted, the function of the up / down key 44 of the increase / decrease adjustment unit 51h is switched so that the numerical value displayed on the display screen 43 and the top / bottom of the image match. You can change the increase / decrease operation. That is, when the display contents other than the input image are displayed in reverse in this way, the up / down key 44 reduces the input image magnification or threshold when the upper key 44a before the reverse display is operated, and displays the reverse display. When the previous down key 44b is operated, the magnification or threshold value of the input image may be increased. As a result, when the display is reversed as in the prior art, it is necessary to increase or decrease in the opposite direction to arrows and top and bottom, avoiding an environment where erroneous operations are likely to occur, avoiding an environment that is easy to understand sensuously, Setting mistakes can be avoided by setting the input operation to increase and decrease downward.
(Matching degree statistics clear part 51g)

The coincidence degree statistical value clear unit 51g is a member for clearing the storage of coincidence degree statistical values. The degree of coincidence statistical value is useful information for adjusting the threshold value by checking whether the pass / fail judgment is stably performed so that the user appropriately sets the threshold value. Degree, minimum matching degree, ON peak minimum value, and OFF bottom maximum value. As shown in FIG. 14 or FIG. 15, when the coincidence degree statistical value is cleared by hold in the coincidence degree statistical value clear unit 51g, it is calculated as a statistical value from that point.
(Increase / decrease adjustment unit 51h)

  The increase / decrease adjustment unit 51h is a member that receives an operation instruction for increasing / decreasing a set value from the user via a pair of switches, an up-side switch and a down-side switch, and transmits the operation instruction to the control unit 61. . The increase / decrease adjustment unit 51h is used to change the display magnification of an image displayed on the display screen 43, for example. The images displayed on the display screen 43 are, for example, a first image such as a non-defective image OKI, a second image such as a defective product image NGI, and a third image such as a background image BGI. In particular, the display magnification is adjusted by the increase / decrease adjustment unit 51h in order to enlarge and display the non-defective image OKI and the good candidate image. Further, the threshold value can be adjusted with the same increase / decrease adjustment unit 51h (details of these adjustment operations will be described later). In this example, when the up-side switch is operated, the magnification and threshold value of the first image can be increased, and when the down-side switch is operated, it can be instructed to decrease the magnification and threshold value of the first image. As described above, the increase / decrease adjustment unit 51h enables different operations of an image display magnification adjustment function and a threshold adjustment function. By using the common increase / decrease adjustment unit 51h to adjust different values, the number of operation buttons to be provided on the display screen 43 is reduced, thereby simplifying the configuration, improving operability, reducing costs, and the like. It is done.

  Specifically, the increase / decrease adjustment unit 51h is an increase / decrease button, and corresponds to an up / down key 44 and up / down displays 4315a, b, c, d which are icons of up / down arrows. The up / down key 44 includes an up key 44a and a down key 44b, and is used for adjustment of increase / decrease, up / down movement, and the like. In the example of FIG. 6, the up / down key 44 is composed of separate keys, the upper key 44a and the lower key 44b. However, the present invention is not limited to this configuration, and the up / down key is integrated into one up / down key. You can increase or decrease with. For example, the up / down key 44 may be configured as a tiltable seesaw type, and may be increased when tilted upward and decreased when tilted downward.

  The up / down keys 44 are arranged side by side so that the user can operate sensibly. In other words, the value can be increased by depressing the upper key 44a disposed above, and the value can be decreased by depressing the lower key 44b disposed below, thereby reducing the possibility of erroneous operation. In general, the image processing sensor 11 has a larger number of parts than the photoelectric sensor, and the casing 4 tends to be thicker. Therefore, the upper key 44a and the lower key 44b can be vertically arranged in a vertically long shape without increasing the size. . This makes it possible to configure the appearance so that the shape of the up / down key 44 matches the function.

  Further, when the same rectangular display screen 43 is arranged on the rectangular display surface 4a extended in one direction, the longitudinal direction of the display screen 43 may be arranged so as to match the longitudinal direction of the display surface 4a. It is rational in terms of space efficiency. In this case, the up / down key 44 is preferably arranged on the side surface of the display screen 43 in the longitudinal direction. When the up / down keys 44 are arranged above and below the display screen 43, the thickness of the display surface 4a increases, leading to an increase in the size of the casing 4 of the image processing sensor 11. Therefore, the display screen 43 and the up / down key 44 are arranged so as to be aligned along the longitudinal direction of the display surface 4a, thereby contributing to the downsizing of the image processing sensor 11.

  Further, it is preferable that the up / down key 44 is not disposed on the same side of the display screen 43 as the SET key 42 but is disposed on the opposite side across the display screen 43. In this way, after an increase / decrease in the display magnification or threshold value, an operation to send a determination instruction from the SET key 42, the user touches the SET key 42 by mistake when operating the up / down key 44 while still increasing / decreasing. The risk of an erroneous operation in which an unintended determination instruction is given can be reduced by physically separating the up / down key 44 and the SET key 42.

  Note that the up / down key 44 is not necessarily limited to a configuration in which the up / down key 44 is arranged side by side, and for example, the up / down key 44C may be arranged side by side. In particular, conventional photoelectric sensors are arranged side by side by rotating the up / down key 44 by 90 degrees in order to reduce the thickness. Therefore, by arranging the upper and lower buttons for the image processing sensor in accordance with the arrangement example of such a photoelectric sensor, it provides a feeling of operation similar to that of the photoelectric sensor, and a user who has experience of using the photoelectric sensor feels comfortable. It becomes easy to operate.

  An up / down key 44, a BACK key 45, a MODE key 46, and the like are arranged on the right side of the display screen 43. By arranging keys that require fine operations on the right side in this way, a user who seems to be right-handed can easily operate with the right hand.

  Furthermore, it is preferable that each key has a different shape. As a result, the user can distinguish the keys by touch, so that even if it is difficult to see the keys directly in a dark place or in a deep position, it is possible to operate with touch. For example, in the example of FIG. 6, the up / down key 44 has an upper key 44a with an upper tip and a lower key 44b with a tapered tip. The BACK key 45 and the MODE key 46 are horizontally long. On the other hand, the SET key 42 is formed vertically long. In particular, by making the shape of the SET key 42 different from that of the BACK key 45 and the MODE key 46, it is possible to reliably perform the work of pressing the SET key 42 after adjustment by the increase / decrease adjustment unit 51h.

Furthermore, on the up / down key 44, marks such as “Δ” and “▽” are displayed on the key top by engraving or printing. As a result, the user can visually recognize that the key is to increase or decrease.
(Upper and lower displays 4315a, b, c, d)

  Further, as shown in FIG. 9 and FIG. 10 and the like, the upper and lower displays 4315a, b, c, and d, which are icons displayed on the display screen 43, change the display form according to items that can be adjusted by the increase / decrease adjustment unit 51h. be able to. For example, as shown in FIG. 9, on a screen in which the threshold value can be changed, a mark such as “Δ” or “▽” is displayed as an upper / lower display 4315a next to the threshold 4314a, and the displayed value is increased or decreased, that is, increased or decreased. It shows that it is possible. On the other hand, as shown in FIGS. 10 and 11, on the screen in which an image is displayed in the image display area PD, “ZOOM” is displayed as an upper / lower display 4315d to indicate that the increase / decrease adjustment unit 51h can zoom in or out. "And a mark such as △ or ▽ are displayed next to it.

As shown in FIG. 28, when the upper key 44a of the up / down key 44 is pressed, the image is enlarged and displayed, and when the lower key 44b is pressed, the image is reduced and displayed. Further, with the display screen 43 as a touch panel, an image is enlarged when an upper icon of the upper and lower display 4315d provided side by side in the “ZOOM” display is touched, and reduced when a lower icon is touched. The threshold value can be increased or decreased by operating the up / down key 44 provided on the display surface 4a of FIG. 6 on the operation screens of FIGS. 12A to 12D or FIGS. 17B, 17D, and 17F, for example. In addition, the threshold value can be increased by touching the upper icon of the upper / lower display 4315a or the upper / lower display 4315b displayed in these drawings, and can be decreased by touching the lower icon. Furthermore, in the setting screens of FIGS. 25A to 25D, similarly, the display posture of the live image LVI can be rotated by operating the up / down key 44 or touching the upper or lower icon of the upper / lower display 4315c. The angle can be increased or decreased.
(Combination of keys used to increase / decrease threshold and image magnification)

  The up / down key 44 is also used to increase / decrease the threshold value and the magnification of the image captured by the imaging unit 21. FIG. 29A shows a setting screen for performing registered image processing, and FIGS. 29B and 29C show operation screens displayed in the first display format and the third display format, respectively.

  When the SET key 42 is pressed on the operation screen, a transition is made to a setting screen as shown in FIG. 29A, and the processing proceeds to image registration processing. As shown in FIG. 28 or FIG. 29A, the live image LVI is displayed in the image display area PD, and the words “SET OK”, “non-defective product”, and “ZOOM” and the right of “ZOOM” are displayed in the explanation display area ED. An up / down display 4315d which is an icon of an up / down arrow is displayed next to the display. On this screen, the live image LVI is enlarged when the upper icon of the upper and lower display 4315d is touched, and reduced when the lower icon is touched. Further, on this screen, when the upper key 44a of the up / down key 44 is pressed, the image is enlarged and displayed, and when the lower key 44b is pressed, the image is reduced and displayed. When the SET key 42 is pressed, the displayed live image LVI is stored in the corresponding storage unit of the still image storage unit 54a, and the magnification of the image is stored in the setting storage unit 54d.

  On the other hand, for example, in the operation screen shown in FIG. 29B and FIG. 29C, the threshold value can be increased or decreased on the vertical display 4315a as described above. In the operation mode in which these operation screens are displayed, the up / down key 44 functions as a switch for increasing / decreasing the threshold value. That is, in the operation mode, if the image magnification at the time of image capturing by the image acquisition unit 52 is changed, the degree of coincidence is affected, so the image is displayed at the magnification of the image stored in the setting storage unit 54d. The up / down key 44 functions as a switch for increasing / decreasing the threshold value on the operation screen shown in FIGS. 29B and 29C, for example, so that it cannot be changed during operation. Therefore, for example, as shown in FIG. 29B, even if the up / down key 44 is pressed, the live image LVI does not change. Note that the image processing sensors 1 and 11 have a key lock function so that settings cannot be changed.

In this way, since the up / down key 44 is used for both increasing and decreasing the threshold value and the image magnification, it is not necessary to provide a plurality of switches, so that the casing 4 can be reduced in size and a decrease in operability is avoided. You can also.
(Switching the function of the increase / decrease adjustment unit 51h)

  The switching of the function of the increase / decrease adjustment unit 51h may be performed after selecting the function of the increase / decrease adjustment unit 51h, but in this case, before the increase / decrease adjustment unit 51h is operated, An operation of selecting and switching functions is essential, and the user is forced to perform troublesome operations. In view of this, such an increase / decrease is configured by automatically performing function switching so that the function of the increase / decrease adjustment unit 51h is a function suitable for each operation mode according to the currently selected operation mode. The function switching operation of the adjustment unit 51h can be made unnecessary. For example, when the setting mode is selected by the operation / setting mode switching unit 51d, a function for changing the image display magnification is assigned to the increase / decrease adjustment unit 51h. On the other hand, in a state where the operation mode is selected by the operation / setting mode switching unit 51d, a function for adjusting the threshold value is assigned to the increase / decrease adjustment unit 51h. Thus, the user's operability can be improved by automatically assigning an appropriate function to the increase / decrease adjustment unit 51h to which a plurality of functions are assigned without selecting any function in advance. .

The function assignment for each operation mode is an example. For example, in the setting mode, when the image display magnification and the threshold value are increased or decreased, the display magnification or the increase / decrease adjustment unit 51h The user may be configured to select one of the threshold increase / decrease functions.
(Cancellation instruction unit 51i)

The cancellation instruction unit 51i is a member for issuing a cancellation instruction by a user operation. In the example of the display surface 4a in FIG. 6 and the like, the BACK key 45 corresponds to the cancel instruction unit 51i.
(Non-defective / defective product output setting unit 51n)

The non-defective / defective product output setting unit 51n is a member for performing switching operation between output setting for detecting the non-defective workpiece WK and output setting for detecting the defective workpiece WK. The non-defective product / defective product output setting unit 51n displays a selection screen displayed as, for example, “Output mode” by pressing and holding the MODE key 46 on the extended function setting screen, as shown in FIG. When operating in the three-point teaching mode, the user can select whether to operate the non-defective image OKI as the master image or the defective image NGI as the master image on this selection screen. In other words, it is possible to select whether to turn on the output when the evaluation target during the driving operation is close to the non-defective image OKI or to turn on the output when close to the defective product image NGI.
(Determination target selection function)

In this manner, the non-defective / defective product output setting unit 51n can perform an operation of selecting the discrimination target. Here, the selection function of the discrimination target will be described. Usually, the non-defective image OKI is operated as a master image. In this case, (1) a threshold value is set between the degree of coincidence 100% of the non-defective image OKI with respect to the non-defective image OKI and the degree of coincidence of the defective image NGI with respect to the non-defective image OKI, and the latest input image and non-defective image OKI Is set to output ON when the threshold value is exceeded. In contrast, in order to operate the defective product image NGI as a master, (2) the degree of coincidence of the defective product image NGI with the defective product image NGI is 100% and the degree of coincidence of the non-defective product image NGI with the defective product image NGI. A threshold value is set in between, the degree of coincidence between the latest input image and the defective product image NGI is calculated, and when the threshold value is exceeded, ON is set to be output. These settings (1) and (2) can be switched by the user's operation in the above-mentioned non-defective / defective product output setting unit 51n.
(Image acquisition unit 52)

The image acquisition unit 52 is a member that delivers an image acquired by capturing an image with the imaging unit 21 or an image acquired from an external storage device or the like to the main control unit 61. In the image acquisition unit 52, the CMOS 231 creates a digital image from the optical image, and the reading method can be changed, for example, skipping one pixel. In the separation-type image processing sensor 1, the controller unit 3 acquires an image captured by the image acquisition unit 52 or stored in an external storage device or the like by the image acquisition unit 52. Note that the image acquisition unit 52 may include an HDR function that continuously captures images with different exposures and automatically synthesizes them.
(Display unit 53)

  The display unit 53 is a member that displays the current sensor state and the content of instructions to the user. As the display screen 43, a liquid crystal (LCD) or the like can be used as the display screen 43 in the display unit 53. In addition to incorporating the display screen 43 into the casing 4 as shown in FIG. 6 and the like, the display screen 43 may be externally attached. The output displayed on the display screen 43 can be output on the display screen of the external display device.

Display examples of the display screen 43 are shown in FIG. 10, FIG. 11, FIG. 31, and FIG. The display screen 43 shown in these drawings is provided with an image display area PD for displaying an image and an explanation display area ED for displaying an explanation by dividing the display area into two. In the example of FIG. 10 and the like, an image display area PD is provided on the left side of the horizontally long display screen 43, and an explanation display area ED is provided on the right side. Of course, it can be displayed in various ways, such as switching left and right, or dividing vertically into two vertically.
(Live image display unit 53a)

The live image display unit 53a is a member for repeatedly updating and displaying the current live image LVI. The live image LVI acquired by the image acquisition unit 52 is temporarily stored by the setting management unit 5 in the live image storage unit 54 b which is a volatile memory of the image / setting storage unit 54. Further, the display control unit 58f reads an image from the live image storage unit 54b, and reads settings such as a zoom magnification from the setting storage unit 54d. The live image display unit 53a repeatedly updates and displays the read image on the image display area PD based on the read setting.
(Still image display unit 53b)

The still image display unit 53b is a member for displaying a registered image. The still image display unit 53b displays a non-defective image OKI registered in a state where the first registration screen is displayed on a second registration screen at the time of teaching described later.
(Operation instruction display unit 53f)

The operation instruction display unit 53f is a member for instructing the user of an image registration procedure and displaying registration guidance information for guiding the user to complete registration. Specifically, when registering the non-defective product image OKI, the defective product image NGI, and the background image BGI, the operation instruction display unit 53f causes the guide display control unit 58a to display the registration guide information in the explanation display area ED. In the explanation display area ED, when registering the non-defective product image OKI, the defective product image NGI, and the background image BGI, for example, characters or icons for explaining what should be registered from now on are displayed.
(Registration guidance information)

The registration guide information is information for instructing the user to perform an image registration procedure and guiding the user to complete registration. For example, character information, image information, or information combining character information and image information can be used as registration guidance information. Specifically, the character information indicates the above-described character for description, and the image information indicates the icon for description. In addition to the still image, a moving image may be used as the image information. The registration guidance information described above is displayed in the explanation display area ED by the guidance display control unit 58a. Here, as the registration guidance information, the first registration screen is instructed to register one image, and the first registration guidance information for the user and the second registration screen is the other image registration procedure. And second registration guidance information for guiding the user. The registration guidance information is stored in a registration identification instruction information storage unit 54h, which is a non-volatile memory of the image / setting storage unit 54, and is managed by the operation instruction display unit 53f under the management of the guidance display control unit 58a. Displayed on ED. Details of these will be described later.
(Matching degree statistical value display part 53g)

The coincidence degree statistical value display unit 53g is a member for displaying the coincidence degree statistical value. The degree-of-match statistical value display unit 53g is calculated by the degree-of-match statistical value calculation unit 57e. The maximum / minimum degree of coincidence, the ON peak value associated with the set threshold, the ON peak maximum / minimum value, and the OFF bottom Value, bottom maximum / minimum value when OFF. 17A and 17B display a maximum coincidence 4319a and a minimum coincidence 4320a, and FIGS. 17C and 17D display an ON peak maximum value 4321a / ON peak minimum value 4322a.
(Image display part 53h at the time of coincidence statistics)

The coincidence statistic image display unit 53h displays the live image LVI when the coincidence statistic value, which is the whole of the coincidence statistic value such as the peak maximum value at ON including the maximum / minimum coincidence, is calculated, It is a member for displaying as a time image. As shown in FIG. 19, the coincidence-statistical image display unit 53h displays the coincidence-statistical image read from the coincidence-statistical image storage unit 54c with the second representation format, the fourth representation format, or the like. It can be configured to display instead of the live image LVI in the expression form of the modified example.
(Operation bank display part 53i)

The operation bank display unit 53i is a member for displaying a bank. For example, as shown in FIG. 23, the operation bank display unit 53i is selected from four settings previously stored in the bank setting storage unit 54f, such as BNK1 to BNK4. , Which of the current settings is BNK1 to BNK4 is displayed on the upper left corner of the operation screen.
(Image / setting storage unit 54)

The image / setting storage unit 54 (corresponding to an example of “image registration unit” in the claims) is a member that stores images and settings. In this embodiment, an internal SRAM or an external flash ROM is used as this member. For example, since registration guidance information needs to be always stored, a flash ROM that is a nonvolatile memory is used as the registration identification instruction information storage unit 54h for storing the registration guidance information. Note that the image / setting storage unit 54 may include a separate device for each piece of data, and may use either volatile or non-volatile memory.
(Still image storage unit 54a)

The still image storage unit 54a is a member for storing a registered image. In accordance with instructions from the non-defective product image setting unit 51a, defective product image setting unit 51b, and background image setting unit 51c in the operation unit 51, the setting management unit 58 performs the image / image timing at the time of input or immediately after input. The live image LVI stored in the setting storage unit 54 is stored in the still image storage unit 54a (non-defective product image storage unit 541a, defective product image storage unit 542a, background image storage unit 543a) of the image / setting storage unit 54.
(Live image storage unit 54b)

The live image storage unit 54b is a member for storing the live image LVI. The live image storage unit 54 b always saves the image obtained from the image acquisition unit 52 in the image / setting storage unit 54. Since the live image LVI is required to operate at a very high speed so as to be repeatedly updated and temporarily stored, an SRAM is used as the live image storage unit 54b for storing the live image LVI.
(Matching degree statistical image storage unit 54c)

The degree-of-matching statistical image storage unit 54c uses the degree-of-match statistics for the live image LVI when the degree-of-match statistical value, which is the general degree of coincidence statistical value such as the peak maximum value at ON including the maximum / minimum degree of matching, is calculated It is a member for memorizing as a time image. The coincidence-statistical image is read from the coincidence-statistical image storage unit 54c, and is displayed instead of the live image LVI in the second representation format, the fourth representation format, or the representation format thereof. Can be configured.
(Setting storage unit 54d)

The setting storage unit 54d is a member for storing various setting values such as an image magnification set in the setting mode. For example, the image magnification is read from the setting storage unit 54d by the image access unit 58c in the operation mode, set to the read image magnification by the display control unit 58f, and the live image is displayed by the live image display unit 53a. LVI is displayed.
(Matching degree statistical value storage unit 54e)

The coincidence degree statistical value storage unit 54e is a member for storing coincidence degree statistical values, which are general coincidence degree statistical values such as the peak maximum value at ON including the maximum / minimum degree of coincidence.
(Bank setting storage unit 54f)

The bank setting storage unit 54f is a member for storing a plurality of settings that are switched and read by the bank switching unit 51l. When the MODE key 46 and the up / down key 44 are pressed at the same time, the bank is switched between BNK1 to BNK4 and stored in the bank setting storage unit 54f in association with the bank displayed on the display screen 43.
(Threshold (first and second) storage unit 54g)

The threshold value (first and second) storage unit 54g is compared with the degree of coincidence of input images when the output channel setting unit 51m sets a channel for outputting the first determination result and the second determination result. This is a member for storing the first threshold and the second threshold.
(Registration Identification Instruction Information Storage Unit 54h)

The registration identification instruction information storage unit 54h is a member for storing registration guidance information. The registered guidance information is displayed in the explanation display area ED by the operation instruction display unit 53f under the management of the guidance display control unit 58a. Nonvolatile memories, semiconductor memories, hard disks, and the like can be used.
(Non-defective / defective product output setting storage unit 54i)

The non-defective / defective product output setting storage unit 54i is a member for storing an output setting for detecting the non-defective workpiece WK and an output setting for detecting the defective workpiece WK. For example, when the SET key 42 is pressed on the selection screen illustrated in FIG. 30, the non-defective product / defective product output setting storage unit 54 i stores which of the non-defective product image OKI and the defective product image NGI is set as the master image. .
(Table storage)

A table storage unit (not shown) is a member for storing information such as the maximum exposure time and the number of readable pixels for each response time.
(Condition allocation unit 55)

  The condition allocating unit 55 is a member for performing adjustment for determining the optimum registration setting condition by changing the registration setting condition. Specifically, in the setting mode, a plurality of different registration setting condition candidates that can be set are set according to the response time given from the response time setting unit 51e, and candidate images obtained by these registration setting condition candidates are set. The candidate image suitable for pass / fail judgment is registered as a registered image, and the registration setting condition at this time is held, and an image is taken with the registration set condition in the operation mode to perform pass / fail judgment. To do.

The condition assigning unit 55 includes an imaging condition assigning unit 55a, an image compression degree setting unit 55e, and an image processing content assigning unit 55f. The imaging condition allocating unit 55a can adjust the imaging conditions of the image so that predetermined image processing for performing pass / fail determination can be performed within the response time set by the response time setting unit. Further, the imaging condition assigning unit 55a includes a brightness condition assigning unit 55b capable of adjusting a condition related to the brightness of an image, that is, a brightness parameter. Examples of the brightness parameter include exposure time and illumination intensity. The brightness condition assignment unit 55b further includes a brightness condition candidate setting unit 55c and a brightness condition selection unit 55d.
(Brightness condition candidate setting unit 55c)

The brightness condition candidate setting unit 55c is a member for setting each of a plurality of brightness conditions as a brightness condition candidate so that a determination result is output within a given response time.
(Brightness condition selection unit 55d)

  The brightness condition selection unit 55d selects a brightness condition according to the selection condition from the plurality of brightness condition candidates based on the matching degree calculated for each of the plurality of brightness condition candidates by the matching degree calculation unit 57c. It is a member.

The above condition allocating unit 55, for example, sets the non-defective image OKI with the background removed from the non-defective product image OKI and the background image BGI, and the defective product image NGI and the background image BGI, and the defective product image NGI with the background removed, respectively. An evaluation method for determining an optimum registration condition for discriminating between a non-defective product and a defective product is determined based on an image obtained by cutting out and removing those backgrounds. For example, the image compression setting unit 55e changes the image resolution, the image processing content assignment unit 55f changes the image processing method, and the brightness condition assignment unit 55b changes the brightness when the image is captured. Alternatively, the condition assigning unit 55 may include a feature amount extraction process assigning unit that changes an internal feature amount extracting method. In this way, the condition assigning unit 55 changes the registration condition pattern, and sets the registration condition pattern with the optimum degree of coincidence calculated by the threshold value calculation unit 56c of the setting image processing unit 56 as the optimum registration condition. In addition, you may make it this function block bear the setting management part 58, for example.
(Setting image processing unit 56)

The setting image processing unit 56 is a member for performing image processing registration based on the image so that the target image can be evaluated. The image processing algorithm is registered based on at least one of the given non-defective image OKI, defective product image NGI, and background image BGI, the weight parameter of the internal feature amount is determined, and during the registration process, The driving image processing unit 57 evaluates the target image, calculates the degree of coincidence, and calculates a threshold value for discriminating between the non-defective product image OKI and the defective product image NGI.
(Differential image generation unit 56a)

The difference image generation unit 56a generates a simple difference image that extracts only the non-defective work by removing the background image BGI from the non-defective image OKI, or removes only the defective work by excluding the background image BGI from the defective product image NGI. It is a member for generating the extracted simple difference image. These difference images are obtained by subtracting corresponding pixels of the two images. However, in this specification, “difference” is not limited to such simple difference processing that subtracts corresponding pixels. For example, it is used in a sense including specifying a work area by excluding a common element with the background.
(Feature Extraction Unit 56b)

The feature amount extraction unit 56b is a member for extracting feature amounts from image data. The feature amount is also called a feature point or simply a feature, and examples thereof include a contour (edge), the number of edge pixels, and luminance average / variance. As an algorithm for extracting such feature amounts from image data, for example, a known algorithm such as a Sobel filter that is an algorithm for extracting edge features can be used.
(Threshold calculation unit 56c)

The threshold value calculation unit 56c displays the non-defective product image OKI including the work WK to be non-defective displayed on the display screen 43, and the background image BGI displayed on the display screen 43 and not including the work WK to be non-defective. This is a member for calculating a threshold value for the degree of coincidence indicating the degree of feature coincidence with the image NGI. The threshold value calculation unit 56c automatically calculates a threshold value for the degree of coincidence indicating the degree of feature coincidence between the good product image OKI and the background image BGI or the defective product image NGI. When teaching is performed from two points of the non-defective image OKI and the background image BGI, the feature amounts of the non-defective image OKI and the background image BGI are calculated, and a threshold is subtracted between the feature amounts. Further, when teaching is performed from three points of the non-defective image OKI, the defective image NGI, and the background image BGI, the non-defective image OKI with the background removed from the non-defective image OKI and the background image BGI, and the defective image NGI and the background image BGI. And the defective product image NGI from which the background has been removed are cut out, the feature amounts of the good product image OKI and the defective product image NGI from which the background has been removed are calculated, and a threshold value is subtracted between the feature amounts. Although there are various methods for calculating the threshold value, it is sufficient to use at least the degree of coincidence with the non-defective image OKI (first image) including the inspection object to be determined as non-defective. For example, the degree of coincidence of the defective product image NGI with respect to the non-defective product image OKI or the degree of coincidence of the background image BGI with respect to the non-defective product image OKI may be used.
(Image compression unit 56d)

The image compression unit 56d is a member for compressing an image and reducing the resolution. As an image compression method, a known method such as Lanczos method, average pixel method, bicubic method or the like can be used. The image compression unit 56d also functions to compress an input image to be compressed based on a given response time so that predetermined image processing has a data size that can be processed within the response time.
(Driving image processor 57)

The driving image processing unit 57 is a member for evaluating the target image and calculating the degree of coincidence. With the setting image processing unit 56 having registered the image processing algorithm, the registered image processing algorithm is operated on the evaluation target image, and the degree of coincidence with the non-defective image OKI is determined for the driving image. calculate. The driving image processing unit 57 compares the degree of coincidence calculated for the driving image with the threshold calculated by the threshold calculation unit 56c of the setting image processing unit 56 to determine whether the work WK is a non-defective product or a defective product.
(Feature Extraction Unit 57a)

The feature amount extraction unit 57a is a member for extracting feature amounts from image data. The feature amount is also called a feature point or simply a feature, and examples thereof include a contour (edge), the number of edge pixels, and luminance average / variance. As an algorithm for extracting such feature amounts from image data, for example, a known algorithm such as a Sobel filter that is an algorithm for extracting edge features can be used. It can be shared with a feature amount extraction unit 56b of the setting image processing unit 56 described later. In this case, at the time of registration, the feature amount extraction unit 57a calculates the feature amount and sends it to the setting image processing unit 56. Conversely, at the time of driving, the feature amount extraction unit 56b of the setting image processing unit 56 calculates the feature amount. Can be sent to the driving image processing unit 57. Alternatively, the setting image processing unit 56 and the driving image processing unit 57 may be integrated.
(Coincidence calculating unit 57c)

The degree of coincidence calculation unit 57c is a member for evaluating the target image and calculating the degree of coincidence. Here, the degree of coincidence means the degree of coincidence with the non-defective image OKI. For example, when the target image is the non-defective image OKI, the degree of coincidence between the background image BGI and the non-defective image OKI. Is 70%, the matching degree of the background image BGI is 70%, and the threshold value is 85% between the matching degree of the non-defective image OKI and the matching degree of the background image BGI. Thus, the degree of coincidence may be calculated as a ratio, or a score may be allocated for each feature amount, and a value obtained by adding the points allocated for each feature amount instead of the degree may be used as the degree of coincidence. In the above-described embodiment, the degree of coincidence is defined as the degree of coincidence with the non-defective image OKI or the value obtained by scoring the feature amount, but is defined as the degree of coincidence with the defective product image NGI. It is also possible to define the degree of coincidence with the target image desired by the user by appropriately selecting the first image.
(Matching degree statistical value calculator 57e)

  The coincidence degree statistical value calculating unit 57e calculates the coincidence degree statistical value of the coincidence degree calculated by the coincidence degree calculating unit 57c from the start of operation or after the coincidence degree statistical value is hold-cleared. It is a member. As shown in FIG. 14, the coincidence degree statistical value calculation unit 57e calculates the coincidence value as the maximum coincidence when the coincidence updated every 3 ms exceeds the past maximum value, for example. Similarly, if the degree of coincidence updated every 3 ms, for example, falls below the past minimum value, the degree-of-match statistical value calculation unit 57e calculates the value of the degree of coincidence at this time as the minimum degree of coincidence.

Further, as shown in FIG. 15, the coincidence degree statistical value calculation unit 57e is at the ON time when the coincidence degree exceeds the threshold and is judged as a non-defective product, and at the end of the current sampling period, the ON peak value of the sampling period is If the peak value at ON is exceeded, the peak value at ON is calculated as the peak maximum value at ON. If the peak value at ON in the sampling period falls below the minimum peak value at ON, the ON value is calculated. The hour peak value is calculated as the ON minimum peak value. Further, as shown in FIG. 15, the coincidence degree statistical value calculation unit 57e is at the OFF time when the coincidence degree falls below the threshold value and is judged as a defective product, and at the end of the current sampling period, If the bottom value exceeds the previous bottom maximum value at OFF, the bottom value at OFF is calculated as the bottom maximum value at OFF, and if the bottom value at OFF of the sampling period falls below the previous bottom maximum value at OFF The OFF bottom value is calculated as the OFF bottom minimum value.
(Setting management unit 58)

  The setting management unit 58 is a member for managing each functional block. The setting management unit 58 controls the image / setting storage unit 54, the condition allocation unit 55, the setting image processing unit 56, and the driving image processing unit 57 based on the information input by the operation unit 51 and the image acquisition unit 52. Necessary images and information are displayed on the display unit 53. For example, in the setting mode, in the state waiting for the setting of the live image LVI, the image obtained from the image acquisition unit 52 is always stored in the memory (volatile or non-volatile). Then, at the timing when the image setting command is received from the operation unit 51, the live image LVI stored in the memory is registered as a non-defective image OKI / defective image NGI / background image BGI. Alternatively, the live image LVI immediately after the operation unit 51 is pressed is registered in the non-defective product image OKI / defective product image NGI / background image BGI without using the image data stored in the memory. Then, the registration image is transferred to the condition assignment unit 55 and the registration result is displayed on the display unit 53. On the other hand, in the operation mode, the live image LVI to be evaluated is received from the image acquisition unit 52 and sent to the operation image processing unit 57, and the evaluation result of the operation image processing unit 57 is displayed on the display unit 53.

  At the time of setting, the setting management unit 58 always stores the image obtained from the image acquisition unit 52 in the image / setting storage unit 54, and the non-defective image setting unit 51 a, defective product image setting unit 51 b, background in the operation unit 51. The live image LVI stored in the image / setting storage unit 54 at the time of input via the image setting unit 51c or immediately after input is converted into a still image storage unit 54a (non-defective image) of the image / setting storage unit 54. Storage unit 541a, defective product image storage unit 542a, background image storage unit 543a), and displays it as a registration result on the still image display unit 53b of the display unit 53.

During driving, the setting management unit 58 outputs the image obtained from the image acquisition unit 52 as a target image to the driving image processing unit 57, and displays the evaluation result by the driving image processing unit 57 on the determination result display unit 53e of the display unit 53. To do.
(Guidance display control unit 58a)

The guidance display control unit 58a is a member for controlling display contents on the display unit 53. The guidance display control unit 58a may include a screen transition unit 58b. The image access unit 58c has a parallel display function of the live image LVI on the second registration screen and the non-defective image OKI registered in a state where the first registration screen is displayed. It may be responsible for this function.
(Screen transition part 58b)

  The screen transition unit 58b performs threshold calculation by the threshold calculation unit 56c from the first registration screen for registering one of the first image and the second image as an image used for threshold calculation by the threshold calculation unit 56c. It is a member for making it change to the 2nd registration screen which registers the other image used. The screen transition unit 58b causes the display unit 53 to display one image captured by the image acquisition unit 52 as a live image LVI on the first registration screen. Furthermore, the screen transition unit 58b causes the display unit 53 to display first registration guidance information for guiding the registration of the one image. The screen transition unit 58b displays the live image LVI in the image display area PD of the display unit 53, and displays the first registration guidance information in the explanation display area ED.

The screen transition unit 58b also displays the other image as the live image LVI in the image display area PD on the second registration screen, and displays the second registration guidance information for guiding the registration of the other image. It can also be displayed in the area ED.
(Image access unit 58c)

  The image access unit 58c is a member for saving, deleting, and reading out the non-defective product image OKI, the defective product image NGI, the background image BGI, the live image LVI, the coincidence degree statistical image, and the like. For example, in the second registration screen during teaching, the image access unit 58c displays the live image LVI on the left side of the display screen 43 via the live image display unit 53a, and has been previously registered on the right side via the still image display unit 53b. The non-defective image OKI is displayed. Thereby, the user can register the defective product image NGI while viewing the registered image of the non-defective image OKI, for example, and thus can prevent unintended registration.

  When the SET key 42 as the operation unit 51 is pressed on the first registration screen shown in FIG. 11 at the time of two-point teaching of the non-defective image OKI and the background image BGI, the image access unit 58c The live image LVI displayed in the display area PD is stored in the non-defective image storage unit 541a as the non-defective image OKI. In the second registration screen shown in FIG. 33, when the SET key 42 is pressed, the live image LVI displayed in the image display area PD is stored in the background image storage unit 543a as the background image BGI.

Further, when the SET key 42 is pressed on the second registration screen shown in FIG. 31 at the time of three-point teaching with the non-defective product image OKI, the defective product image NGI, and the background image BGI, the image access unit 58c displays the image display area. The live image LVI displayed on the PD is stored as a defective product image NGI in the defective product image storage unit 542a. In the third registration screen shown in FIG. 33, when the SET key 42 is pressed, the live image LVI displayed in the image display area PD is stored in the background image storage unit 543a as the background image BGI.
(Matching degree statistical value access unit 58d)

The coincidence statistical value access unit 58d is a member for saving, deleting, and reading the coincidence statistical value. The coincidence degree statistical value access unit 58d is calculated by the coincidence degree statistical value calculation unit 57e, for example, during operation, and is stored in the coincidence degree statistical value storage unit 54e, and the coincidence saved in the coincidence degree statistical value storage unit 54e. The degree statistics are read out and displayed on the display unit 53.
(Bank switching control unit 58e)

The bank switching control unit 58e enables switching between a plurality of banks, stores the setting in association with the bank in the bank setting storage unit 54f, reads the setting in association with the bank, and reads the setting. It is a member that performs control to be operated.
(Display control unit 58f)

The display control unit 58 f is a member for controlling display contents on the display unit 53. The display control unit 58f may include a guidance display control unit 58a. In the display unit 53, the display control unit 58f performs various displays in the first display format to the fifth display format switched by the screen display switching unit 51f.
(Registering images in setting mode)

In the image processing sensors 1 and 11, there are the following four methods for registering an image in the setting mode.
1. 3-point teaching

In the three-point teaching, a good product image OKI, a defective product image NGI, and a background image BGI are registered. Three-point teaching is aimed at identifying good and defective products. When the mode is switched to after the three-point teaching, the degree of coincidence for evaluating how close the input image is to the non-defective image OKI is calculated.
2. Two-point teaching (Register non-defective image OKI and defective image NGI)

  In the two-point teaching, a non-defective product image OKI and a defective product image NGI are registered. The two-point teaching is also aimed at discriminating between a non-defective product and a defective product. When switching to the operation mode after performing the two-point teaching, a degree of coincidence that evaluates how close the input image is to the non-defective image OKI is calculated.

  The difference from the three-point teaching is whether or not the workpiece can be specified depending on the presence or absence of the background image BGI. Since the difference process cannot be performed in a situation where the background image BGI is not registered, the non-defective workpiece / defective workpiece cannot be identified well. Since the workpiece cannot be specified, the information on the non-defective product / defective product at the time of registration is the non-defective product including the background and the defective product including the background. Since the background and the work area cannot be identified, if the background included in the non-defective image OKI and the background included in the defective image NGI are different (for example, the size of the non-defective workpiece and the defective workpiece is different), the evaluation is originally performed. Identification is attempted due to background differences that should be excluded, leading to false detection.

  Further, since it is not possible to cut out a non-defective product or a defective product not only at the time of registration but also for the driving image, the quality determination is performed based on the work including the background. In this case, even if the background unrelated to the non-defective product and the defective product changes, the degree of coincidence changes based on the change.

Since an element that is unstable with respect to the identification focusing only on the non-defective product and the defective product (for example, the background is applicable) is included in the identification, the best identification result cannot be expected. As a result, there is a difference in detection performance depending on the presence or absence of the background image BGI, and it is expected that the performance of the three-point registration that can identify the workpiece is better.
3. Two-point teaching (Register non-defective image OKI and background image BGI)

  In this two-point teaching, the background image BGI is registered instead of the non-defective product image OKI and the defective product image NGI. The purpose of this two-point teaching is to determine the presence or absence of a non-defective workpiece. When switching to the operation mode after performing two-point teaching, the probability that there appears to be a non-defective workpiece is calculated with a degree of coincidence of 0 to 100%. The

  Two-point teaching for registering the non-defective image OKI and the background image BGI can be used for identification purposes. In this case, since the non-defective workpiece is specified at the time of registration, the identification operation can be performed by identifying whether the non-defective workpiece exists on the operation screen. However, since there is no defective work, it is necessary to evaluate the degree of coincidence of the whole non-defective work. In this case, assuming that a non-defective workpiece is missing as a defective workpiece, the degree of coincidence must be changed based on the size of the piece, and a large difference in degree of coincidence will be produced for small pieces. May not be sufficient, and the sensitivity for discriminating between good and defective products may be insufficient.

  On the other hand, since the non-defective workpiece and the defective workpiece are registered in the three-point teaching, it is possible to specify a region having a difference in advance. Therefore, regardless of the size of the workpiece and the difference, it is possible to obtain a large difference in the degree of coincidence even for a small chip by determining the degree of coincidence at a portion where there is a difference.

  As a result, there is a difference in the identification performance depending on the presence or absence of the defective product image NGI, and it is expected that the three-point teaching capable of specifying the defective product has better identification performance.

Further, by registering a plurality of images, it is possible to realize high discrimination and high stability as compared with the conventional method of performing registration processing with a single image.
4). One-point teaching (Register non-defective image OKI or background image BGI)

In one-point teaching, a non-defective image OKI or a background image BGI is registered. The purpose of this one-point teaching is to evaluate whether something is different from the registered state. For example, by registering the background image BGI, it is used in such a manner that the background state is grasped and a reaction is made when some work is conveyed.
(Two-point teaching procedure for registering a non-defective image OKI and a defective image NGI)

  Next, as a specific teaching, a two-point teaching procedure will be described based on the flowchart of FIG. 8 as viewed from the image processing sensor side and FIGS. 9 to 11, 28, and 31. Here, as an example of two-point teaching, an example in which two images, a non-defective product image OKI and a defective product image NGI, are registered will be described.

  First, in step ST100, the process is started. In step ST101, it is determined whether or not the mode is switched to the two-point teaching mode. Here, it is determined whether or not a short press of the SET key 42 which is one form of the operation unit 51 is performed. Specifically, the time when the SET key 42 is pressed is measured from the operation screen shown in FIG. If a short press is detected, the process proceeds to step ST102, and if not detected, the processing in the two-point teaching mode is stopped. In the example of FIG. 8, the process returns to step ST100. Instead of returning to step ST100, a three-point teaching mode described later may be shifted.

  Next, in step ST102, the first image is registered from the first registration screen. Here, the captured image is displayed on the display screen 43. Specifically, first registration guide information that is instruction information for registering a non-defective image OKI is read from the registration identification instruction information storage unit 54 h and displayed on the display screen 43. A display example of the first registration screen on the display screen 43 is shown in FIG. The display screen 43 is provided with an image display area PD (left side in FIG. 10) and an explanation display area ED (right side). A live image LVI is displayed in the image display area PD, and registration guidance information is displayed in the explanation display area ED. I am letting. Here, the registration guide information indicates a guidance for instructing the user to register the non-defective image OKI as the first image. In this example, “SET PRESENSE” is displayed so as to instruct the registration of the image in the “detected work exists (non-defective)” state. In this way, the guidance display control unit 58a displays the first registration guidance information on the display screen 43 so that the non-defective workpiece OKI to be registered as a non-defective image OKI is placed at the imaging position for the user and is imaged by the imaging unit 21. Let me guide you. The user places a non-defective workpiece by such a display (note that the sensor may be moved without moving the workpiece, and the non-defective workpiece may be in a positional relationship that can be imaged by the imaging unit 21. The same applies hereinafter). It can be understood that an operation is necessary at this timing, and is guided to place a non-defective work according to this guidance.

Next, the current image captured by the imaging unit 21 is displayed on the first registration screen of the display screen 43. As described above, the image display area PD is in a display state of the live image LVI whose display contents are updated in real time. When the user places a non-defective workpiece at the imaging position according to the first registration guide information, the user can check the non-defective workpiece on the display screen 43 in real time as shown in FIG. 11 by the live image LVI display function. The live image LVI displayed on the display screen 43 at this stage is a good product candidate image. As described above, the display form of the image that is the candidate for the first image is the live image LVI display, so that when the user changes the position or rotation angle at which the non-defective work is placed, the display content of the display screen 43 is immediately reflected. The user can easily adjust an image to be registered as a non-defective image OKI obtained by capturing a non-defective work to a desired state. That is, when registering as a non-defective image OKI, the user visually confirms from the display screen 43 whether the size and field of view are appropriate. If there is no problem, the image currently displayed on the display screen 43 is displayed. Is registered (details will be described later).
(Enlargement / reduction function)

  In addition, the live image LVI displayed in the image display area PD can be enlarged or reduced. With such an enlargement / reduction function, the display screen 43 with a limited display area can be used effectively. The enlargement / reduction may be digital zoom of a captured optical image, or may be magnification adjustment of an optical lens provided in the imaging unit 21.

  In the example of FIG. 11, in order to show that such an enlargement / reduction operation is possible, an icon indicating the characters “ZOOM” and an upper / lower display 4315d are displayed in the explanation display area ED as enlargement / reduction display information. ing. Such visual display allows the user to recognize that the image can be enlarged or reduced on this screen. Specifically, an up / down key 44 which is one form of the increase / decrease adjustment unit 51h provided on the display surface of FIG. 6 can be operated to enlarge or reduce the image. For example, as shown in FIG. 28, when the upper key 44a of the up / down key 44 is pressed, the image is enlarged and displayed, and when the lower key 44b is pressed, the image is reduced and displayed. Alternatively, the display screen 43 may be configured as a touch panel so that an image is enlarged when an upper icon provided side by side with a “ZOOM” icon is touched and reduced when a lower icon is touched.

  As described above, the “ZOOM” icon is displayed on a screen capable of enlarging / reducing an image, and the “ZOOM” icon is not displayed on a screen where the image enlarging / reducing function is disabled. Can be notified to the user.

  The example of FIG. 11 shows an example in which display information that can be enlarged / reduced is displayed in the explanation display area ED. However, the present invention is not limited to this configuration. For example, display information that can be enlarged / reduced can be displayed in the image display area PD. Alternatively, display information that can be enlarged / reduced may be displayed across the image display area PD and the explanation display area ED.

  In this manner, the user presses the SET key 42 which is a form of the operation unit 51 in a state where the non-defective image OKI having the field of view and magnification appropriately adjusted as necessary is displayed on the image display area PD. The live image LVI displayed in the image display area PD is registered as a non-defective image OKI. A specific flow of this process will be described with reference to the flowchart of FIG.

  First, in step ST102-1, the presence / absence of an operation instruction from the operation unit 51 is detected. Here, it is determined whether or not the user has operated the SET key 42 which is a form of the operation unit 51. If there is no operation instruction, that is, if the user has not pressed the SET key 42, the process proceeds to step ST103, and the presence or absence of a magnification change instruction is detected. Here, the presence / absence of an operation of the increase / decrease adjustment unit 51h is detected. In the example of the display surface 4a shown in FIG. 6, the up / down key 44, which is an increase / decrease button, corresponds to the increase / decrease adjustment unit 51h.

  When the operation of the increase / decrease adjustment unit 51h is detected in step ST103, the process proceeds to step ST104, and the display magnification on the display screen 43 is changed. In the example of FIG. 6, when the up key 44a is pressed among the up and down keys 44, the display magnification is increased and the display is enlarged (television). On the other hand, when the down key 44b is pressed, the display magnification is reduced to widen the imaging region (wide). Then, it progresses to step ST105. Or you may return to step ST102 and repeat a display.

  On the other hand, when the operation of the increase / decrease adjustment unit 51h is not detected in step ST103, the process proceeds to step ST105, and the presence / absence of a cancel instruction is determined. The cancel instruction is issued from the cancel instruction unit 51i, and the BACK key 45 corresponds to the cancel instruction unit 51i in the example of the display surface 4a of FIG. The BACK key 45 is a key operated when the user cancels the image registration process or the like. When a cancel instruction is detected, the process is stopped (for example, the process returns to step ST100 or the two-point teaching is stopped and the operation screen of FIG. 9 is returned).

  If there is an operation instruction in step ST102-1, that is, if the user presses the SET key 42, the process proceeds to step ST102-2, and the live image LVI currently displayed in the image display area PD is registered as a non-defective image OKI. To do.

  In step ST106, the second image is registered from the second registration screen. For this reason, it is necessary to capture a new image and display it on the display screen 43. Here, the second registration guidance information, which is instruction information or guidance information for registering the defective product image NGI, is read from the registration identification instruction information storage unit 54h and displayed on the display screen 43 to constitute the second registration screen. . Specifically, as shown in FIG. 31, the guidance display control unit 58a causes the second registration guidance information to be displayed on the display screen 43, and a defective product work to be registered as a defective product image NGI for the user is set at the imaging position. Invite to put. Thereby, the user can understand that the work which puts inferior goods work is required at this timing, and is guided to the work which a user should perform. In other words, it is possible to avoid the risk of mistaking the timing of placing a non-defective workpiece and the timing of placing a defective workpiece by visual guidance through the display screen 43.

  In this way, when the user places a defective product work in accordance with the second registration guidance information displayed on the second registration screen of the display screen 43, an image newly captured by the imaging unit 21 is displayed on the display screen 43. Specifically, the current image as the defective product candidate image is displayed on the display screen 43 as the live image LVI. In this state, as shown in FIG. 31, the user can confirm on the display screen 43 a live image LVI that is a defective product candidate image obtained by imaging a defective product work. Specifically, before registering as a defective product image NGI, it is possible to visually confirm whether there is no problem in size, field of view, etc., and after determining that registration is possible, the defective product image NGI can be registered. In the example of FIG. 31, “SET NG” is displayed in the explanation display area ED so as to instruct registration of the “detected work present (defective product)” state as the second registration guidance information. On the other hand, in the image display area PD, an image that becomes a defective product candidate image is displayed as a live image LVI.

  Next, in step ST106-1, it is detected whether or not there is an operation instruction from the operation unit 51. If there is no operation instruction, that is, if the user has not pressed the SET key 42, the process proceeds to step ST107 to determine whether or not there is a cancel instruction. If pressing of the BACK key 45 is detected, the process returns to step ST102. If the operation of the BACK key 45 is not detected, the process returns to step ST106 and the process is repeated.

  Note that the display magnification changing function is not performed when registering the defective product image NGI. This is because it is necessary to match the magnifications of the non-defective product image OKI and the defective product image NGI at the time of image processing such as difference acquisition described later. Therefore, by maintaining the display magnification set at the time of registration of the non-defective product image OKI at the time of registration of the defective product image NGI, an image with the same magnification can be registered as it is, and the subsequent image work can be performed smoothly. In addition, since the scales of the non-defective product image OKI and the defective product image NGI are often approximately the same, it is often considered that the defective product image NGI can be appropriately imaged with the magnification set in the non-defective product image OKI.

  However, there may be a case where the magnification is to be changed, for example, when the defective workpiece is larger than the non-defective workpiece. In this case, a change in display magnification may be added to the defective product candidate image as in the case of the good product candidate image described above. For example, on the display screen 43 shown in FIG. 31, display information that can be enlarged or reduced, such as a “ZOOM” icon, is displayed. In this case, it is preferable to re-register the non-defective image OKI in order to make the display magnification of the registered good product image OKI coincide with the display magnification of the defective product image NGI. However, the image may be enlarged or reduced using the digital zoom or the like so that the magnifications of the non-defective product image OKI and the defective product image NGI coincide. In this case, the trouble of re-imaging the good product image OKI can be saved.

  On the other hand, if there is an operation instruction in step ST106-1, that is, if the user presses the SET key 42, the process proceeds to step ST106-2, and the live image LVI currently displayed in the image display area PD is defective. Register as an image NGI.

  In step ST108, the registered good product image OKI and defective product image NGI are stored in the good product image storage unit 541a and the defective product image storage unit 542a. In this embodiment, the registration operation is performed when the non-defective product image OKI and the defective product image NGI are prepared. However, the non-defective product image storage unit 541a or the defective product image is displayed when an operation for registering each is performed. You may make it preserve | save in the memory | storage part 542a. In step ST109, a threshold value is calculated from the non-defective product image OKI and the defective product image NGI, and the calculated threshold value is set. In this way, two-point teaching can be performed, an appropriate threshold value can be automatically calculated from the non-defective product image OKI and the defective product image NGI, and the threshold value can be set. The set threshold value may be displayed on the display screen 43. Further, the threshold value may be confirmed by switching from the setting mode registration screen to the driving screen during driving. For example, by returning to the operation mode after the two-point teaching setting mode is finished, the set threshold value is displayed on the display screen 43 in the operation screen shown in FIG. 9 so that the user can check the numerical value. Good. In addition, a newly set or updated threshold value may be displayed by blinking on the display screen 43 to indicate that the threshold value has been set or updated.

  As described above, the non-defective image OKI registration (step ST102-2) and the defective image NGI registration screen (step ST106) are simultaneously performed by pressing the SET key 42 once. Also, registration of the defective product image NGI (step ST106-2) and calculation of a threshold value from the registration process (step ST108 and subsequent steps) are simultaneously performed by pressing the SET key 42 once. As a result, the user can proceed with the two-point teaching setting operation simply by pressing the SET key 42. In other words, a complicated operation is not required, and it is possible to set a threshold value suitable for pass / fail determination by the work placing the work WK and pressing the SET key 42 according to the guidance displayed on the display screen 43.

  In addition, although these operations can be performed collectively by a single operation, labor can be saved, but on the other hand, each operation can be individually instructed. For example, the non-defective image OKI may be registered by operating the SET key 42, and the display may be switched to the registration screen for the defective image NGI by further operating the SET key 42.

As described above, it is possible to select a feature amount so that a difference between the non-defective image OKI and the defective product image NGI appears remarkably. That is, since the work area of the non-defective product and the defective product is extracted using the difference, the adjustment that maximizes the feature difference in the area can be performed. In addition, there is an advantage that registration work can be easily performed. That is, it is only necessary to press the SET key 42 while viewing an image, and it is possible to eliminate the need for a tool frame and parameter setting as in a conventional image processing sensor.
(Two-point teaching procedure for registering a non-defective image OKI and a background image BGI)

  In the above example, the two-point teaching for registering the two images, the good product image OKI and the defective product image NGI, has been described. However, the two-point teaching is not limited to a combination of these images, but can be other images. For example, two-point teaching may be performed on a non-defective image OKI and a background image BGI without a work WK. Such an example will be described based on the flowchart of FIG.

  First, in step ST200, the process is started, and in step ST201, it is determined whether or not the mode is switched to the two-point teaching mode. Here, it is determined whether or not the SET key 42 is pressed shortly. If a short press is detected, the process proceeds to step ST202. If not detected, the two-point teaching mode process is stopped.

  Next, in step ST202, the first image is registered from the first registration screen. From the start of step ST202, first registration guidance information, which is instruction information for registering the non-defective image OKI, is read from the registration identification instruction information storage unit 54h and displayed on the display screen 43 (FIG. 10). Here, the guide display control unit 58a displays the first registration guide information on the display screen 43 so that the non-defective product OKI to be registered as the non-defective image OKI is arranged for the user and the image pickup unit 21 picks up the image. Induce. From such a display, the user can understand that an operation to place a non-defective workpiece is necessary, and is guided to place the non-defective workpiece according to this guidance.

  In step ST202-1, the current image captured by the imaging unit 21 is displayed on the display screen 43. Here, the display screen 43 is in a display state of a live image LVI whose display contents are updated in real time. In this state, the user can check a live image LVI that is a good product candidate image obtained by picking up a good product work on the display screen 43 as shown in FIG. Specifically, after confirming that there is no problem in size and field of view when registering as a non-defective image OKI, if there is no problem, the SET key 42 is pressed. If there is a problem, the SET key 42 is pressed. Do not press.

  Specifically, if there is a problem, that is, if the user has not pressed the SET key 42, the presence / absence of a magnification change instruction is confirmed in step ST203, and the magnification is changed in step ST204. Thereafter, the process proceeds to step ST205, where it is determined whether or not there is a “return” instruction. The “return” instruction is determined, for example, by pressing the BACK key 45 in the example of the operation button 4C in FIG. The BACK key 45 is a key operated when the user cancels the registration of the non-defective image OKI. When the operation of the BACK key 45 is detected, the process returns to step ST200. If the operation of the BACK key is not detected, the process returns to step ST202 and the process is repeated.

  On the other hand, if there is no problem in step ST203, that is, if the user presses the SET key 42, the process proceeds to step ST202-2, and the live image LVI currently displayed in the image display area PD is registered as a non-defective image OKI. To do. The procedure so far is the same as the two-point teaching procedure for registering the non-defective product image OKI and the defective product image NGI shown in FIG.

  In step ST206, the second image is registered from the second registration screen. Specifically, the second registration guidance information, which is instruction information for registering the background image BGI, is read from the registration identification instruction information storage unit 54 h and displayed on the display screen 43. Here, as shown in FIG. 33, in order for the guidance display control unit 58a to display the second registration guidance information on the display screen 43 and register it as the background image BGI for the user, the non-defective workpiece is removed from the imaging position. To guide. The user can understand that the operation of removing the workpiece is necessary according to the displayed second registration guidance information, and the necessary operation is induced at this stage. In other words, it is possible to avoid the risk of mistaking the timing of placing a non-defective workpiece and the timing of excluding the non-defective workpiece by visual guidance through the display screen 43.

  Next, in step ST206, the current image (background candidate image) captured by the imaging unit 21 is displayed on the display screen 43. Here, on the display screen 43, the background image BGI may be displayed as a still image in addition to the live image LVI (FIG. 33). That is, unlike the work, the background image BGI does not require adjustment of the field of view or size, so it is only necessary to confirm that there is no work WK. Therefore, the purpose can be achieved without using the live image LVI, and the still image An advantage of simplifying the processing can be obtained by using the display. If there is no problem in registering as the background image BGI, the SET key 42 is pressed. Note that the display of the background image BGI may be omitted.

  Next, in step ST206-1, it is detected whether or not the SET key 42 has been pressed. If the SET key 42 has not been pressed, the process proceeds to step ST207, where it is determined whether or not a “return” instruction has been issued. When the operation of the BACK key 45 is detected, the process returns to step ST202. When the operation of the BACK key 45 is not detected, the process returns to step ST206 and is repeated.

  On the other hand, if the SET key 42 is pressed in step ST206-1, the process proceeds to step ST206-2, and the image currently displayed in the image display area PD is registered as the background image BGI.

  Further, in step ST208, the registered good product image OKI and background image BGI are stored in the good product image storage unit 541a and the background image storage unit 543a. In this embodiment, the registration work is performed when the non-defective image OKI and the background image BGI are prepared. However, the non-defective image storage unit 541a or the background image storage unit is operated when an operation for registering each is performed. You may make it preserve | save to 543a. In step ST209, a threshold value is calculated and set from the non-defective image OKI and the background image BGI. Thus, two-point teaching can be performed, and an appropriate threshold value can be automatically calculated from the non-defective image OKI and the background image BGI, and the threshold value can be set.

  As described above, it is possible to perform the determination process in which the influence of the background is removed. That is, by registering the background image BGI, it is possible to make an evaluation that is not easily affected by the background elements.

In the above example, the procedure for first registering the non-defective image OKI as the first registration screen and then registering the background image BGI as the second registration screen has been described. Thus, the order of registering images during teaching is defined in advance. Further, the above-described registration guide information is used so that the user does not mistake the image to be registered and the order. However, the order in which the images are registered is not limited to the above example. For example, it is possible to define the order as any order, for example, the background image BGI is registered first and then the non-defective image OKI is registered. Nor.
(Three-point teaching)

  The two-point teaching for registering the two points of the non-defective image OKI and the other images has been described above. However, according to the present invention, the number of images to be registered is not limited to two, and three or more images can be registered. Many conventional image processing sensors register only one image, and a plurality of image processing tools can be set for this image. In other words, most image processing sensors register a plurality of images. Does not exist. Here, considering the work of setting a plurality of image processing tools for a single image as a work on the user side, it is possible to detect image processing desired by the user from a plurality of image processing tools prepared in advance. It is necessary to select a necessary tool and set a window as an area to which the tool is applied, or select an image processing parameter to set or fine-tune these. Such work is difficult to perform properly unless it is a user with a certain level of knowledge who understands the utility and use of each prepared image processing tool, and the work itself is troublesome. .

  In addition, even when viewed from the image processing sensor side, if one non-defective image OKI is registered, it is registered as an entire image, and thus is registered as an image including the background. For this reason, the image is processed including the background, and the quality is determined. Since the background portion exists not only in the non-defective product image OKI but also in the defective product image NGI, if the background portion is large, the difference between the defective product image NGI and the non-defective product image OKI becomes small and it is difficult to detect the defective product. On the other hand, when the amount of sunlight changes between daytime and nighttime, and the amount and color of illumination light change, there is a risk that even a non-defective product will be judged as a defective product due to a difference in illumination light in the background portion. . As described above, since the conventional image processing sensor cannot determine the boundary between the target work WK region and the background, image processing is performed including a background portion that is originally unnecessary for the non-defective product determination and the defective product determination. As a result, the difference between the non-defective product and the defective product is influenced by the background and illumination light, and there is a problem that image processing based on the difference between the good product and the defective product to be detected may not be appropriately performed.

  On the other hand, in the present embodiment, by registering three images of a non-defective product image OKI, a defective product image NGI, and a background image BGI, it is possible to extract a non-defective product work and a defective product work excluding the background, and the accuracy of pass / fail judgment is improved. Can be improved. Specifically, by registering not only the non-defective image OKI but also the background image BGI, unnecessary portions such as the background can be extracted and excluded from the determination target. Furthermore, when registering these images, it is possible to calculate and set an appropriate threshold value by simply registering the three images in sequence, such as setting windows and setting image processing parameters as in the past. Troublesome work is unnecessary, and the labor saving of setting work itself is realized.

  More specifically, in the present embodiment, three images of a non-defective product image OKI, a defective product image NGI, and a background image BGI are registered as three-point teaching, and the non-defective product image OKI and the background image are registered based on these three images. The difference between the BGI and the difference between the defective product image NGI and the background image BGI are extracted. As a result, it is possible to extract non-defective workpieces and defective workpieces excluding the background.

  FIG. 34A shows an example in which the background image BGI is removed from the non-defective image OKI and a simple difference image for extracting only the non-defective work is generated. FIG. 34B shows an example in which the background image BGI is removed from the defective product image NGI, and a simple difference image in which only the defective product work is extracted is generated. Such a difference image is obtained by subtracting corresponding pixels of two images.

However, in this specification, “difference” is not limited to such simple difference processing that subtracts corresponding pixels. For example, it is used in a sense including specifying a work area by excluding a common element with the background.
(Three-point teaching procedure)

  Here, in the setting mode, the procedure for performing the three-point teaching for registering the three images of the non-defective product image OKI, the defective product image NGI, and the background image BGI will be described with reference to the flowchart of FIG. 35 and FIGS. To do.

  First, in step ST300, the process is started, and in step ST301, it is determined whether or not the mode is switched to the three-point teaching mode. Here, it is determined whether or not the SET key 42 has been pressed for a long time. Specifically, the time when the SET key 42 is pressed is measured from the operation screen of the display screen 43 shown in FIG. When the long press is detected, the process proceeds to step ST302, and when it is not detected, the process of the three-point teaching mode is stopped. In the example of FIG. 35, the process returns to step ST300. In the case of a short press, the above-described two-point teaching mode may be entered.

  Next, in step ST302, the first image is registered from the first registration screen. Here, the captured image is displayed on the display screen 43. Specifically, first registration guide information that is instruction information for registering a non-defective image OKI is read from the registration identification instruction information storage unit 54 h and displayed on the display screen 43. Here, the guidance display control unit 58a displays the first registration guidance information on the display screen 43 so that the non-defective product OKI to be registered as a non-defective image OKI for the user is placed at the imaging position and is imaged by the imaging unit 21. Induce. From such a display, the user can understand that an operation for placing a non-defective workpiece is necessary, and is guided to place a non-defective workpiece according to this guidance.

  Further, the current image captured by the imaging unit 21 is displayed on the display screen 43. Here, the display screen 43 is in a display state of a live image LVI whose display contents are updated in real time. In this state, the user can confirm a live image LVI, which is a non-defective product candidate image obtained by capturing non-defective workpieces, on the display screen 43 as shown in FIG. Specifically, when registering as a non-defective image OKI, it is confirmed whether there is no problem in size or field of view. If there is no problem, the SET key 42 is pressed.

  In the example of FIG. 36, registration order information indicating the order of images to be registered is displayed on the explanation display area ED (details will be described later). A “ZOOM” icon is also provided as display information that can be enlarged or reduced. Here, the registration order information is arranged in the upper part of the explanation display area ED, and the display information that can be enlarged / reduced is arranged in the lower part, but the present invention is not limited to this arrangement example. Further, a guide line that stores the difference of the workpiece WK is displayed in the image display area PD (details will be described later).

  Next, in step ST302-1, it is detected whether or not there is an operation instruction from the operation unit 51. If there is no operation instruction, that is, if the user has not pressed the SET key 42, the process proceeds to step ST303, and the presence / absence of a magnification change instruction is detected. Here, the presence / absence of operation of the increase / decrease adjustment unit 51h is detected, and in the example of the display surface 4a shown in FIG. If an operation of the increase / decrease adjustment unit is detected in step ST303, the process proceeds to step ST304, and the display magnification is changed. Then, it progresses to step ST305. Alternatively, the display may be repeated by returning to step ST302. On the other hand, when the operation of the increase / decrease adjustment unit is not detected in step ST303, the process proceeds to step ST305, and it is determined whether or not there is a cancel instruction. Here, it is determined whether or not there is a “return” instruction. Specifically, when the operation of the BACK key is detected, the process returns to step ST300, and when the operation of the BACK key is not detected, the process returns to step ST302 and the process is repeated. Alternatively, the three-point teaching may be stopped and the operation screen of FIG. 9 may be returned.

  On the other hand, if there is an operation instruction in step ST302-1, that is, if the user presses the SET key 42, the process proceeds to step ST302-2, and the live image LVI currently displayed in the image display area is displayed as a non-defective image OKI. Register as

  In step ST306, the second image is registered on the second registration screen. Specifically, the second registration guidance information, which is instruction information for registering the defective product image NGI, is read from the registration identification instruction information storage unit 54 h and displayed on the display screen 43. Here, the guidance display control unit 58a displays the second registration guidance information on the display screen 43, and guides the user to place the defective product work to be registered as the defective product image NGI at the imaging position.

  Further, the current image (defective product candidate image) captured by the imaging unit 21 is displayed on the display screen 43. An example of such a second registration screen is shown in FIG. Here, the defective product candidate image is displayed as a live image LVI in the image display area PD. The user adjusts the imaging position, orientation, and magnification as necessary to register as a defective product image NGI, and presses the SET key 42 when determining that registration is possible on the live image LVI.

  Next, in step ST306-1, it is detected whether or not there is an operation instruction from the operation unit 51. If there is no operation instruction, that is, if the user has not pressed the SET key 42, the process proceeds to step ST307, where it is determined whether or not there is a cancellation instruction. Here, when a “return” instruction, for example, pressing of the BACK key 45 is detected, a predetermined operation is performed such as stopping the processing and returning to step ST301. If pressing of the BACK key 45 is not detected, the process returns to step T306 and the process is repeated.

  On the other hand, if there is an operation instruction in step ST306-1, that is, if the user presses the SET key 42, the process proceeds to step ST306-2, and the live image LVI currently displayed in the image display area PD is defective. Register as an image NGI.

  In step ST308, the third image is registered on the third registration screen. Specifically, the third registration guidance information that is instruction information for registering the background image BGI is read and displayed on the display screen 43. Here, the guidance display control unit 58a displays the second registration guidance information on the display screen 43 to prompt the user to remove the defective workpiece from the imaging position in order to capture the background image BGI. The user is instructed that the work WK needs to be removed in accordance with the displayed third registration guidance information, and is guided to capture the necessary work, that is, the background image BGI without the work WK. The background image BGI captured in this way is displayed in the image display area. An example of such a third registration screen is shown in FIG. The background image BGI can be displayed as a still image as described above in addition to the live image LVI. That is, unlike the work WK, the background image BGI does not require adjustment of the field of view or the size, so it is only necessary to confirm that there is no work WK. Therefore, the purpose can be achieved without using the live image LVI, and the still image can be achieved. By displaying the above, there is an advantage that the processing can be simplified. Alternatively, the display of the background image BGI may be omitted. If there is no problem in registering as the background image BGI, the SET key 42 is pressed.

  Further, in step ST308-1, it is detected whether or not there is an operation instruction from the operation unit 51. If there is no operation instruction, for example, if the user has not pressed the SET key 42, the process proceeds to step ST309, where it is determined whether or not there is a cancellation instruction. For example, when an operation of the BACK key 45 is detected as a “return” instruction, predetermined processing such as returning to step ST306 is performed. If the operation of the BACK key 45 is not detected, the process returns to step ST308 and is repeated.

  On the other hand, when there is an operation instruction in step ST308-1, for example, when the user presses the SET key 42, the process proceeds to step ST308-2, and the image currently displayed in the image display area PD is set as the background image BGI. sign up.

  In step ST310, the registered three images are stored in the still image storage unit 54a. In step ST311, a threshold value is calculated and set from the good product image OKI, the defective product image NGI, and the background image BGI. In this way, it is possible to perform the three-point teaching, automatically calculate an appropriate threshold value from the non-defective product image OKI, the defective product image NGI, and the background image BGI, and to set the threshold value.

  In this three-point teaching example, the enlargement / reduction function is functioned only when the non-defective image OKI is registered on the first registration screen, and the enlargement / reduction function is not operated on the second registration screen or the third registration screen. That is, the second image and the third image are registered while being fixed at the magnification set on the first registration screen, and the user's setting work is complicated by the control to automatically turn on / off such an enlargement / reduction function. It avoids confusion and simplifies operation. However, the enlargement / reduction function may be turned on in the second registration screen or the third registration screen.

In the three-point teaching example described above, first, a non-defective image OKI is registered as a first registration screen, a defective image NGI is registered as a second registration screen, and a background image BGI is registered as a third registration image. Explained. Here, the order in which the images are registered is not limited to the above. For example, the background image BGI is registered as the second registered image first, and then the defective product image NGI is registered. Needless to say.
(One-point teaching procedure for registering OK image OKI or background image BGI)

  Further, a one-point teaching procedure for registering the non-defective image OKI or the background image BGI will be described with reference to FIG. First, in step ST401, a background image BGI is acquired. For example, a background image BGI as shown in FIG. 40 is registered.

  Next, in step ST402, the resolution of the background image BGI is reduced based on a preset response time setting.

  In step ST403, the entire screen is set as an evaluation area. For example, for the background image BGI of FIG. 40, an evaluation area is automatically set as shown by a frame shape in FIG.

  Further, in step ST404, feature amounts are extracted. Specifically, first, in step ST404-1, the feature amount of the background image BGI in the evaluation area is extracted. For example, with respect to the background image BGI of FIG. 41, feature quantities such as 0 edge points and an average luminance of 70 are obtained.

  Next, in step ST404-2, an evaluation weight is determined for each feature amount. For example, 50% of the number of edge points and 50% of the average luminance are selected as the feature values for pass / fail judgment.

  In step ST404-3, a threshold is set. For example, a threshold value is automatically set for the number of edge points and the average brightness.

When the setting mode is thus completed, the operation mode is entered. In the operation mode, in step ST405, the input image is evaluated. Note that no search is performed here.
(Setting when the discrimination target is a defective workpiece)

  The selection function of the discrimination target described above is a mode in which the master image is switched to either a non-defective image OKI or a defective product image NGI, so that the two-point teaching mode or the three-point teaching mode for registering the non-defective product and the defective product can be linked. It is a function to attach. Here, a setting procedure when the discrimination target is a defective workpiece will be described based on an example of a three-point teaching mode in which image registration is performed in the order of a non-defective product image OKI, a defective product image NGI, and a background image BGI. Here, a setting operation procedure when the discrimination target is a defective workpiece will be described based on the flowchart of FIG. FIG. 42 is a flowchart illustrating an operation procedure for setting when the determination target is a defective workpiece WK.

  First, processing is started in step ST450, and in step ST451, the work WK is imaged by the imaging unit 21, and the live image LVI is displayed on the display screen 43. In step ST452, it is determined whether or not the SET key 42 is pressed. If pressing of the SET key 42 is detected, the process proceeds to step ST453, and the live image LVI is registered in the non-defective image OKI. If pressing of the SET key 42 is not detected, the process returns to step ST451, and the live image LVI is updated. In steps ST454 to ST459, as in steps ST451 to ST453, a live image LVI is displayed, whether or not the SET key 42 is pressed is determined, and the live image LVI is converted into a defective product image NGI and a background image BGI. Register each.

  Proceeding to step ST460, registration processing is executed using the defective product image NGI from the three registered images as a master image. 35A and 35B, the main difference in operation procedure from the case where the discrimination target is the non-defective workpiece WK is that when the discrimination target is the non-defective workpiece WK, registration processing is performed using the non-defective image OK as a master image. On the other hand, when the discrimination target is a defective product WK, registration processing is performed using the defective product image NGI as a master image.

Finally, a threshold value is calculated and set in step ST461. Specifically, when the discrimination target is a non-defective product WK, the coincidence calculation unit 57c calculates a first coincidence indicating the degree of feature coincidence of the defective product image NGI with the model pattern corresponding to the non-defective product OKI. When the threshold value calculation unit 56c calculates the first threshold value used in the operation mode on the basis of the first degree of coincidence, it matches when the discrimination target is the defective workpiece WK. A second degree of matching indicating the degree of feature matching of the non-defective image OKI with the model pattern corresponding to the defective product image NGI is calculated by the degree calculating unit 57c, and based on the second degree of matching by the threshold calculating unit 56c. The third threshold value used in the operation mode is calculated.
(Preferred registration status)

In registering an image in the image / setting storage unit 54 in the setting mode, registration is performed under preferable registration setting conditions. Here, the preferable registration setting condition is a condition that allows the good / bad determination unit 57d to determine the good / defective product stably when the good / bad determination unit 57d makes the good / bad determination. In this determination, it is important how to distinguish between a good product and a defective product stably. In the operation mode, the pass / fail determination unit 57d performs pass / fail determination using the matching degree between the input live image LVI and the non-defective image OKI as an evaluation value. With respect to the input live image LVI, an evaluation value of 0% to 100% is calculated as the coincidence calculated by the coincidence calculating unit 57c. When the input live image LVI is a non-defective image OKI obtained by capturing a non-defective product, the degree of coincidence is ideally calculated as 100%. However, when the input live image LVI is a defective product image NGI obtained by imaging a defective product, the degree of coincidence is generally not 0%. This is because, in many cases, the defective image NGI includes a portion that matches the non-defective image OKI because a part of the non-defective image OKI varies depending on chipping or cracking.
(Threshold)

  The threshold value that serves as a criterion for pass / fail determination is determined based on the degree of coincidence of defective products and the degree of coincidence of non-defective products. For example, the threshold value calculation unit sets an intermediate value between the degree of coincidence of non-defective products that generally increases and the degree of coincidence of defective products that generally decreases as the threshold value. Here, in order to stably distinguish between non-defective products and defective products, that is, to stabilize the determination result, it is necessary to separate them as much as possible so that the difference between the conformity of good products and the conformity of defective products becomes large. preferable. From this, under the condition that the variation in the degree of coincidence with the non-defective product can be considered to be constant, the lower the degree of coincidence of the defective product, the greater the difference in the degree of coincidence between the non-defective product and the defective product. Since a pass / fail judgment can be expected, it is considered a good registration state. Therefore, it is necessary to obtain the brightness and resolution of the image to be captured and the image processing conditions so that the non-defective product and the defective product are separated and a stable determination result is obtained. This makes it possible to appropriately set a threshold value that serves as a criterion for pass / fail judgment.

The coincidence degree calculation unit 57c and the threshold value calculation unit 56c are separate members in the example of the block diagram of FIG. 7, but the present invention is not limited to this configuration. For example, the coincidence degree calculation unit 57c and the threshold value calculation unit 56c are the same. You may comprise with a member.
(Method in which threshold calculation unit 56c sets a threshold)

  Setting of a threshold value that serves as a criterion for pass / fail determination is performed by the threshold value calculation unit 56c. The threshold value calculation unit 56c sets a threshold value between the matching level of the defective product image NGI calculated by the matching level calculation unit 57c and the matching level of the non-defective product image OKI. It is desirable that the threshold value be set in the middle of the degree of coincidence between the good product image OKI and the defective product image NGI. As an example, the table in FIG. 43 shows an example in which the threshold is set according to the degree of coincidence of the defective product image NGI when the degree of coincidence of the non-defective product image OKI is 100%. For example, when the degree of coincidence of the defective product image NGI is 80%, the threshold is set to (100% + 80%) / 2 = 90%. Similarly, when the degree of coincidence of the defective product image NGI is 70%, the threshold is set to (100% + 70%) / 2 = 85%. When the degree of coincidence of the defective product image NGI is 60%, the threshold is (100% + 60%) / 2 = 80%, and when the degree of coincidence is 50%, the threshold is (100% + 50%) / 2 = 75%, respectively.

As described above, it is considered that the lower the coincidence degree of the defective product image NGI, the more the non-defective product image OKI and the defective product image NGI are separated, and the stability of the quality determination is improved. Therefore, when registering an image in the image / setting storage unit 54, an image registration state in which the degree of coincidence of the defective product image NGI is thus reduced is aimed. In the example of FIG. 43, the lowest threshold of 50% is preferable because the difference in the degree of coincidence between the non-defective product image OKI and the defective product image NGI is the largest.
(Determination of feature value at the time of registration)

On the other hand, if the pass / fail determination is performed only with the feature amount having the lowest difference in the degree threshold, an erroneous determination may occur in a specific case. For example, in the feature amounts A to D in which the degree of coincidence between the non-defective product image OKI and the defective product image NGI is a value as shown in Table 1, the feature amount D has the largest difference in the degree of coincidence between the good product image OKI and the defective product image NGI. Although large and preferable, specific noise resistance may be reduced.

Therefore, the pass / fail judgment result can be stabilized by evaluating pass / fail judgment by considering other feature quantities instead of making pass / fail judgment by one feature quantity. For example, in the case of Table 1, not only the feature quantity D is determined, but also other feature quantities A and B that can discriminate between good and defective products are evaluated.
(Weight setting unit 56e)

  Here, in the setting mode, the image processing sensor sets, for each image processing algorithm, a weight used when the threshold value calculation unit 56c calculates the threshold value according to the first matching degree for each of a plurality of different image processing algorithms. The weight setting unit 56e can also be provided.

  In order to perform evaluation combining a plurality of feature amounts, for example, weighting is performed on the plurality of feature amounts. As for the weighting, the larger the difference in the degree of matching between the non-defective product and the defective product, the larger the weighting, and conversely, the smaller the difference in the matching degree, the smaller the weighting. For example, in the example of Table 1, weighting of 40% for the feature amount A, 10% for the feature amount B, 0% for the feature amount C, and 50% for the feature amount D is performed. In this case, the feature amount C has a weighting of 0% and is not evaluated even if it is calculated.

Such weighting of the feature amount can be performed by the above-described feature amount extraction unit 56b. In both the registration mode and the operation mode, the coincidence degree is calculated by the coincidence degree calculating unit 57c. The coincidence calculation unit 57c calculates the coincidence for the input image based on the weight calculated at the time of registration. For example, when the feature amounts A to D in Table 1 are evaluated with the above-described weighting, the final score of the matching degree is
(Score of feature quantity A) x (weight of feature quantity A) + (score of feature quantity B) x (weight of feature quantity B) + (score of feature quantity C) x (weight of feature quantity C) + (feature The score of the quantity D) x (weight of the feature quantity D) can be calculated.
(Guide line)

  In the example of FIG. 36 and the like described above, a guide line serving as an index for positioning the workpiece WK is shown in the image display area PD. These guide lines are displayed in a frame shape surrounding the four corners in an L shape. By doing so, for example, the user is positioned so that a characteristic part such as a part that appears to be defective among the workpiece WK that is an inspection target is included in the frame of the guide line. Encourage matching. In other words, an effect that makes the user aware that an important image is arranged near the center is obtained, and as a result, evaluation with weighting on the feature difference is expected, and the determination of the degree of coincidence is stably performed, A highly reliable determination result can be obtained. In addition, the guide line is not limited to such a frame shape, and other modes, for example, a cross line passing through the center of the image display area PD, a target shape, or the like, are appropriately displayed to guide the work WK to be arranged at the center. Can be adopted. The guide line display may be switched on / off.

In the example of FIGS. 11 and 33 described above, the example in which the character information is displayed in two rows as the first registration guidance information has been described. However, the character information may be displayed in one row. Such an example is shown in FIGS. FIG. 44 displays “OK SET” in the explanation display area ED as the first registration guidance information for registering the non-defective image OKI on the first registration screen. In FIG. 45, “BG SET” is displayed in the explanation display area ED as the second registration guidance information for registering the background image BGI on the second registration screen.
(Registration order information)

Furthermore, registration order information indicating the registration order may be included as the registration guidance information. For example, “1” is displayed on the first registration screen of FIG. 44 and “2” is displayed on the second registration screen of FIG. 45, and the user visually grasps the stage of image registration from these displays. can do. In this way, the registration guidance information can use numbers as well as character strings. The number may indicate the type of display screen in addition to the image registration order. For example, “1” is displayed on the first registration screen, “2” is displayed on the second registration screen, and “3” is displayed on the third registration screen. You may let them.
(Guidance information)

  In the above example, the display control unit 58f has explained the example in which the character information is displayed on the display screen 43 as the guidance information. However, the present invention is not limited to the guidance by characters, and may be a figure, a voice, or a combination thereof. The registration procedure can be guided to the user in other manners. As an example, FIGS. 46 and 47 show an example in which a registration instruction is performed by combining symbols with characters. FIG. 46 is a diagram showing how the workpiece WK is placed at the imaging position as the first registration guidance information for instructing registration in the “with detected workpiece” state, and corresponds to FIGS. 11 and 44 described above. Also in this figure, in order to show that the live image LVI displayed in the display area can be enlarged / reduced, a “ZOOM” icon may be displayed as the enlargeable / reducible display information in the explanation display area ED. Further, such display information that can be enlarged / reduced is not limited to horizontal writing as in the example of FIG. 11, but can also be shown in vertical writing as shown in FIG. Thereby, the display area of a limited area can be used effectively.

FIG. 47 shows, as a second registration guidance information for instructing the registration of the “no detected workpiece” state, a state in which the workpiece WK is removed from the imaging position, and corresponds to FIG. 33 and the like. Thus, by displaying the figure on the display unit, it is possible to visually instruct the operation to be performed and provide an easy-to-understand operation environment for a user who is not familiar with the operation. Further, the graphic is not limited to a still image, and can be displayed as a moving image. For example, by displaying the state of placing the work WK by hand or the state of removing the work WK with a moving image, for example, an animation, the user can instruct the operation to be performed more easily.
(Display switching)

Further, the display unit 53 may switch between a plurality of screen displays. For example, in the example of FIGS. 46 and 47, the image display area PD and the explanation display area ED are displayed simultaneously on one screen. However, as shown in FIGS. 48 and 49, the image display area PD and the explanation display are displayed. The area ED can be switched and displayed. Alternatively, the image display area PD and the explanation display area ED are not limited to switching, and the images may be switched and displayed. For example, as shown in FIG. 50, on the second registration screen, the candidate image to be registered and the registered good product image OKI are switched and displayed. Thereby, since an explanation can be displayed together with the image, it becomes easier to grasp which image is displayed and what is displayed, and the two images can be compared by switching and displaying. Alternatively, as shown in FIG. 51, on the second registration screen, a candidate image to be registered and a parallel display (here, a non-defective image OKI and a candidate image) described later can be switched and displayed. In this way, the display area of the limited display screen 43 can be used more effectively. Especially when the display area of the display screen 43 is small, the displayed image and characters are reduced, or the display screen 43 with high resolution is displayed. Can be avoided. The screen can be automatically switched alternately at a constant cycle. Alternatively, in addition to such an automatic alternate display function, the user may manually perform the operation by operating a switching button or the like.
(Parallel display function)

In two-point teaching or three-point teaching, a plurality of images can be displayed side by side on one screen. For example, after registering one image in the setting mode, when registering the other, the registered image is displayed as a still image, and the currently registered image is displayed as a live image LVI. An example of such parallel display is shown in FIG. This figure shows a second registration screen for two-point teaching. Here, it is assumed that the non-defective image OKI is registered as the first image in advance on the first registration screen for two-point teaching. In the second registration screen for registering the defective product image NGI as the second image in this state, as shown in FIG. 52, the first image display region for displaying the first image in the image display region PD of the display screen 43, A second image display area for displaying two images is provided. Thus, the user can register the defective product image NGI while taking into account the registered good product image OKI. Such a second registration screen can be used in place of the above-described FIG. 31, FIG. Such a parallel display function can be applied not only to the second registration screen but also to the third registration screen.
(Still image / live image LVI simultaneous display function)

  In parallel display, some images can be displayed as still images, and other images can be displayed as live images LVI. In other words, the registered image is displayed as a still image, and the image to be registered is displayed as a live image LVI. It becomes easy to adjust to a proper state. For example, in the example of FIG. 52, a non-defective image OKI is displayed as a still image as the first image in the first image display area on the right side, and the live image of the defective product image NGI registered as the second image in the second image display area on the left side. The image LVI is displayed. The user can adjust the placement so that the posture or size of the defective product matches that of the good product image OKI while looking at the good product image OKI on the right side. Also, the amount of illumination light can be adjusted. As a result, the non-defective product image OKI and the defective product image NGI can be registered as a state in which the difference is likely to be highlighted when extracting the difference so that the same part can be easily matched. The degree can be easily calculated, and is advantageous in setting a threshold value for distinguishing between the two. Further, by displaying the non-defective image OKI that has already been registered, the user can confirm whether or not the non-defective image OKI registered earlier is correctly registered. For example, when an unintentional background cutout occurs in the non-defective image OKI, this can be noticed, which is a judgment material for re-imaging. Furthermore, by displaying the non-defective product image OKI and the defective product image NGI side by side on the screen of the display unit 53, it is possible to compare the difference between the actual work WK on the screen. By making the state of the registered image into a state in which the user can be conscious, it becomes easy to create a good registration state, which can lead to stable detection.

  An example of a procedure for realizing such a still image / live image LVI simultaneous display function is shown in the flowchart of FIG. This corresponds to the detailed flow of step ST108 in the two-point teaching of FIG. First, in step ST501, a live image LVI is acquired. Here, the live image LVI is imaged by the imaging unit as an optical image that is a defective product candidate image as the second image. Next, in step ST502, the contents of the memory holding the live image LVI are updated. Specifically, the previous live image LVI is imaged and the data stored in the live image storage unit 54b is overwritten and saved with the newly acquired live image LVI data. Note that the live image storage unit 54b may be a dedicated memory for the live image LVI or a common memory. Next, in step ST503, the stored live image LVI and the non-defective product image OKI registered on the first registration screen are read out. In step ST504, these images are transferred to the display screen. Here, the non-defective product image OKI is displayed as a still image and the defective product candidate image is displayed as a live image LVI on the second registration screen. Thereafter, these steps are repeated to realize a real-time display in which the display content of the display unit 53 is updated. In this way, while displaying the non-defective product image NGI, the live image LVI is displayed, and the non-defective product OKI is adjusted while adjusting the position and orientation of the defective work, and the adjusted image is displayed. An environment in which a desired image can be easily registered is provided so that it can be confirmed on the display unit in real time.

  In the above example, the non-defective image OKI registered on the first registration screen is displayed as a still image on the second registration screen and the defective product image NGI is displayed as the live image LVI. For example, the non-defective image OKI registered on the first registration screen can be displayed as a still image on the second registration screen, and the background image BGI can be displayed as the live image LVI. Or conversely, the background image BGI and the defective product image NGI are registered on the first registration screen, and the non-defective product image OKI is displayed as the live image LVI while the registered images are displayed as still images on the second registration screen. You can also register. Further, the still image / live image LVI simultaneous display function is not limited to two-point teaching, but can also be used in three-point teaching. That is, the non-defective image OKI registered on the first registration screen is displayed as a still image on the second registration screen, the defective product image NGI is displayed as a live image LVI, and the non-defective image OKI is displayed still on the third registration screen. The background image BGI can also be displayed as the live image LVI while being displayed as a picture. Alternatively, the background image BGI may be displayed as the live image LVI while the defective product image NGI is displayed as a still image on the third registration screen.

  Alternatively, the parallel display or the still image / live image LVI simultaneous display may be combined with the single display in the three-point teaching. For example, when registering the defective product image NGI on the second registration screen, the non-defective product image OKI is displayed on the first registration screen while displaying the non-defective product image OKI of the still image and the defective product candidate image of the live image LVI in parallel. When registering and when registering the background image BGI on the third registration screen, a single image is displayed. In particular, since it is often sufficient to capture the background image BGI in general, the processing can be simplified by eliminating the need for parallel display.

  As such a parallel display screen, for example, a registered image and the current live image LVI are displayed side by side. As an example, the display unit shown in FIG. 52 displays the registered good product image OKI and the current live image LVI as the defective product candidate image side by side. In this case, the normal registration screen and the parallel display screen may be switched and displayed. For example, during the above-described three-point teaching, the second registration screen shown in FIG. 37 and the parallel display screen shown in FIG. 52 can be switched and displayed. As a result, when the defective product image NGI is registered, it can be registered while comparing with the non-defective product image OKI. Similarly, when the background image BGI is registered, for example, when the third registered image shown in FIG. 38 is displayed, the registered defective product image NGI shown in FIG. You may switch and display the parallel display screen which displayed the still image or the live image LVI side by side. Alternatively, the parallel display screen may be a combination of the non-defective product image OKI and the background image BGI, without combining the defective product image NGI and the background image BGI. Furthermore, the parallel display screen is not limited to a configuration in which two images are displayed in parallel, and three or more images may be displayed on one screen.

  In the above example, the image display area PD and the explanation display area ED are separated, but these may be displayed partially overlapped or overlapped. For example, in the example of FIG. 55, the image display area PD and the explanation display area ED are partially overlapped to display the character information that is the first registration guidance information. Alternatively, as shown in FIG. 56, the character information may be displayed by completely overlapping the image display area PD and the explanation display area ED. Further, without distinguishing between the image display area PD and the explanation display area ED, these can be integrated and the first registration guidance information can be incorporated and displayed during the display of the image. In this way, the limited display area can be used effectively. As described above, in the present embodiment, the image display area PD and the explanation display area ED are exclusively provided, or the boundary does not necessarily have to be clearly divided, and the parts may be arranged so that part or all of them overlap. It also includes a mode in which character information is superimposed on an image, for example, by unifying it.

  In these examples, the character strings and icons on the display unit are written in English, but it is needless to say that the language is not limited to English and may be Japanese or other languages.

In this way, by guiding the setting work in the setting mode so that it can be advanced by pressing the SET key 42, it is excellent that even a beginner who does not understand the operation principle of the image processing sensor can easily use it. Demonstrate convenience.
(Procedure for increasing / decreasing the image magnification with the up / down key 44)

  At the time of image registration, the up / down key 44 or the up / down display 4315d functions as a switch for increasing / decreasing the magnification of the image. The procedure for increasing / decreasing the image magnification will be described below with reference to the flowchart of FIG. 57 and FIG. 29A. Unless otherwise specified, the operation of pressing the up / down key 44 here includes an operation of touching the up / down display 4315d.

  First, image registration processing is started in step ST550, a live image LVI is acquired by the imaging unit 52 in step ST551, and a display image is constantly updated in step ST552. In step ST553, it is determined whether or not the upper key 44a or the lower key 44b of the up / down key 44 has been pressed. If it is detected that the up / down key 44 is pressed, the process proceeds to step ST554. If the up key 44a is pressed, the setting for increasing the image magnification is changed, and if the down key 44b is pressed, the image magnification is reduced. Change the settings. Then, returning to step ST551, imaging is performed with the changed image magnification, and a live image LVI is acquired. If the pressing of the up / down key 44 is not detected, it is determined in step ST555 whether the SET key 42 has been pressed. If pressing of the SET key 42 is not detected, the process returns to step ST551, and a live image LVI is acquired at an image magnification without change.

In step ST555, when pressing of the SET key 42 is detected, it progresses to step ST556 and a display image is registered as a registration image. Next, in step ST557, an image registration process is performed. When the image registration process is completed, the operation is started.
(Setting of the first threshold and the second threshold)

  Here, the procedure for setting the first threshold value and the second threshold value in the setting mode will be described with reference to the flowchart of FIG. 58 and FIG. 22A.

  First, in step ST600, the process is started, and in step ST601, the first threshold setting is displayed. In step ST602, it is determined whether or not the up / down key 44 has been pressed. If pressing of the up / down key 44 is detected, the process proceeds to step ST603, where the first threshold setting value is changed and stored in the threshold (first, second) storage unit 54g. When not detected, it progresses to step ST604 and a 1st threshold value setting value is hold | maintained. At this time, the first threshold value is set for the output channel 1 in the example of the left diagram of FIG. 22A.

  Regardless of whether step ST603 or step ST604 is passed, the process proceeds to step ST605 to determine whether or not the MODE key 46 is pressed. If the pressing of the MODE key 46 is detected, the process proceeds to step ST606, and the second threshold setting is displayed. In step ST607, it is determined whether or not the up / down key 44 has been pressed. If pressing of the up / down key 44 is detected, the process proceeds to step ST608, where the second threshold value is changed and stored in the threshold (first, second) storage unit 54g. When not detected, it progresses to step ST609 and hold | maintains a 2nd threshold value setting value. At this time, the second threshold value is set for the output channel 2 in the example of the right side of FIG. 22A.

After executing the procedure of step ST608 or step ST609, the setting of the first threshold value and the second threshold value ends. If the pressing of the MODE key 46 is not detected in step ST605, the process ends without setting the second threshold value.
(Operation mode)

  When the setting of the threshold value for the degree of coincidence of images is completed as described above, the mode can be shifted from the setting mode to the operation mode. In the operation mode, an image of a workpiece actually conveyed on the conveyance line is taken, a degree of coincidence is calculated with respect to the obtained input image, and a non-defective product or a defective product is determined by comparison with a threshold value. Also, if the desired determination result is not obtained according to the determination result in the operation mode, or if you want to adjust to a setting with higher accuracy, enter the setting mode again and update the setting. Can do. Alternatively, the registration setting condition can be temporarily changed during the operation mode. For example, the threshold value is finely adjusted according to the pass / fail judgment result (details will be described later).

Switching between the operation mode and the setting mode is performed from the operation / setting mode switching unit. As an example of the operation / setting mode switching unit, the SET key 42 is used in the image processing sensor of FIG. Here, as shown in FIG. 59, the operation mode and the setting mode can be switched by pressing the SET key 42. For example, in the above-described setting mode, when the SET key 42 is pressed in a state where necessary image registration has been completed, the operation mode is switched. Here, in the setting mode described above, the SET key 42 is used to instruct screen transition such as transition from the first registration screen to the second registration screen. Then, by pressing the SET key 42 when the final setting is completed, the setting mode can be switched to the operation mode. In this way, the screen switching means in the setting mode and the switching means from the setting mode to the operation mode are the common operation, in this case, the user presses the SET key 42 by pressing the SET key 42. By repeating the above, necessary settings can be made and further switching from the setting mode to the operation mode can be performed, thereby realizing a smooth setting work. Further, switching from the setting mode to the operation mode can be made common with the final work in the setting mode. For example, in the three-point teaching shown in FIG. 59, a non-defective image OKI is registered by pressing the SET key 42 on the first registration screen, and a defective product image NGI is registered by pressing the SET key 42 on the second registration screen. Further, by pressing the SET key 42 on the third registration screen, the background image BGI is registered, and the switching operation from the setting mode to the operation mode is simultaneously performed. As a result, the operation mode is automatically switched to after the necessary settings are completed, and the user can smoothly switch from the setting operation to the operation mode without being confused.
(Procedure for increase / decrease of threshold value by up / down key 44)

  During operation, the up / down key 44 or the up / down display 4315a, b functions as a switch for increasing or decreasing the threshold value. The procedure for increasing / decreasing the threshold will be described below with reference to the flowchart of FIG. 60 and FIGS. 29B and 29C. Unless otherwise specified, the operation of pressing the up / down key 44 here includes an operation of touching the up / down displays 4315a and 4315b.

  When the image registration process is completed through the above-described step ST557, the operation is started. With respect to the operation by pressing the up / down key 44, the procedure of the flowchart of FIG. 57 and the procedure of the flowchart of FIG. 60 are alternately repeated, and transition from the setting mode to the operation mode or from the operation mode to the setting mode. In the series of steps, the increase / decrease of the image magnification and the increase / decrease of the threshold can be made to function by operating one up / down key 44, respectively.

  As shown in the flowchart of FIG. 60, the operation is started in step ST650, the live image LVI is acquired in the imaging unit 21 in step ST651, the image processing is performed in step ST652, and the coincidence calculation unit 57c is matched. Calculate the degree. Next, in step ST653, the quality determination unit 57d compares the degree of coincidence with a threshold value, determines whether it is a non-defective product, and updates the determination output. In step ST654, the display image is constantly updated. Note that the display image update in step ST654 may be performed immediately after imaging in step ST651.

Next, in step ST655, it is determined whether or not the up key 44a (UP) or the down key 44b (DOWN) is pressed. If it is detected that the up / down key 44 is pressed, the process proceeds to step ST656. If the up key 44a is pressed, the setting is changed to increase the threshold. If the down key 44b is pressed, the setting is changed to decrease the threshold. I do. Then, returning to step ST651, imaging is performed with the changed image magnification, and a live image LVI is acquired. If pressing of the up / down key 44 is not detected, it is determined in step ST657 whether or not the SET key 42 has been pressed. If pressing of the SET key 42 has not been detected, the process returns to step ST651, and a series of steps from step ST651 to step ST657 is repeatedly executed with the threshold value unchanged. If the pressing of the SET key 42 is detected in step ST657, the operation is stopped and the setting mode is executed in step ST658. In other words, when the threshold value is changed, the operation is performed with the changed threshold value until the SET key 42 is pressed.
(Operation procedure when changing bank settings during operation)

  Here, the operation procedure at the time of changing the bank setting during operation will be described based on the flowchart of FIG. 61 and FIG.

First, in step ST700, the processing is started, and in step ST701, the operation state is set with the first bank setting. At this time, in the example in the upper left diagram of FIG. 23, the number 1 and the live image LVI of the bank 1 are displayed, and the threshold value of the bank 1 is set. In step ST702, whether or not the MODE key 46 and the up / down key 44 are simultaneously pressed is determined. If simultaneous pressing of the MODE key 46 and the up / down key 44 is detected, the process proceeds to step ST703 and the operation is stopped. While the driving operation is stopped, for example, the determination result indicator lamp 41 may blink green. In step ST704, the registered image of the selected second bank is read out, the registered image of the second bank, the bank number display, and the fact that it is being changed are displayed. In the example in the lower left diagram of FIG. 23, the number 2 and the live image LVI of the bank 2 are displayed, and the threshold value of the bank 2 is set. Proceeding to step ST705, the operation setting is changed based on the setting of the second bank, and the process proceeds to step ST706. In step ST706, the operation is started with the setting of the second bank. In step ST702, when simultaneous pressing of the MODE key 46 and the up / down key 44 is not detected, the operation state in the first bank setting is maintained.
(Correspondence statistics calculation procedure)

  Subsequently, the calculation procedure of the maximum coincidence and the minimum coincidence among the coincidence statistics during driving will be described based on the flowchart of FIG.

  First, processing is started in step ST800, and the latest input image is acquired from the imaging unit 52 in step ST801. In step ST802, the coincidence calculation unit 57c calculates the coincidence. Next, in step ST803, the pass / fail determination unit 57d compares the latest coincidence with the threshold setting value and makes a determination based on the comparison study, and proceeds to step ST804, where the coincidence degree statistical value calculation unit 57e Compare the maximum match. In step ST805, the coincidence statistical value calculation unit 57e determines whether the latest coincidence exceeds the past maximum coincidence. If it is determined that the value is higher, the process proceeds to step ST806, where the coincidence degree statistical value access unit 58d overwrites and stores the latest coincidence degree as the past maximum coincidence degree in the coincidence degree statistical value storage unit 54e. If it is determined that the number does not exceed, the process proceeds to step ST807, and the past maximum matching degree is held as it is.

  Regardless of whether step ST806 or step ST807 is passed, the process proceeds to step ST808, and the coincidence degree statistical value calculation unit 57e compares the latest coincidence with the past minimum coincidence. In step ST809, the matching degree statistical value calculation unit 57e determines whether the latest matching degree is lower than the past minimum matching degree. If it is determined that it is lower, the process proceeds to step ST810, and the coincidence degree statistical value access unit 58d overwrites and stores the latest coincidence degree as the past minimum coincidence degree in the coincidence degree statistical value storage unit 54e. If it is determined that it is not lower, the process proceeds to step ST811, and the past minimum matching degree is held as it is.

Regardless of whether step ST810 or step ST811 is passed, the process proceeds to step ST812, and it is determined whether or not the coincidence degree statistical value access unit 58d is set to display the maximum / minimum degree of coincidence. If it is set to display the maximum / minimum coincidence, the latest coincidence, threshold setting value, past maximum coincidence, and past minimum coincidence are displayed in step ST813. If it is not set to display the maximum / minimum coincidence, the latest coincidence, the threshold setting value, and the latest input image are displayed in step ST814.
(Operation procedure during operation when the object to be identified is a defective workpiece)

  Here, the operation procedure during operation when the discrimination target is a defective workpiece will be described based on the flowchart of FIG.

First, processing is started in step ST900, and a live image LVI is acquired from the imaging unit 21 in step ST901. In Step ST902, the coincidence degree calculation unit 57c calculates a second coincidence degree that is a coincidence degree between the live image LVI and the defective product image NGI registered as the master image. Next, in step ST903, the quality determination unit 57d compares the second matching degree with the third threshold value, and determines in step ST904 whether the second matching degree exceeds the third threshold value. If it exceeds, it is determined as a defective image NGI, and the output is turned on in step ST905. If not, the output is turned off in step ST906.
(Determination target selection function and operating principle)

  Here, the selection function and operation principle of the discrimination target will be described based on FIG. 64, FIG. 65, and FIG. FIG. 64 is an image diagram showing a state in which a non-defective workpiece and a defective workpiece are flowing on the production line. As shown in FIG. 64, the detection areas of the image processing sensors 1 and 11 have a width. The spot diameters of the image processing sensors 1 and 11 are, for example, about 6 cm × 6 cm in a large size and about 2 mm × 2 mm even in a small size. In view of the fact that the spot diameter of a normal photoelectric sensor is about 1.2 mmφ, it can be said that the spot diameters of the image processing sensors 1 and 11 are large.

  For this reason, in the detection region imaged by the imaging unit 52, for example, as shown in FIG. 65A, the workpiece WK changes in the order of (A) to (F). At this time, in the normal operation state, that is, when the master image is a non-defective image OKI, as shown in FIG. 65B which is an image diagram of the time series change of the first coincidence, the first coincidence is ( It gradually increases from around B), reaches a peak at (C), and gradually decreases at (D). The first degree of coincidence slightly increased in (E) means that the defective product image NGI has an element that matches the feature of the non-defective product image OKI. FIG. 65C shows an image diagram showing the output state in this case. As shown in this figure, the output is turned ON when the first matching degree exceeds the first threshold. That is, the output is turned ON only when a non-defective work WK comes.

  Output when the output logic is changed as shown in FIG. 65C, for example, the output logic is inverted or the output is turned on when the output is lower than the threshold, such as the negative output of the photoelectric sensor. The time series change of is shown in FIG. 65D. As shown in this figure, in any case, (1) there is no work WK in the detection area (the state (A)), or a state in which the work enters the detection area halfway ((B) (D) The state (F)) and the state (2) where the defective workpiece is present (the state (E)) cannot be separated by output.

  Therefore, in order to recognize that the defective workpiece has entered the detection area, the state of “the workpiece WK is in the detection area and is the timing to be determined” ((C) (E) ) Need to be notified to the sensor by another means. That is, if it is “the timing to be determined” and “the determination output is OFF”, it can be recognized that a defective work is coming.

  Here, when the setting for operating the defective product image NGI as a master image is selected, for example, with respect to the flow of the workpiece WK that changes in the order of (A) to (F) in FIG. A time-series change in the degree of coincidence and a time-series change in output shown in FIG. 66C are obtained.

  That is, when the defective product output is set, the second degree of coincidence gradually increases from around (D), reaches a peak at time (E), and gradually decreases at (F). In this case, as shown in FIG. 66C, the output is turned ON when the second matching degree exceeds the third threshold value. In other words, the output is turned ON only when a defective workpiece comes.

When the setting for operating the defective product image NGI as the master image is selected as described above, it is possible to control the discharge of the defective product using this output as a trigger. Here, the image processing sensors 1 and 11 according to the present embodiment can select whether the non-defective image OKI is operated as the master image or the defective image NGI is operated as the master image. Both users who perform discharge control when they come (users who want to know that a defective product has arrived) and users who perform counting when a good product arrives (users who want to know that a good product has come) It becomes possible to cope with the user by one setting change.
(Registered image replacement function during operation)

  Examples of cases where the registered image is re-registered after the operation is started in the image sensor include (1) when changing the type of the work WK on the production line or (2) re-adjusting the setting. (1) Conventionally, there is a method of preparing a plurality of banks, registering images of a plurality of products in each bank, and switching the banks when changing the product as a response when changing the product type. It is necessary to prepare a memory corresponding to the number of banks, which increases the cost. If the memory cannot be prepared, it is necessary to replace the registered image every time the product type is changed.

  (2) Cases that require readjustment include changes over time due to illumination of the image processing sensor and lens contamination, and changes in the background other than the workpiece. There is a case that can be dealt with by adjusting the threshold value, but there is a case where the registered image itself is desired to be replaced with any one of the current non-defective work, defective work, and background. In the conventional image sensor, when the registered image is replaced, it is necessary to go through a dedicated setting mode, which is troublesome.

  In the image processing sensors 1 and 11 according to the present embodiment, when there is a request to replace the registered image during operation, the image processing sensors 1 and 11 can display a desired new image without redoing all the registration operations in the setting mode. It has a registered image replacement function that allows registered images to be replaced.

  FIG. 67 is a screen display during operation, and shows a state in which the screen display is switched in the order of screen A, screen B, screen C, and screen D. The operation of switching the screen display and replacing the registered image is functionally performed by, for example, a replacement target selection unit (not shown). Specifically, the screen is displayed by pressing the MODE key 46 during operation. This is realized by switching the display and pressing the SET key 42 on the screen. In this figure, a screen A shows a normal operation screen, a live image LVI is displayed in the image display area PD, and a matching degree 4313a and a threshold value 4314a are displayed in the explanation display area ED. When the MODE key 46 is pressed once on this screen, the screen B is switched to display. In this screen B, a matching degree 4313b and a threshold value 4314b are displayed in a bar format at the left end, a live image LVI is displayed in the image display area PD, and a non-defective image OKI is displayed in the explanation display area ED. When the SET key 42 is pressed on this screen, the live image LVI can be replaced with a non-defective image OKI. Similarly, when the SET key 42 is pressed on the screen C displayed by pressing the MODE key 46, the live image LVI can be replaced with the background image BGI, and the screen D displayed by pressing the MODE key 46 is displayed. When the SET key 42 is pressed, the live image LVI can be replaced with a defective product image NGI. The example in FIG. 67 assumes three-point teaching. In the case of two-point teaching, for example, the screen D is not displayed.

In the process of calculating the degree of coincidence, the difference image between the non-defective image OKI and the background image BGI is used in the case of two-point teaching, and the difference image between the defective product image NGI and the background image BGI is used in the case of three-point teaching. Each difference registration image is also updated. The image processing algorithm and threshold are automatically updated based on the updated registered image.
(Modification: Add registered image)

Up to this point, the description has been made on the assumption that the registered images are replaced. However, it is possible to improve the discrimination capability between the non-defective workpiece WK and the defective workpiece WK by registering a plurality of non-defective images OKI and defective images NGI. In this modification, the non-defective product image OKI, the defective product image NGI, etc. registered by the operation of the replacement target selection unit are not replaced, but are additionally registered when the SET key 42 is pressed in the example of FIG. Thus, for example, a registered image having the highest discrimination capability between the non-defective workpiece WK and the defective workpiece WK is employed. Further, the user may be able to select from the additionally registered registration candidate image group.
(Operation procedure for replacing registered images)

  Here, the operation procedure for replacing registered images will be described with reference to the flowcharts of FIGS. 68, 69, and 70 and FIG. FIG. 68 is a flowchart showing a normal operation process in which registered images are not replaced, and FIGS. 69 and 70 are flowcharts showing operation procedures for replacing registered images in two-point teaching and three-point teaching, respectively.

  First, the flow of normal operation processing will be described based on the flowchart of FIG. Processing is started in step ST1000, and a live image LVI is acquired from the imaging unit 21 in step ST1001. In step ST1002, the coincidence calculation unit 57c performs image processing on the live image LVI and updates the coincidence. Next, in step ST1003, the pass / fail determination unit 57d compares the degree of coincidence with a threshold value, outputs the determination result, and updates it. In ST1004, display unit 53 updates the display of live image LVI.

  Subsequently, an operation procedure for replacing a registered image in the two-point teaching will be described based on a flowchart of FIG. First, processing is started in step ST1100, and in step ST1101, the screen display is set to screen A in FIG. In step ST1102, normal operation processing is performed. This procedure is the same as the procedure of steps ST1000 to ST1004 in the flowchart of FIG. In step ST1103, it is determined whether or not the MODE key 46 is pressed. If the pressing of the MODE key 46 is detected, the process proceeds to step ST1104, and the screen display is switched between screen A to screen C. If the MODE key 46 is pressed, the screen is switched, and if the pressing of the MODE key 46 is not detected, the screen is displayed as it is, and the process proceeds to step ST1105, where the SET key 42 is pressed. Determine presence or absence. If pressing of the SET key 42 is not detected, the process returns to step ST1102, and the operation process is repeated. If pressing of the SET key 42 is detected, the process proceeds to step ST1106, and it is determined whether the current screen display is the screen A to the screen C. In the case of screen A, in step ST1107, the operation is stopped and the mode is changed to the teaching mode. If it is the screen B, the process proceeds to step ST1108, and the non-defective image OKI is replaced. If it is the screen C, the process proceeds to step ST1109, and the background image BGI is replaced. After step ST1108 or step ST1109 is executed, in step ST1110, (1) a plurality of brightness conditions, (2) resolution, and (3) a re-teaching process considering the algorithm load is performed. After the re-teaching process, the process returns to step ST1102, and the operation process is performed based on the setting where the re-teaching process is executed.

Finally, an operation procedure for replacing registered images in three-point teaching will be described based on the flowchart of FIG. The operation procedure for replacement of registered images in three-point teaching is substantially the same as that in the case of two-point teaching, but in step ST1203 to step ST1206, a procedure for selecting screen D for replacement registration of defective product images NGI. And the point that the defective product image NGI is replaced when the screen D is selected. After replacement registration, as in the case of two-point teaching, in step ST1211, re-teaching processing is performed in consideration of (1) a plurality of brightness conditions, (2) resolution, and (3) algorithm load. After the re-teaching process, the process returns to step ST1202, and the operation process is performed based on the setting where the re-teaching process is executed.
(Operation mode screen)

In the operation mode screen displayed on the display screen 43 in the operation mode, an image display area PD and an explanation display area ED are provided. In the example of FIG. 59, the image display area PD is arranged on the left side of the display screen 43, and the explanation display area ED is arranged on the right side.
(Common position display function)

  Here, the display content of the display screen 43 preferably has a common layout of the image display area PD and the explanation display area ED in the setting mode and the operation mode. In particular, the user can confirm the image without being confused by setting the region in which the image is displayed to a common position in the setting mode and the operation mode. More specifically, by fixing the area where the live image LVI is displayed at a certain position, the user can easily grasp which image is the target. In the example of FIG. 59, the image display area PD is fixed to the left side of the display unit 53 in both the setting mode and the operation mode. As described above, since the relative positional relationship is shared between the setting time and the driving time, it is possible to give the user a sense of security in operation. In the second registration screen, the registered first image and the live image LVI that is a candidate for the second image are displayed on one screen, but by fixing the live image LVI to the left side, the user can It can be recognized that the live image LVI to be registered is on the left side of the common position, and there is little confusion about which image is the image to be registered.

  In addition, the degree of coincidence and the threshold value are displayed on the operation mode screen. As a result, the user can confirm on one screen the degree of coincidence between the input image of the workpiece WK that is sequentially imaged and the non-defective image OKI calculated from this image, and the threshold set in the setting mode.

  The result of the pass / fail judgment is output to the outside. For example, a signal indicating a determination result such as an OK signal or an NG signal is transmitted. Further, the determination result may be displayed outside. For example, the determination result indicator lamp 41 provided on the display surface of the image processing sensor 11 shown in FIG. 6 is turned on according to the determination result.

  In this specification, the pass / fail judgment is used to include not only an operation for determining whether the work WK is a non-defective product but also an operation for determining whether the work WK is a non-defective product. For example, when the defective product is detected, the pass / fail judgment unit outputs, and when the defective product is not detected, the output is not performed. In addition to the output when the defective product is detected, the output is performed when the defective product is not detected. It also includes embodiments that are not

  The display screen 43 may be turned off in the operation mode.

  Subsequently, screen transition and common operation in the operation mode will be described. Examples of operation mode screen transitions are shown in FIGS. Screen A shown in FIG. 71A is a screen display during operation after teaching is completed. This screen A has a display similar to that of a conventional photoelectric sensor, and the large display in the upper right indicates the degree of coincidence of the live image LVI currently captured. A small display in the lower right of FIG. 71A indicates the threshold value. By pressing the MODE key 46 once, the screen is switched to the screen B shown in FIG. 71B. In this screen B, the live image LVI is displayed in the image display area PD. In the explanation display area ED, the matching degree of the live image LVI and the threshold value are displayed. On this screen B, when the BACK key 45 is pressed once, the screen A is switched to the screen A shown in FIG. 71A.

  Similarly, when the MODE key 46 is pressed once on the screen B, the screen changes to the screen C shown in FIG. 71C. By repeating this operation, the screen D shown in FIG. 71D and the screen E shown in FIG. The screen is switched to a screen F shown in FIG. 71F and a screen G shown in FIG. 71G. When the MODE key 46 is pressed once on the screen G, the screen is switched to the first screen A. On the other hand, when the BACK key 45 is pressed once on a predetermined screen, the screen is switched in the reverse order to that of the MODE key 46. In addition, by pressing and holding the BACK key 45 on a predetermined screen, the screen is switched to the first screen A.

  Banks displayed at the left end of screen A and screen B may require setup change in which a plurality of workpieces WK flow through one production line, so teaching does not have to be performed again at each setup change. For example, four settings such as “BNK1” to “BNK4” can be stored, and it is displayed which of the settings is “BNK1” to “BNK4”. Further, “OUT” displayed at the left end of the screen A and the screen B indicates an output channel number. If the value of “OUT” is “2”, it means that the signal is output from the output terminal 2, for example.

  In the screen C shown in FIG. 71C, the live image LVI is displayed in the image display area PD. A non-defective image OKI is displayed in the explanation display area ED. On the screen D shown in FIG. 71D, the live image LVI is displayed in the image display area PD, and the defective product image NGI is displayed in the explanation display area ED. Furthermore, on the screen E shown in FIG. 71E, the live image LVI is displayed in the image display area PD, and the background image BGI is displayed in the explanation display area ED. Thereby, the user can confirm the registered good product image OKI, the defective product image NGI, and the background image BGI while driving and comparing with the live image LVI.

  In the screen F shown in FIG. 71F and the screen G shown in FIG. 71G, the live image LVI is displayed in the image display area PD, and the statistical value of the matching degree is displayed in the explanation display area ED. On the screen F, the maximum value and the minimum value of the degree of coincidence after the start of operation are displayed. On the screen G, the maximum value and the minimum value of the degree of coincidence exceeding the threshold value are displayed. Further, at the left end of the screens C to G, the degree of coincidence and the statistical value of the degree of coincidence are displayed as images so as to be sensed. Scales are arranged above and below, and a mark indicating a threshold and a mark (center in the figure) indicating the current degree of coincidence are displayed. On the screen F, a mark indicating the maximum / minimum matching degree is displayed. On the screen G, a mark indicating the maximum / minimum matching degree exceeding the threshold is displayed.

By displaying the statistical values in this way, the user knows the degree of coincidence variation from the maximum / minimum coincidence degree after starting driving, and the coincidence degree and threshold value from the maximum / minimum coincidence degree exceeding the threshold value. Therefore, it is possible to know whether the threshold has been exceeded or whether it has exceeded the threshold with sufficient margin, to determine whether the threshold needs to be adjusted, and to be used as a reference when manually adjusting the threshold Can do.
(Short press of up / down key 44)

When the up / down key 44 is pressed for a short time on the screen C to the screen F, as shown in FIG. 72A, the coincidence degree and threshold value displayed on the screen B are displayed in the explanation display area ED, and the user can manually change the threshold value. . When the up / down key 44 is pressed and left for 5 seconds, the screen before the up / down key 44 is pressed is restored. Note that the time for leaving the screen to return to the screen before pressing the up / down key 44 is not limited to 5 seconds.
(Short press of the SET key 42)

As described above, whether to perform two-point teaching or three-point teaching can be determined by pressing the SET key 42 for a short time or a long time. When the SET key 42 is pressed for a short time, as shown in FIG. 72B, a progress bar for starting the two-point teaching setting mode is displayed on the entire display screen 43, and the two-point teaching setting mode is displayed. Switch.
(Press and hold the SET key 42)

When the SET key 42 is pressed for a long time, as shown in FIG. 72C, a progress bar for starting the three-point teaching setting mode is displayed using the entire display screen 43, and the three-point teaching setting mode is entered. Switch.
(Press and hold MODE key 46)

When the MODE key 46 is pressed for a long time, the setting screen is displayed as shown in FIG. 72D.
(Short press of MODE key 46 and UP / DOWN key 44 at the same time)

Further, when the MODE key 46 and the down key 44b of the up / down key 44 are simultaneously pressed, the bank and the output channel described above can be changed to “next”. Further, when the MODE key 46 and the up key 44a of the up / down key 44 are pressed for a short time, the bank and the output channel described above can be changed to "previous". For example, when there are four banks and there are two output channels, switching is performed in eight stages. In addition, after the output channel is switched in two stages, the bank can be switched in four stages.
(Press and hold the MODE key 46 and the BACK key 45 simultaneously)

Furthermore, when the MODE key 46 and the BACK key 45 are simultaneously pressed for a long time, it is possible to switch between key lock and key lock release.
(Press the SET key 42 five times while pressing the MODE key 46)

  Furthermore, if the SET key 42 is pressed five times while pressing the MODE key 46, the image processing sensors 1 and 11 can be initialized.

  On the other hand, during the operation mode, the registration setting conditions can be changed according to the result of the quality determination. For example, the set threshold value is finely adjusted to reduce erroneous determination. In this case, the member for adjusting the threshold value can also be used in the increase / decrease adjustment unit 51h used for adjusting the display magnification of the image. Thereby, the adjustment of the display magnification of the image and the adjustment of the threshold value are performed with a common member provided on the display surface 4a, thereby simplifying the configuration and unifying the operating environment. Such a procedure will be described based on the flowcharts of FIGS. 73A and 73B. In these drawings, FIG. 73A is a flowchart showing the operation of the setting mode including the step of adjusting the display magnification of the image, and FIG. 73B is a flowchart including the step of adjusting the threshold value in the operation mode following FIG. 73A. . First, in step ST1300, the setting mode is selected. Next, in step ST1301, an image that is a candidate for registration is captured, and in step ST1302, the image displayed on the display screen 43 is updated.

  Here, as an operation on the user side, the captured candidate image is confirmed on the display screen 43, and it is determined whether or not it is appropriate as a registered image. If the posture or field of view needs to be adjusted, appropriate processing is performed accordingly. For example, when it is determined that the display magnification of the image needs to be adjusted, the display magnification is adjusted by operating the increase / decrease adjustment unit 51h.

  As a result, as an operation on the image processing sensor side, in step ST1304, it is determined whether or not the up / down key 44 as the increase / decrease adjustment unit 51h has been operated. If there is an operation, the process proceeds to step ST1305, and the display magnification of the image is set. Change the settings to change according to the operation. Here, when the up key 44a, which is an up-side switch, is operated, the image magnification is increased, and conversely, when the down key 44b, which is a down-side switch, is operated, the image magnification is decreased. Change the settings so that Then, the process returns to step ST1301, and the image is re-captured at the changed magnification so that the image with the changed magnification is displayed on the display screen 43. Note that it is not always necessary to recapture the image. For example, when the magnification is enlarged, the captured image may be displayed by digital zooming. On the other hand, when the image is reduced, the displayed field of view is widened, so it is necessary to take an image again. However, when images captured in the past are stored, an image with a corresponding magnification may be called.

  In this way, when an image with a desired display magnification is obtained and no further magnification adjustment is necessary, the operation of the up / down key 44 is eliminated in step ST1303, so that the process proceeds to step ST1305 and whether the SET key 42 is pressed or not. Determine. If the SET key 42 has not been pressed, the process returns to step ST1304 to repeat the process. If the press has been detected, the process proceeds to step ST1306, where the display image is registered as a registered image, and image registration processing is performed in step ST1307. . Subsequently, as shown in FIG. 73B, the process proceeds to step ST1308 to switch to the operation mode. In step ST1309, an image of a workpiece that is an object of image processing, that is, quality determination is taken. Next, in step ST1310, predetermined image processing is performed, and the degree of coincidence is calculated. Then, the degree of coincidence calculated in step ST1311 is compared with a threshold value, the determination result is output, the calculated degree of coincidence is displayed, and the display content of the live image LVI displayed on the display screen 43 is also updated. (Step ST1312). In step ST1313, it is determined whether or not the up / down key 44 serving as the increase / decrease adjustment unit 51h has been operated.

  Here, as the operation on the user side, the obtained determination result, the input live image LVI displayed on the display screen 43, and the degree of coincidence calculated for the input live image LVI are confirmed, and the determination result Is appropriate and whether the threshold is set appropriately. If it is determined that the threshold value needs to be changed, the increase / decrease adjustment unit 51h is operated to finely adjust the threshold value.

As a result, when the operation of the up / down key 44 is detected as an operation on the image processing sensor side, the process proceeds to step ST1314 to change the threshold value. Again, the threshold value is increased when the up key 44a, which is an up-side switch, is operated, and conversely, the threshold value is decreased when the down key 44b, which is a down-side switch, is operated. Then, the process returns to step ST1309, and determination is performed with the changed threshold value. If it is determined that an appropriate threshold value has been set by repeating these operations as necessary, the operation of the up / down key 44 is not detected in step ST1313, and the process proceeds to step ST1315 to determine whether or not there is an operation to stop the operation. judge. Here, the presence / absence of operation of the SET key 42 is detected. If not detected, the process returns to step ST1309 to repeat the above processing. On the other hand, when operation of the SET key 42 is detected, it progresses to step ST1316 and stops an operation mode. In this way, it is possible to finely adjust an appropriate display magnification and threshold value to improve the accuracy of image registration and pass / fail judgment. Further, a common increase / decrease adjustment unit 51h can be used for these adjustments. In particular, an adjustment function of the image display magnification is automatically assigned to the increase / decrease adjustment unit 51h in the setting mode, while the increase / decrease adjustment unit 51h in the operation mode is changed to a threshold adjustment function, and the user can There is an advantage that necessary settings can be made only by focusing on the operation of the increase / decrease adjustment unit 51h without performing an operation for switching the functions and without being conscious of the switching.
(Low resolution setting)

  In the teaching in the setting modes such as two-point teaching, three-point teaching, and one-point teaching described above, the resolution of the image data can be reduced in order to speed up the arithmetic processing. Further, not only in the setting mode but also in the operation mode, it is possible to reduce the resolution of the image data and increase the processing speed. By reducing the resolution of an image, it is possible to reduce the data size and reduce the load and speed of processing such as image processing. Depending on the image, noise may be reduced by processing such as image compression or smoothing. When such processing is performed, the problem is how to set the degree of image resolution reduction.

  Conventionally, a response time may be set in a photoelectric sensor, whereas an action of setting such a response time in an image processing sensor has not been assumed. Even in the case of an image processing sensor that defines a response time, the response time is determined as a result of other set conditions, such as the response time changing based on the field of view set by the user. It was different from the one that arbitrarily set the response time. On the other hand, in the production line of a factory, the field of view and the response time are set directly, although there are many restrictions on the response time that can be spent on the existence of the work WK and the pass / fail judgment from the viewpoint of the conveyance speed of the line, etc. I couldn't. This is because, for example, the resolution of the captured optical image changes directly depending on the setting of the user's visual field, and jitter (shake) occurs in the processing time, so the image processing sensor defines the response time. Due to the difficulty. On the other hand, the image processing sensor according to the present embodiment is configured so that a response time can be set for a fixed visual field region, and an image resolution to be processed internally is determined based on the set response time. Yes. Hereinafter, this will be described in detail with reference to FIGS. 74 and 75.

  Conventionally, the setting of the image processing sensor has required the user to set the light amount, adjust the field of view, set the image processing to be detected (detection setting), and the like. The block diagram of FIG. 74 shows the state of the operation processed inside the image processing sensor in response to such user settings for light quantity setting, visual field adjustment, and detection setting. As shown in this figure, as a result of the user setting the amount of light, the exposure time of the imaging unit 21 is determined. As a result of the adjustment of the visual field, the resolution of the optical image to be inspected is determined. Further, as a result of setting the detection conditions, an algorithm used for the set image processing is determined. As a result, the time required for imaging including the time required for reading the optical image, that is, the imaging time is determined from the exposure time and resolution of the imaging unit 21. On the other hand, the time required for image processing, that is, the image processing time is determined from the resolution of the image and the image processing algorithm. In accordance with the order as described above, a response time that is a processing time for setting is determined.

  On the other hand, there is a case where an allowable response time may be determined in advance due to a relationship such as a conveyance speed of the production line, and in this case, there is a problem that it is impossible to set depending on setting contents. . For example, when the resolution is naturally determined by the user's visual field setting, jitter changes in the processing time when the resolution changes, and it becomes difficult to define the response time.

On the other hand, in the image processing sensor according to the present embodiment, the response time can be set in addition to the field of view and the detection setting. In order to realize this, registration setting conditions such as an appropriate image resolution and image processing algorithm are determined by internal processing of the image processing sensor. As a result, the data size of the processed image is suppressed regardless of the field of view setting, and the response time can be determined. This will be described with reference to the block diagram of FIG. As shown in this figure, as the items that can be specified by the user, in addition to the light amount setting, visual field adjustment, and detection purpose similar to those in FIG. 74, the response time can also be set. In response to such user designation, the condition allocating unit 55 performs optimal allocation, determines the exposure time so that the processing is completed within the designated response time, determines the resolution, and selects an appropriate image. Select a processing algorithm.
(Lower image resolution)

Here, a method for reducing the resolution of an image will be described. For example, as shown in FIG. 77, a method of compressing image data as shown in FIG. 77 can be used as a method for changing the resolution to be lower than the prescribed visual field range. In the example of FIG. 77, the vertical and horizontal directions are compressed to ½ using pixel values averaged by 2 × 2 pixels. Alternatively, as shown in FIG. 78, a method of thinning out image data can also be used. In the example of FIG. 78, every other image value is employed in the vertical direction and the horizontal direction, respectively, so that the vertical and horizontal directions are compressed to ½. In the present invention, the technique for reducing the resolution of an image is not limited to these, and a known technique for reducing the resolution can be appropriately employed. In order to achieve low resolution, there are a method using hardware such as a dedicated GPU and a method using software. Any method can be used in the present invention, or a combination thereof can be used. May be. In this specification, for the sake of convenience, the reduction in image resolution may be referred to as compression comprehensively regardless of the method such as compression or thinning.
(Two-point teaching of non-defective image OKI and background image BGI including resolution reduction processing)

Here, based on the set response time, the condition allocating unit 55 can complete the process from image capturing to pass / fail determination within this response time, such as the image capturing conditions, the degree of compression, and the image processing algorithm. A procedure for setting registration setting conditions will be described. Here, a case will be described in which the image compression level setting unit 55e of the condition allocating unit 55 adjusts the compression rate for reducing the resolution of an optical image within the registration setting conditions. First, in the two-point teaching of the non-defective image OKI and the background image BGI described as described above, the setting in the two-point teaching when the resolution reduction processing is included and the processing procedure in the subsequent operation mode are shown in the flowchart of FIG. Based on
(Response time setting)

  First, in step ST1401, a response time is set. Specifically, the user sets a desired response time from the response time setting unit 51e. Here, it is preferable that the response time setting unit 51e presents a plurality of different response time candidates to the user in advance and prompts the user to select. By presenting response time candidates that can be set in advance as response time candidate groups, combinations of detection conditions such as exposure time, resolution (compression rate), and image processing algorithm that can be set for each response time can be prepared. Further, processing such as calculation in the condition allocating unit 55 can be reduced. In other words, according to the selected response time, detection conditions such as exposure time that cannot be set within the registration setting conditions can be quickly eliminated. However, it can also be configured such that the user directly inputs a desired response time as a numerical value or the like. In this case, based on the input response time, the condition assignment unit 55 calculates a combination of detection conditions such as selectable exposure time, resolution, and image processing algorithm.

  Next, in step ST1402, a non-defective image OKI and a background image BGI are acquired and stored in the still image storage unit 54a.

  Next, in step ST1403, the non-defective image OKI and the background image BGI are reduced in resolution based on the response time setting set in step ST1401. The resolution reduction is performed by, for example, the image compression unit 56d. Here, the compression degree of each image is common.

  Next, in step ST1404, a non-defective background compressed difference image is generated from the compressed non-defective image COKI and the compressed background image CBGI. The generation of the non-defective background compressed difference image is performed by, for example, the difference image generation unit 56a.

  In step ST1405, an evaluation area is set. As the evaluation area, for example, the entire image, the vicinity of the center, or the area where the difference image exists may be automatically set on the image processing sensor side, or the evaluation area may be manually specified by the user. Good. When the user manually performs, for example, an evaluation area setting unit is provided in the operation unit 51 of FIG.

  Next, in step ST1406, the feature quantity of the optimal non-defective image OKI is extracted. The feature amount extraction is performed by, for example, the feature amount extraction unit 56b.

Further, in step ST1407, a threshold value is determined. For example, the threshold value calculation unit 56c determines the threshold value by evaluating the degree of coincidence with the background image BGI based on the extracted feature amount of the non-defective image OKI.
(Operation mode)

When the setting operation in the setting mode is completed as described above, the operation mode is switched to. Subsequently, the operation procedure in the operation mode will be described with reference to FIG. 79. In step ST1408, the input live image LVI of the workpiece WK to be evaluated is acquired by the image acquisition unit 52. Next, in step ST1409, the resolution of the input live image LVI to be evaluated is reduced. Here, the compression degree of the input live image LVI is made equal to the compression degree of the image in the setting mode. Further, in step ST1410, the degree of coincidence of the work WK is calculated based on the feature amount of the non-defective image OKI registered in the setting mode, and the quality is determined by comparing with the threshold value. In this manner, the resolution can be reduced according to the set response time, and the operation mode can be set so that processing can be performed within the specified response time.
(Modification of two-point teaching of non-defective image OKI and background image BGI including resolution reduction processing)

  In the above example, the method of setting the threshold in the order in which the difference image is generated after reducing the resolution first at the time of setting has been described. However, the present invention does not limit the order in which the thresholds are set to the above. For example, the differential image may be generated first and the image may be compressed. Hereinafter, such an example will be described as a modification based on the flowchart of FIG. First, in step ST1501, a response time is set, and in step ST1502, a non-defective image OKI and a background image BGI are acquired and stored in the still image storage unit 54a. These procedures are the same as steps ST1401 to ST1402 in FIG. 79 described above.

  Next, in step ST1503, the difference image generation unit 56a generates a non-defective product background differential image from the non-defective image OKI and the background image BGI. In step ST1504, the resolution of the non-defective background difference image is reduced according to the response time setting. The compression degree of each image when the resolution is reduced by the image compression unit 56d is common. As a result, a non-defective background differential compressed image that is a resolution-reduced image of the non-defective background differential image is obtained by the image compression unit 56d.

Thereafter, as in steps ST1405 to ST1410 of FIG. 79 described above, an evaluation area is set in step ST1505, an appropriate feature amount of the non-defective image OKI is extracted in step ST1506, and a threshold value is set in step ST1507. Further, after the setting mode ends, the mode is switched to the operation mode, the input live image LVI to be evaluated is acquired in step ST1508, and the resolution of the input live image LVI is reduced in step ST1509. The compression degree of the input live image LVI is made equal to the compression degree of the image in the setting mode. And quality determination is performed in step ST1510. Even in this method, the resolution of the difference image can be reduced, and the processing time can be adjusted according to the set response time.
(Three-point teaching procedure for non-defective product image OKI, defective product image NGI and background image BGI including resolution reduction processing)

  The example in which the resolution reduction process is added in the two-point teaching has been described above. Here, an example in which the non-defective product image OKI and the background image BGI are registered has been described. However, in the two-point teaching in which the non-defective product image OKI and the defective product image NGI are registered, a resolution reduction process can be added similarly. Further, a resolution reduction process may be added also in the three-point teaching. Hereinafter, an example in which the resolution reduction processing is added in the three-point teaching for registering the non-defective product image OKI, the defective product image NGI, and the background image BGI will be described based on the flowchart of FIG. First, in step ST1601, a response time is set. Next, in step ST1602, a good product image OKI, a defective product image NGI, and a background image BGI are acquired. Here, each image is picked up by the image pickup unit 21, the non-defective product image OKI, the defective product image NGI, and the background image BGI are acquired and stored in the still image storage unit 54a. In step ST1603, the non-defective product image OKI, the defective product image NGI, and the background image BGI are reduced in resolution according to the response time setting. The compression degrees of the compressed good product image CGDI, the compressed defective product image CNGI, and the compressed background image CBGI compressed by the image compression unit 56d are the same.

  Next, in step ST1604, a non-defective product background difference image, which is a difference image between the non-defective image OKI and the background image BGI, and a defective product background difference image, which is a difference image between the defective product image NGI and the background image BGI, are generated.

  In step ST1605, an evaluation area is set for each of the difference images obtained in this way. Further, in step ST1606, feature amounts are extracted from the evaluation areas of the difference images. Specifically, the feature amount extraction unit 56b extracts the feature amount of the non-defective product image OKI from the non-defective product background difference image, and the feature amount of the defective product image NGI from the defective product background difference image. In step ST1607, a threshold value is set. Here, the threshold value calculation unit 56c sets the threshold value by evaluating the degree of coincidence of the defective product image NGI based on the feature amount of the non-defective product image OKI.

  When the setting is completed in this way, the setting mode is shifted to the operation mode. In the operation mode, in step ST1608, an input live image LVI to be evaluated is acquired, and in step ST1609, the acquired input live image LVI is reduced in resolution. Here, the compression degree of the input live image LVI is made equal to the compression degree of the image in the setting mode. In step ST1610, quality determination is performed. Here, the degree of coincidence of the input live image LVI is calculated based on the feature amount of the non-defective image OKI, and this is compared with a threshold value, whereby the quality determination unit 57d determines the quality and outputs the determination result.

In this way, by adding the low resolution processing even in the three-point teaching, the image processing can be completed within the set response time, and an image processing sensor corresponding to inline processing can be realized.
(Modification of three-point teaching of non-defective image OKI, defective product image NGI and background image BGI including resolution reduction processing)

  The example in which the resolution reduction process is added in the three-point teaching has been described above. In this example, the case where thresholds are set in the order in which difference images are generated after performing resolution reduction first at the time of setting has been described, but the present invention is the order in which thresholds are set as described in the two-point teaching. Are not limited to this order. Similarly, in the three-point teaching, the image may be compressed after the difference image is generated first. Such an example will be described below with reference to the flowchart of FIG. First, in step ST1701, a response time is set, and then in step ST1702, a good product image OKI, a defective product image NGI, and a background image BGI are acquired and stored in the still image storage unit 54a. These procedures are the same as steps ST1601 to ST1602 in FIG. 81 described above.

  Next, in step ST1703, a non-defective product background differential image is generated from the non-defective product image OKI and the background image BGI, and a defective product background differential image is generated from the defective product image NGI and the background image BGI. In step ST1704, the non-defective product background differential image and the defective product background differential image are reduced in resolution according to the response time setting. The compression degree of each image when the resolution is reduced by the image compression unit 56d is common. As a result, a non-defective background differential compressed image and a non-defective background differential compressed image, which are reduced-resolution images of the non-defective background differential image and the defective background differential image, are obtained, respectively.

Thereafter, similarly to steps ST1605 to ST1610 in FIG. 81 described above, an evaluation area is set in step ST1705, and in step ST1706, appropriate feature values of OK image OK and feature values of defective image NGI are extracted, respectively. In ST1707, a threshold is set based on these. Further, after the setting mode ends, the mode is switched to the operation mode, the input live image LVI to be evaluated is acquired in step ST1708, and the resolution of the input live image LVI is reduced in step ST1709. The compression degree of the input live image LVI is made equal to the compression degree of the image in the setting mode. And quality determination is performed in step ST1710. Even with the above method, the resolution of the differential image can be reduced and the processing time can be adjusted according to the set response time.
(Procedure for one-point teaching of background image BGI including resolution reduction processing)

  Further, a resolution reduction process can be added even in one-point teaching. Such an example will be described with reference to the flowchart of FIG. First, in step ST1801, a response time is set. Next, in step ST1802, a background image BGI is acquired. Specifically, the background image BGI is captured by the imaging unit 21 and stored in the still image storage unit 54a. Next, in step ST1803, the resolution of the background image BGI is reduced according to the response time setting, whereby a compressed background image CBGI is obtained. Next, in step ST1804, an evaluation area is set. Here, all the areas of the compressed background image CBGI are set as the evaluation areas. In step ST1805, the feature amount of the compressed background image CBGI is extracted. Further, in step ST1806, a threshold value is calculated. For example, the threshold value calculation unit 56c uniformly sets the threshold value to 50%.

When the setting is thus completed, the setting mode is switched to the operation mode. In the operation mode, first, in step ST1807, an input live image LVI to be evaluated is acquired. Next, in step ST1808, the resolution of the input live image LVI is reduced. The compression degree of the input live image LVI is made equal to the compression degree of the image in the setting mode. In step ST1809, quality determination is performed. Here, based on the feature amount of the background image BGI, the coincidence degree of the input live image LVI is calculated by the coincidence degree calculating unit 57c, and this is compared with a threshold value, and the pass / fail determination unit 57d performs the pass / fail determination. In this way, even in one-point teaching, it is possible to add a low resolution process and perform image processing within the set response time.
(Adjusting imaging conditions)

In the above example, an example is described in which the image compression level setting unit 55e of the condition allocating unit 55 adjusts the compression level for reducing the resolution of an image as the registration setting condition so that the processing can be completed within the set response time. did. However, in the present invention, the registration setting condition adjusted by the condition allocating unit 55 is not limited to the compression degree of the image, but other conditions, for example, the imaging condition of the image captured by the imaging unit 21, the condition of the image processing, and the like. You can also. Next, an example in which the condition assignment unit 55 adjusts the imaging condition will be described.
(Imaging condition assignment unit 55a)

The range of the registration setting condition that can be adopted as the registration setting condition is determined by the set response time. Here, it is considered to adjust the image capturing condition with respect to the response time. In this case, the condition allocating unit 55 serves as an imaging condition allocating unit 55a that can adjust the imaging condition of an image captured by the imaging unit 21 so that predetermined image processing for performing pass / fail determination can be performed within the response time. Function.
(Imaging conditions)

  Here, the imaging conditions include, for example, adjusting the exposure time at the time of imaging by the imaging unit 21 and the illumination intensity in order to adjust the brightness of the image. Alternatively, when the imaging unit 21 has a function of generating a high dynamic range image (HDR) by synthesizing a plurality of low gradation images picked up by changing the dynamic range of the luminance region and forming a high gradation image. , HDR function ON / OFF. In addition, automatic brightness adjustment functions, pixel skipping and thinning functions for increasing the frame rate, ON / OFF of neighboring pixel total calculation force functions, etc., imaging of rotation and tilt angles (± 180 °, etc.) Time parameters, parameters for processing the obtained image data, and the like can also be included in the imaging conditions.

Hereinafter, as one form of the imaging condition allocating unit 55a, the brightness condition allocating unit 55b, that is, the brightness condition candidate setting unit 55c and the brightness condition selecting unit 55d adjust the brightness of the image to obtain the optimum brightness. A procedure for determining the condition will be described with reference to FIG. 84A. First, the response time is set by the response time setting unit 51e.
(Determination of brightness conditions)

The brightness condition candidate setting unit 55c and the brightness condition selecting unit 55d determine the brightness condition as the registration setting condition according to the set response time. The example in FIG. 84A shows an example of two-point teaching of a non-defective image OKI and a background image BGI. First, the brightness condition candidate setting unit 55c, based on the response time set by the response time setting unit 51e, outputs a plurality of brightness condition conditions so that the determination result by the pass / fail determination unit 57d is output within the response time. Each is assigned as a brightness condition candidate. That is, the upper and lower limits of the imaging time required for imaging per image that can be set by the imaging unit 21 are determined by the performance and specifications of the apparatus. On the other hand, the upper limit of the imaging time allowed within this response time is determined from the response time set by the response time setting unit 51e. In this way, the allowable imaging time is determined from the physical specifications of the imaging unit 21 and the given response time. Considering that image transfer and processing capability are constant within the imaging time, the exposure time is a parameter that can be set. In addition, since the lower limit of the exposure time that can be set is also determined from specifications and the like, the range that can be taken as the exposure time is determined. Therefore, a plurality of brightness conditions are set as brightness condition candidates by changing an allowable exposure time. Specifically, the brightness condition candidate setting unit 55c extracts brightness condition candidates that can be taken within the allowable exposure time range. For example, the exposure time is set by equally dividing the allowable exposure time range by a predetermined number (for example, five). Alternatively, all exposure times that can be set with a stipulated width (for example, 10 ms) are extracted as brightness condition candidates. In the example of FIG. 84A, the brightness condition candidate setting unit 55c sets n brightness condition candidates from brightness condition candidates 1 to n. Note that the brightness condition candidates are not necessarily set at equal intervals. For example, brightness condition candidates may be set densely in a range where appropriate brightness can be expected.
(Acquisition of candidate images)

Next, a candidate image is acquired for each of a plurality of different brightness condition candidates. Here, the image group acquisition unit 52a controls the imaging unit 21 to capture a plurality of candidate images. A candidate image to be imaged is determined according to the setting mode. For example, in the two-point teaching using the non-defective image OKI and the background image BGI, the non-defective product candidate image and the background candidate image are displayed. In the two-point teaching using the non-defective image OKI and the defective product image NGI, the non-defective product candidate image and the defective product candidate image are displayed. In addition, in the three-point teaching, a non-defective product candidate image, a defective product candidate image, and a background candidate image are captured, and in the single-point teaching, a background candidate image is captured. Here, as described above, the user is guided to arrange the work WK for each image to be captured. For example, the registration guide information is displayed on the display screen 43. When the workpiece WK is set, the image processing sensors 1 and 11 change the brightness condition and capture a candidate image for each brightness condition candidate. Note that the setting of a plurality of different brightness condition candidates and the operation of capturing candidate images for each brightness condition candidate are automatically performed. The user need only set or remove the workpiece WK at the imaging position according to the registration guidance information in the setting mode without being aware of such setting work. In the example of FIG. 84A, in order to perform two-point teaching of the non-defective image OKI and the background image BGI, the user is instructed to place the non-defective workpiece at the imaging position, and the brightness conditions that differ depending on the non-defective workpiece placed according to this instruction A plurality of non-defective product candidate images are captured for each candidate. Then, after the non-defective product candidate image is captured, the user is instructed to remove the non-defective workpiece, and a plurality of background candidate images are captured with the user removing the non-defective workpiece according to this instruction. In addition, in the case of three-point teaching, in addition to this, registration guidance information for instructing to place a defective workpiece at the imaging position, and imaging the defective workpiece placed at the imaging position in accordance with this, for each brightness condition candidate Thus, an operation of capturing a defective product candidate image is added.
(Generation of difference candidate images)

  Next, a difference candidate image is generated from the acquired candidate images. Here, the difference image generation unit 56a generates a difference candidate image from a pair of candidate images captured with the same brightness condition candidate. In the example of FIG. 84A, a good product background difference candidate image is generated from the good product candidate image and the background candidate image. In the case of three-point teaching, in addition to this, an operation of generating a defective product background difference candidate image from the defective product candidate image and the background candidate image is added.

Note that the difference image and the original image before the difference image generation can be compressed. In this case, the image compression degree setting unit 55e adjusts the image compression degree within the given conditions.
(Execution of image processing: optional)

Then, predetermined image processing is performed on each difference candidate image as necessary. This image processing is set in advance as image processing included in the registration setting condition. The image processing may be one type, a series of image processing in which a plurality of image processing elements are combined, or the image processing may be omitted. Image processing is performed by an image processing execution unit.
(Assignment of image processing contents)

Further, when performing image processing, the degree of coincidence calculated from each candidate image after image processing is evaluated by assigning image processing conditions to one or a plurality of image processing elements constituting the image processing. Thus, the optimum image processing can be selected. When assigning image processing conditions, image processing condition candidates are generated by an image processing content assignment unit 55f described later. The image processing condition candidates can be image processing algorithm types, image processing parameters that are referred to by the image processing algorithm, or the like.
(Calculation of matching score)

In this way, the degree of coincidence is calculated by the degree-of-matching calculation unit 57c for each difference candidate image that has been subjected to image processing as necessary. In the example of FIG. 84A, the degree of coincidence of the background candidate image with respect to the pattern model corresponding to the obtained non-defective background difference candidate image is calculated. In the case of three-point teaching, the degree of coincidence of the defective product background difference candidate image with respect to the pattern model corresponding to the non-defective product background difference candidate image is calculated.
(Select brightness condition)

  In this way, with the degree of coincidence obtained for each brightness condition candidate, an appropriate brightness condition is selected by the brightness condition selection unit 55d according to the selection condition. As the selection condition, in the example of FIG. 84A, the brightness condition is evaluated using the matching degree between the non-defective background difference candidate image and the background candidate image as an evaluation value. In the case of three-point teaching, the brightness condition is evaluated using the degree of coincidence between the non-defective background difference candidate image and the defective background difference candidate image as an evaluation value. The brightness condition selection unit 55d selects, for example, a brightness condition candidate having the lowest matching degree from among a plurality of brightness condition candidates as an optimal brightness condition. By selecting the brightness condition with the lowest degree of coincidence, in the operation mode, it is separated from the high degree of coincidence with the non-defective image OKI, and it becomes easy to set the threshold value.

However, the selection condition is not limited to that the degree of coincidence is minimum. In other words, it is not always necessary to select the one with the smallest degree of matching as the optimum brightness condition, and it can also be determined in consideration of the difference with the degree of matching adjacent to it. For example, as shown in Table 2, when the degree of coincidence is calculated for each brightness condition candidate, if the lowest degree of coincidence is the optimum brightness condition, the optimum brightness condition is a brightness with a degree of coincidence of 40%. This is when Condition 7 is satisfied. However, in this case, the difference in the degree of coincidence between adjacent brightness condition candidates is large. This indicates that the evaluation value varies greatly when the brightness of the illumination changes even a little. In other words, it is assumed that the tolerance to fluctuations in ambient brightness is weak. On the other hand, the brightness condition candidate 3 having the second smallest matching degree (matching degree 45%) has a relatively small difference between adjacent brightness condition candidates. From this, it can be evaluated that it is excellent in resistance to fluctuations in brightness, and it is evaluated that it is worth adopting as an appropriate brightness condition. In this way, in addition to the small degree of matching of brightness condition candidates, a relatively small difference from the degree of matching of neighboring brightness condition candidates is also considered as a selection condition for selecting a brightness condition candidate. It is preferable to do.
(Image processing content allocation unit 55f)

  In the above example, the procedure for selecting the optimum brightness condition by changing the brightness condition of the image as the imaging condition has been described. As described above, the condition assigning unit 55 can adjust the image processing conditions in addition to the imaging conditions and the degree of image compression. Here, the image processing conditions include the type of image processing algorithm to be selected, adjustment of image processing parameters of the selected image processing algorithm, and the like. When changing or adjusting the conditions of the image processing algorithm, the condition assigning unit 55 changes the conditions of the image processing algorithm executed in the image processing so that the determination result by the pass / fail determination unit 57d is output within the response time. It functions as the image processing content allocation unit 55f for this purpose. As a result, the processing load of image processing used for pass / fail judgment can be changed to an appropriate load within the response time desired by the user, and inline processing can be performed so that the image processing can be completed within a given time. it can.

Next, a procedure in which the condition assignment unit 55 adjusts the image processing condition as the registration setting condition according to the response time set by the response time setting unit 51e will be described. Here, in the setting mode, in addition to a configuration in which only one optical image is captured by the imaging unit 21 and image registration is performed, an image is captured as a candidate image for each of a plurality of candidate registration setting conditions with different registration setting conditions. These images can be held, and an image suitable for registration can be selected from the plurality of candidate images to obtain a registered image. Here, the condition allocating unit 55 picks up a plurality of candidate images under a plurality of different candidate registration setting conditions, selects an optimum registration setting condition suitable for pass / fail judgment, and selects candidate images obtained under this condition. Will be described with reference to Tables 3 and 4.

  The time that can be taken to capture the optical image is naturally determined when the response time is set by the response time setting unit 51e. That is, an image is captured within a response time, compressed, differential processing is performed as necessary, and a feature amount is calculated to determine pass / fail, so the time allocated for imaging is within the given response time Limited to a certain time. Therefore, the upper limit of the time that can be taken according to the response time is determined, that is, the upper limit of the exposure time at the time of imaging is also determined. The range of exposure time that can be set is also determined by the specifications of hardware and software such as the imaging device used in the imaging unit 21 and the camera 211. Taking these into consideration, the selectable exposure time is determined in accordance with the range of exposure time that can be set in advance on the imaging unit 21 side and the given response time. In this way, the condition assignment unit 55 determines a combination of exposure times that can be selected according to the response time. For example, when the exposure time is provided in advance in a plurality of combinations, the condition assignment unit 55 extracts a combination of selectable exposure times.

  Further, when the response time setting unit 51e is configured to allow the user to select a response time from a plurality of response time candidate groups prepared in advance instead of an arbitrary numerical value, the response time can be selected for each response time candidate. Since a combination of exposure times is determined, it is possible to prepare a table or the like in advance so that a group of exposure time candidates is automatically extracted according to the selection of response time candidates. With this method, the processing to be performed on the condition allocating unit 55 side can be reduced, and cheaper, lighter load, or faster processing can be realized.

  Table 3 shows examples of combinations of exposure times with respect to response times. Thus, the longer the response time, the greater the number of exposure times that can be selected. As described above, it is not possible to spend all of the response time on the exposure time because other processing such as image compression, difference processing, and determination processing is necessary even after the image is captured.

  In addition to image capturing conditions such as exposure time, in addition to or in addition to this, image processing conditions and image compression (resolution) can be applied as registration setting conditions. As an example, Table 4 shows combinations of image processing algorithms and resolutions with respect to response time.

  In this table, Holistic [A] and Holistic [B] are image processing algorithms for extracting feature amounts from the entire live image. Search [A] and Search [B] are image processing algorithms for searching and specifying a work from a live image and extracting a feature amount from the specified work. Here, in order to extract an edge which is one of feature quantities, Holistic [A] uses a Roberts filter, and Holistic [B] uses a Sobel filter. Search [A] searches based on pixel values (normal correlation search) when searching for the position of a workpiece from a live image, and Search [B] searches based on geometric information such as edges. . Note that even if the type of image processing algorithm and the resolution are the same combination, differences in processing time, identification performance, and operating characteristics are caused by differences in internal processing. The image processing can also include a parameter corresponding to the rotation allowable angle at the time of image search.

In the example of Table 4, an example of adjusting both the image processing algorithm and the resolution with respect to the response time has been described. However, the present invention is not limited to this, and the exposure time, the image processing algorithm, and the resolution are adjusted with respect to the response time. You can also. As an example, Table 5 shows selectable combinations of exposure time, image processing algorithm type, and resolution when a response time is given (for example, 20 ms). In this table, “○” indicates a selectable combination, “×” indicates a combination that cannot be selected due to response time constraints, and shaded “×” indicates a combination that cannot be selected depending on the combination of exposure time, image processing algorithm, and resolution. Respectively.

  As described above, a selectable registration setting condition candidate group is determined according to the response time, and a preferable registration setting condition is selected by the condition allocating unit 55 from these. Here, the preferable registration setting condition is a condition that, as described above, when a quality determination is made in the operation mode, a good product and a defective product can be reliably discriminated. Then, the pass / fail determination unit 57d performs pass / fail determination by using the degree of coincidence with the non-defective product as an evaluation value. Is set by the threshold value calculation unit 56c, it is preferable that the condition is such that the degree of coincidence with a defective product is calculated as low as possible. Therefore, it is important for the condition assignment unit 55 to obtain a registration setting condition that can achieve such a good registration state, for example, a combination of exposure time, resolution, and image processing algorithm.

In the above example, the user can specify the response time from the response time setting unit 51e. However, the present invention is not limited to this configuration, and the response time can be a fixed value. In this case, since the response time is given as a predetermined fixed value, the response time becomes the prescribed response time in FIG. Since the upper limit of the imaging time, that is, the maximum imaging time is uniquely determined based on this default response time, the imaging conditions of the image, the degree of compression of the captured image, the image processing algorithm, etc. are within this maximum imaging time range. The condition setting unit 55 assigns registration setting conditions. Such a procedure will be described with reference to FIG. 84B. As compared with FIG. 84A, the response time setting unit 51e is not present, and the response time is given as a predetermined fixed value. Based on the allowable maximum exposure time, the brightness condition candidate setting unit 55c sets the brightness condition, and the image processing content assignment unit 55f sets the image processing. Alternatively, the image compression level setting unit 55e adjusts the image compression level. The specific processing flow is the same as described above.
(Determination of optimal registration setting conditions)

  Next, a procedure in which the condition allocating unit 55 finds an appropriate registration setting condition from such a group of registration setting conditions and performs image registration will be described with reference to the flowchart of FIG. First, in step ST1901, the response time is acquired. The response time set by the user or the preset response time is acquired from the response time setting unit 51e.

  Next, in step ST1902, candidate registration setting conditions are extracted according to the response time. Candidate registration setting conditions are predetermined parameters that can be changed. For example, when the exposure time, resolution, and image processing algorithm can be adjusted, combinations of exposure time, resolution, and image processing algorithm that can be combined are extracted according to the response time set in step ST1901. In this case, a combination of exposure time, resolution, and image processing algorithm that can be set for the specified response time can be prepared in advance as a candidate registration setting condition table and stored in the setting storage unit 54d. Thereby, by referring to the candidate registration setting condition table, candidate registration setting conditions including combinations of exposure time, resolution, and image processing algorithm that can be set according to the set response time are extracted. In the following steps, an image is captured for each extracted candidate registration setting condition, the degree of coincidence is evaluated, and the optimum registration condition is selected from the obtained degree of coincidence.

  Specifically, first, in step ST1903, it is determined whether there is an unevaluated candidate registration setting condition. In the first loop, imaging and evaluation under the candidate registration setting conditions have not been performed yet, so the process proceeds to step ST1904 and subsequent steps, and an optical image is actually captured for each candidate registration setting condition to calculate the degree of coincidence. Specifically, in step ST1904, based on the unevaluated candidate registration setting condition, the process from the optical image capturing to the image processing is performed, and the degree of coincidence is calculated. This process is the same as each registration process at the time of setting in FIG. 79, FIG. 80, FIG. 81, FIG. That is, any of two-point teaching, three-point teaching, and one-point teaching may be used. Furthermore, in order to save waste of repeating the imaging many times under the same imaging condition (for example, exposure time), the image may be stored as appropriate, and the stored image may be read and processed under the same imaging condition. .

Next, in step ST1905, it is determined whether or not the obtained threshold evaluation value is minimum. Since the evaluation value is not yet stored in the first loop, this is the minimum value, so the process proceeds to step ST1906, where the evaluation value at this time and the candidate registration setting condition obtained are stored, and step ST1903 Return to and repeat the process. Thereafter, similarly, imaging and image processing are performed under new candidate registration conditions, and an evaluation value is acquired. In step ST1905, it is determined whether or not the evaluation value is the minimum value. If not, the process returns to step ST1903 to continue. If the evaluation value is minimum, the process proceeds from step ST1905 to step ST1906. The minimum evaluation value and the candidate registration setting condition at that time are updated, and then the process proceeds to step ST1903. Return and repeat the evaluation. When evaluation of all candidate registration setting conditions is completed in this way, the process proceeds from step ST1903 to step ST1907, and the candidate registration setting condition with the smallest evaluation value is set as the registration setting condition. In this way, the condition allocating unit 55 can determine the optimum registration setting condition that provides the lowest degree of matching of defective products from among candidate registration setting conditions that can be set during the designated response time.
(Change of image processing algorithm)

  Here, an example in which the image processing changing unit, which is one form of the condition allocating unit 55, replaces the image processing algorithm in the image processing will be described based on the flowcharts of FIGS. 86A to 86B. Here, the non-defective product image OKI shown in FIG. 86C, the defective product image NGI shown in FIG. 86D, and the background image BGI shown in FIG. 86E are registered in the setting mode, and the evaluation image shown in FIG. 86F is obtained in the operation mode. Shall. 86A, image processing is performed in the order of registration processing A in the registration mode and preprocessing B and evaluation processing C in the operation mode. For such a series of image processing, an example will be described in which the image processing changing unit changes a part of the image processing and changes the preprocessing B to the preprocessing D as shown in FIGS. 86A to 86B.

  Here, in the above-described two-point teaching of the non-defective image OKI and the background image BGI, the non-defective background difference image is acquired in the registration mode, the non-defective background difference image is registered as a master image, and the master image and the input image are registered in the operation mode. Consider an example in which the degree of coincidence is calculated to determine pass / fail.

  Specifically, in the registration process A in FIG. 86A, the background image BGI in FIG. 86E is removed from the non-defective image OKI in FIG. 86C, and a simple difference image in which only the non-defective workpiece is extracted as shown in FIG. 86G is generated. Further, the feature quantity of the non-defective workpiece is extracted from the obtained non-defective workpiece image. For example, the feature amount extraction unit 56b calculates a luminance average value 75, a luminance variance 30, an edge pixel 50, and the like as feature amounts from the non-defective work image in FIG. 86G. In this way, after the registration process A is processed in advance in the registration mode, the pre-process B and the evaluation process C are performed in the operation mode. In addition, it is necessary to process within the specified response time. In other words, the image processing that needs to shorten the processing time is not the processing in the setting mode, but these preprocessing B and evaluation processing C in the operation mode. Is the processing time.

  In the preprocessing B, an image search is performed for the non-defective workpiece (FIG. 86G) cut out in the registration processing A with respect to the evaluation image (FIG. 86F) to be evaluated obtained as the input image. Thereby, a non-defective work is specified from the evaluation image as shown in FIG. 86H.

  In the evaluation process C, feature amounts are extracted and evaluated for the work area (FIG. 86J) cut out from the evaluation image (FIG. 86H). Further, the degree of coincidence is calculated by comparing with the feature quantity extracted in the registration process A. For example, the feature amount extraction unit 56b calculates a luminance average value 70, a luminance variance 30, an edge pixel 55, and the like as feature amounts from the work area in FIG. 86J. The quality determination unit 57d determines the quality by comparing the obtained feature value of the work area with the above-described feature value of the non-defective workpiece image.

In the above image processing, the processing time in the preprocessing B is required. For this reason, when the set response time is short, the preprocessing B and the evaluation processing C may not be completed within the response time in the operation mode. In this case, the image processing change unit changes the preprocessing B to a lighter load preprocessing D as shown in FIG. 86B. In the preprocessing D, for example, as shown in FIG. 86I, a difference process with the background image BGI (FIG. 86E) is performed instead of performing an image search of the work image with respect to the evaluation image (FIG. 86F). As a result, the non-defective work area can be cut out from the evaluation image of FIG. 86F as shown in FIG. 86I. As a result, the processing time can be shortened by replacing it with preprocessing that is simpler than the image search for the common purpose of removing the background from the evaluation image, and the image processing is completed within the response time. Is possible.
(Change of image processing algorithm component)

  In the above example, the method in which the image processing changing unit replaces the image processing algorithm in the image processing has been described. However, the method of changing the image processing condition by the image processing changing unit is not limited to the replacement of the image processing algorithm, and may be another method. Next, as another example in which the image processing change unit changes the image processing condition, an example in which the components of the image processing flow are changed will be described with reference to the flowcharts of FIGS. 87A and 87B. The images handled here (non-defective product image OKI, defective product image NGI, background image BGI, evaluation image) are the same as those in FIGS. 86C to 86F described above, and a series of image processing before changing the image processing conditions is shown in FIG. 87A, which is the same as FIG. 86A described above.

  First, in the registration process A ′ in the registration mode after the change, a non-defective work is specified based on the difference between the non-defective image OKI (FIG. 86C) and the background image BGI (FIG. 86E), and the feature quantity of the non-defective work is extracted. This image processing is the same as registration processing A in FIG. 86A (FIG. 87A), but the image processing parameters of the image processing algorithm are changed from registration processing A in registration processing A ′ when extracting the feature amount. Specifically, in the registration process A, a Sobel filter is used to extract “edge features” of the feature amounts. On the other hand, in the registration process A ′ in FIG. 87B, a “2 × 2 Roberts filter” is used for “edge feature” extraction.

Here, as shown in FIGS. 88A and 88B, the Sobel filter applies two types of filters, SobelX (FIG. 88A) and SobelY (FIG. 88B), to the eight pixels near the target pixel. Calculating thereafter, X component of the edge multiplied by SobelX, Sx each Y component of the edge multiplied by the SobelY, and Sy (Figure 88C), strength ^{= √ (Sx 2 + Sy 2} ), the angle = Arctan (Sy / Sx) To do. Although the 3 × 3 Sobel filter is used here, the present invention is not limited to this, and other Sobel filters such as 5 × 5 may be used.

On the other hand, the Roberts filter is image processing that simplifies the Sobel filter. More specifically, instead of SobelX and SobelY, filters of RobertsX and RobertsY shown in FIGS. 89A and 89B are simplified. From the obtained X component of the edge multiplied by RobertsX and Sx ′, Sy ′ (FIG. 89C) which are the Y components of the edge multiplied by RobertsY, the intensity = √ (Sx ′ ² + Sy ′) as in the Sobel filter. ² ) and angle = Arctan (Sy ′ / Sx ′). As a result, for example, the brightness average value 75, the brightness variance 30, the edge pixel 50, and the like are calculated as the feature amount of the work. Note that the feature value of the edge pixel may change due to the difference between the filter of Sobel and Roberts.

  In this way, after the image processing in the setting mode is performed first, the preprocessing B and the evaluation processing C and C ′, which are image processing in the registration mode, are performed. In both of FIG. 87A and FIG. 87B, the preprocessing B is similar to the above-described preprocessing B of FIG. 86A. Image search is performed on the cut out work, and the work is cut out from the evaluation image (FIG. 86F) (FIG. 86H).

  Further, in the evaluation processes C and C ′, the features of the work area (FIG. 86J) cut out from the evaluation image are extracted and evaluated. Here, in the evaluation process C of FIG. 87A, the Sobel filter similar to the registration process A is used, whereas in the changed evaluation process C ′ in FIG. 87B, the same Roberts filter as that of the registration process A is used. ing. Then, the feature amount of the evaluation image obtained by using the Roberts filter is compared with the feature amount extracted in the registration process A, and the degree of coincidence is calculated. In this way, for common image processing called edge extraction, which is one of the components of image processing, the processing time is shortened by simplifying the edge extraction method, and image processing is performed within the set response time. It is possible to finish.

  Further, in the above-described example, the example in which either the change of the image processing algorithm itself or the change of the components of the image processing algorithm is performed by the image processing content assignment unit 55f has been described. However, the present invention is not limited to this, The change of the image processing algorithm and the change of the components of the image processing algorithm can be combined. Further, the image processing content assignment unit 55f can change the already set image processing content according to the response time, and can also be used for an initial operation of assigning appropriate image processing in a state where the response time is given in advance. .

  Furthermore, image processing parameter changes in the image processing algorithm may be applied. For example, for the Sobel filter, the filter size may be changed from 3 × 3 to 5 × 5 or the like. As described above, the image processing changing unit can change the filter size of the edge filter for extracting the edge of the non-defective image OKI in the registration mode and extracting the edge of the input image in the operation mode.

  The image processing may be composed of a single image processing algorithm or a plurality of different image processing algorithms. In any case, the image processing content allocation unit 55f outputs all or a part of each image processing algorithm and image processing parameter for each image processing algorithm within the response time. Can be changed.

  Further, the coincidence degree calculation unit 57c may be configured to calculate a first coincidence degree that is a basis of the coincidence degree of the input image with respect to the master image for each of a plurality of different image processing algorithms in the operation mode.

  Furthermore, in the above-described example, the example in which the non-defective background difference image is used as the master image in the two-point teaching of the non-defective image OKI and the background image BGI has been described. However, the present invention is not limited to this. When performing two-point teaching of the image NGI, a good / defective product difference image may be used as a master image. Alternatively, in the three-point teaching of the non-defective product image OKI, the defective product image NGI (FIG. 86D), and the background image BGI, the master image corresponding to the non-defective product background differential image and the master image corresponding to the defective product background differential image are registered in the registration mode. In the operation mode, when calculating the degree of coincidence between the master image of the non-defective background difference image, the master image of the non-defective background difference image, and the input image, the image processing content assignment unit 55f performs image processing. You can also change the conditions. Alternatively, in the one-point teaching for registering the background image BGI, when the degree of coincidence with the input image is calculated using the background image BGI as a master image, the image processing content assignment unit 55f can change the image processing conditions.

In the example described above, the coincidence degree calculation unit 57c calculates a coincidence degree indicating the degree of coincidence between the feature amounts of the master image and the input image. Here, the master image that is the basis for calculating the degree of coincidence is configured according to the non-defective product image OKI, the defective product image NGI, and the background image BGI registered in the image / setting storage unit 54. For example, various kinds of difference images, compressed difference images obtained by compressing them, or edge images can be used. Further, the feature amount may be calculated based on information other than the image instead of the master image. For example, the degree of coincidence may be calculated by the degree of coincidence calculation unit 57c based on feature quantities such as edges and luminance. Thus, the basis for calculating the degree of coincidence by the coincidence degree calculation unit 57c is not necessarily limited to image data, and other information such as features such as edges and luminance can be used. In this specification, the degree of coincidence calculation is used. The underlying information is called a pattern model.
(Reset brightness condition)

  As described in the item of determining the optimum registration setting condition, the optimum assignment in which the condition allocation unit 55 has the lowest degree of coincidence of defective products among the candidate registration setting conditions that can be set in the designated response time. Determine the setting conditions. However, for example, when the exposure time, the resolution, and the image processing algorithm change, the image to be picked up changes, so it is necessary to re-image and re-register a registered image that serves as a reference after changing the setting. On the other hand, in this embodiment, by registering at least one image, it has means for determining adjustment values such as exposure time, resolution, and image processing algorithm, and is used at the current response time during registration. Even if there is a combination of adjustment values that do not exist, an image can be captured and saved, so that when the user changes the set value, the optimum adjustment value can be determined without re-registering the image. Here, focusing on the exposure time among the adjustment values, resetting of the brightness condition including the exposure time will be described.

  Table 3 is a table for showing evaluation based on a combination of response time and exposure time. If the image processing sensors 1 and 11 according to the present embodiment do not have a brightness condition resetting function, the following inconvenience occurs. As shown in this figure, for example, when four images having a response time of 20 ms and an exposure time of 0.2 ms to 3 ms are acquired, for example, if two-point teaching is used, the non-defective image OKI is registered 4 4 images are registered in the registration of the background image BGI, and then the process of determining the exposure time is performed. For example, when the exposure time of 3 ms is determined to be optimal, the non-defective memory OK image and the background image BGI of 3 ms are stored in the nonvolatile memory. save. Thereafter, when the response time is changed from 20 ms to 50 ms, from Table 3, 5 ms is optimal as the exposure time, but under the registration setting condition when the response time is 20 ms, imaging and storage at 5 ms are performed. Therefore, the user must set the response time to 50 ms, install the work WK again, and perform imaging with an exposure time of 5 ms. Note that the storage destination memory may be volatile or nonvolatile.

  On the other hand, in the present embodiment, seven images having an exposure time of 0.2 ms to 20 ms are acquired for all response times regardless of the current response time, and thereafter, at each response time, Determine the optimal exposure time. In the example of this figure, for example, images at four exposure times of 0.2 ms, 1.5 ms, 3 ms, and 5 ms are stored. By doing so, even if the response time is changed from 20 ms to 50 ms, 5 ms can be determined as the optimal exposure time without setting the work WK and taking an image again.

  The example of Table 3 shows that when the response time is 50 ms and 100 ms, evaluation that allows the exposure time to be longer than 5 ms cannot be obtained. This is because as the brightness increases, the S / N improves, and a clear image can be captured, but when it is too bright, it is affected by halation. Even in such a case, since the optimum exposure time is stored with respect to the response time, it is not necessary for the user to install again and re-image.

  A procedure for resetting the brightness condition according to the first embodiment will be described with reference to the flowchart of FIG. First, in step ST2001, an image is captured and displayed as a live image LVI. In step ST2002, it is determined whether or not the SET key 42 has been pressed. If it is detected that the SET key 42 has been pressed, the process proceeds to step ST2003, and the latest live image LVI or a newly captured image is registered as a non-defective image OKI. . If pressing of the SET key 42 is not detected, the process returns to step ST2001 and the live image LVI is displayed. Up to this point, the flow of registration of the non-defective image OKI is the same, but the flow of registration of the defective product image NGI in steps ST2004 to ST2006 and the flow of registration of the defective product image NGI in steps ST2007 to ST2009 are the same. When the registration of the non-defective product image OKI, the defective product image NGI, and the background image BGI is completed, in step ST2010, the optimum exposure time at each response time is calculated from the acquired image group, and the image at the exposure time is stored. To do. Proceeding to step ST2011, teaching processing is executed with an image having an optimum exposure time at the current response time.

  Next, the procedure of registration processing in step ST2003, step ST2006, and step ST2009 will be described based on the flowchart of FIG. First, in step ST2101, the exposure time setting for each response time is acquired from the table storage unit. Proceeding to step ST2102, the exposure time setting to be acquired is determined. In step ST2103, setting, image acquisition, and saving are repeated for the combination of settings.

  Finally, the operation procedure when changing the response time after teaching processing will be described based on the flowchart of FIG. First, processing is started in step ST2200, and in step ST2201, it is determined whether the response time has been changed. If not changed, the process returns to step ST2200 to repeat this determination. If changed, in step ST2202, the optimum exposure time with the changed response time and the image with the exposure time are read from the still image storage unit 54a. Next, in step ST2203, teaching processing using an image with the determined exposure time is performed.

  In the first embodiment, the optimum exposure time for all response times is calculated. However, if this calculation takes time, it takes time until the teaching is completed, and the user's convenience is lost. Therefore, in such a case, all the exposure time images that can be taken (7 images of 0.2 to 20 ms in the example of Table 3) are stored, and when the response time is changed, The optimum exposure time in the response time may be calculated after changing the response time.

  The procedure for resetting the brightness condition according to the second embodiment is substantially the same as that of the first embodiment, but the steps corresponding to step ST2010 in the flowchart of FIG. 90 are different. That is, in the second embodiment, in this step, the optimum exposure time is selected from the acquired image group and the teaching process using the image of the exposure time is executed, but the calculation for evaluation is not performed. Is different. In addition, regarding the operation procedure when changing the response time after teaching processing according to the second embodiment, steps corresponding to step ST2202 and step ST2203 in the flowchart of FIG. 92 are different from those in the first embodiment. In the second embodiment, in a step corresponding to step ST2202, an exposure time setting pattern at the response time after change is acquired from the table storage unit. In a step corresponding to step ST2203, an optimal exposure time is determined within the pattern. That is, in the second embodiment, the optimum exposure time in the response time is calculated after the response time is changed.

  As described above, both the first embodiment and the second embodiment store images while changing only the exposure time. However, the present invention can be similarly applied when the resolution and the image processing algorithm are changed. For example, when HDR (High Dynamic Range) ON / OFF is a function of the CMOS sensor, in each teaching step, not only the image at each exposure time but also 2 patterns of HDR ON / OFF × each exposure time. If the image is stored, it is possible to eliminate the need for re-imaging even when the HDR ON / OFF setting is changed.

  Here, the procedure of registration processing in the combination of HDR ON / OFF and exposure time will be described based on the flowchart of FIG. First, in step ST2301, the exposure time setting for each response time is acquired from the table storage unit. For example, when matched with the example in Table 3, seven settings of 0.2, 0.8, 1.5, 3, 5, 10, and 20 ms are acquired. In step ST2302, a combination of exposure time and setting to be acquired is determined. For example, a total of 14 patterns of 2 patterns of exposure time 7 patterns × HDR ON / OFF are determined. In step 1602, the setting of the apparatus is changed so that an image can be captured in a certain combination. In step ST2303, an image is acquired based on the registration setting condition. It progresses to step ST2304, it is determined whether the image for the determined pattern was acquired, and if it is not acquired, it will return to step ST2302 and will repeat acquisition of an image until acquisition of the image for a pattern is completed. Next, an operation procedure when changing the response time after the teaching process will be described based on the flowchart of FIG. First, in step 1701, for example, consider a case where the response time is changed from 20 ms to 50 ms. In step ST2402, an exposure time setting pattern (6 patterns of 0.2 ms to 10 ms) at a response time of 50 ms is acquired from the table storage unit. Next, in step ST2403, an optimal exposure time is calculated from the six patterns, and determined to be 5 ms, for example. In step ST2404, teaching processing using an image having an exposure time of 5 ms is performed.

The same applies to the digital zoom (imaging range setting). For example, when the digital zoom is set to 1 time, even if an image with one pixel skip is sufficient, an image without pixel skip in the entire field of view is acquired. By doing so, even if the digital zoom setting changes, re-imaging can be made unnecessary. In addition, for example, the following parameters can be considered.
-CMOS sensor neighboring pixel total calculation power ON / OFF
・ Maximum exposure time setting (setting for work speed)
・ Algorithm setting (± 180 degrees permissible, precision mode: processing time changes, so the number of pixels that can be processed changes, pixel skip setting changes with each response time, automatic brightness adjustment, etc.)

  As described above, the image processing sensors 1 and 11 according to the present embodiment can be displayed in various display formats by combining any one of various images, threshold values, matching degrees, and various matching degree statistical values, You can switch between them. In other words, by providing images that are elements that are not in the display format familiar to photoelectric sensors and enabling them to be switched, it is possible to provide an image processing sensor that can be set at a higher level with ease of use, such as a photoelectric sensor. Can do.

  According to the image processing sensor, the image processing method, the image processing program, the computer-readable recording medium, and the recorded device of the present invention, an image having a certain spread can be used instead of the photoelectric sensor installed in the production line. Good product inspection and defective product inspection can be suitably performed.

DESCRIPTION OF SYMBOLS 1, 11 ... Image processing sensor 2 ... Sensor part 21 ... Imaging part; 211 ... Camera; 212 ... Illumination 22 ... Illumination board | substrate;
23 ... Imaging substrate; 231 ... CMOS
24 ... Power supply board; 241 ... LED driver 25 ... Main board; 251 ... DSP; 252 ... Memory 3 ... Controller part; 3A ... Sensor part side connector; 3B ... Cover part 31 ... Display board;
32 ... Power supply board; 321 ... External communication 33 ... Main board 331 ... MCU
4 ... casing; display surface ... 4a; imaging surface ... 4b; 4c ... operation button 401 ... front case; 402 ... heat insulation case; 403 ... optical base; 404 ... rear case 41 ... judgment result indicator lamp 42 ... SET key 43 ... display 4311 ... bank display; 4312 ... output channel display; 4313a, b ... coincidence; 4314a, b ... threshold; 4315a, b, c, d ... vertical display; 4319a, b ... maximum coincidence; 4320a, b ... Minimum coincidence; 4321a, b ... peak maximum value when ON; 4322a, b ... peak minimum value when ON; 4323 ... bar; 4325 ... image with maximum coincidence / minimum coincidence obtained; 4326 ... peak maximum value when ON Image 44 with peak minimum value obtained when ON / OFF; 44a ... Up key; 44b ... Down key; 44C ... Up / down key 45 ... BACK key 46 MODE key 47 ... output status indicator 48 ... connector 51 ... operation part; 51a ... non-defective image setting part; 51b ... defective image setting part; 51c ... background image setting part; 51d ... operation / setting mode switching part; Time setting unit; 51f ... screen display switching unit; 51g ... coincidence statistics clearing unit; 51h ... increase / decrease adjustment unit; 51i ... cancellation instruction unit; 51j ... rotation allowable range setting unit; 51k ... registration mode switching unit; 51m ... Output channel setting unit; 51n ... Non-defective / defective product output setting unit 52 ... Image acquisition unit 53 ... Display unit; 53a ... Live image display unit; 53b ... Still image display unit; 53e ... Determination result display unit; 53f ... Operation instruction display unit; 53g ... Consistency statistics display unit; 53h ... Consistency statistics image display unit; 53i ... Operation bank display unit 54 ... Image / setting storage unit; 54a ... Static Image storage unit: 541a ... non-defective product image storage unit; 542a ... defective product image storage unit; 543a ... background image storage unit; 54b ... live image storage unit; 54c ... coincidence-statistical image storage unit; 54d ... setting storage unit; ... coincidence statistic storage unit; 54f ... bank setting storage unit; 54g ... threshold (first, second) storage unit; 54h ... registration identification instruction information storage unit; 54i ... non-defective / defective product output setting storage unit 55 ... condition Allocation unit; 55a ... Imaging condition allocation unit; 55b ... Brightness condition allocation unit; 55c ... Brightness condition candidate setting unit; 55d ... Brightness condition selection unit; 55e ... Image compression setting unit; 55f ... Image processing content allocation unit 56 ... Setting image processing unit; 56a ... Difference image generation unit; 56b ... Feature amount extraction unit; 56c ... Threshold calculation unit; 56d ... Image compression unit; 56e ... Weight setting unit 57 ... Driving image processing unit; Extraction unit; 57c ... coincidence calculation unit; 57d ... pass / fail determination unit; 57e ... coincidence statistical value calculation unit 58 ... setting management unit; 58a ... guidance display control unit; 58b ... screen transition unit; 58c ... image access unit; ... coincidence statistical value access unit; 58e ... bank switching control unit; 58f ... display control unit 61 ... main control unit WK ... work PD ... image display area ED ... description display area OKI ... non-defective image NGI ... defective product image BGI ... background Image LVI ... Live image COKI ... Compressed good product image CNGI ... Compressed defective product image CBGI ... Compressed background image

Claims (16)

An image processing sensor for detecting that an inspection object is a non-defective product or a defective product by performing image processing on an image of the inspection object,
An imaging unit for imaging an inspection object;
A display unit for displaying an input image acquired by the imaging unit;
Based on the input image acquired by the imaging unit, a quality determination unit that determines the quality of the inspection object;
An image including an inspection object to be determined as non-defective by the non-defective determination unit is acquired by the imaging unit and registered as a first non-defective image, and a background image from which a characteristic part as a non-defective product of the inspection object is removed Is acquired by the imaging unit and registered as a first background image;
A difference image generation unit that generates a first non-defective background difference image from the first non-defective image registered by the image registration unit and the first background image registered by the image registration unit;
Based on the first non-defective background difference image generated by the differential image generating unit, a degree of coincidence indicating the degree of feature matching of the first background image with respect to the pattern model corresponding to the first non-defective background difference image is calculated. A coincidence calculation unit;
A threshold value calculation unit that calculates a threshold value used for pass / fail determination by the pass / fail determination unit based on the match level calculated by the match level calculation unit;
In the display unit, the threshold value calculated by the threshold value calculation unit and a degree of coincidence of the latest input image with the pattern model are numerically displayed, and the first display format for displaying the latest input image, and the threshold value calculation unit Switching control of two display formats, the threshold value calculated by the above and the matching degree of the latest input image with respect to the pattern model and the second display form for numerically displaying the past maximum and / or the past minimum matching degree during operation. A display control unit to perform,
An image processing sensor comprising: An image processing sensor for detecting that an inspection object is a non-defective product or a defective product by performing image processing on an image of the inspection object,
An imaging unit for imaging an inspection object;
A display unit for displaying an input image acquired by the imaging unit;
Based on the input image acquired by the imaging unit, a quality determination unit that determines the quality of the inspection object;
An image including an inspection object to be determined as a non-defective product by the quality determination unit is registered as a second non-defective image, and an image including the inspection target to be determined as a non-defective product by the quality determination unit is defined as a defective product image. An image registration unit for registering and acquiring a background image from which a characteristic part as a non-defective product of the inspection object is removed by the imaging unit and registering it as a second background image;
The second good product background difference image from the second good product image registered by the image registration unit and the second background image registered by the image registration unit, the defective product image registered by the image registration unit, and the A difference image generation unit for generating a defective product background difference image from the second background image registered by the image registration unit, and
A degree of coincidence calculation unit that calculates a degree of coincidence indicating the degree of feature coincidence of the defective product background difference image with respect to the pattern model corresponding to the second non-defective background difference image generated by the difference image generation unit;
A threshold value calculation unit that calculates a threshold value used for pass / fail determination by the pass / fail determination unit based on the match level calculated by the match level calculation unit;
In the display unit, the threshold value calculated by the threshold value calculation unit and a degree of coincidence of the latest input image with the pattern model are numerically displayed, and the first display format for displaying the latest input image, and the threshold value calculation unit A display for performing switching control between two display formats: a threshold value calculated by the above and a second display format in which the degree of coincidence of the latest input image with respect to the pattern model and the past maximum or past coincidence degree during driving are numerically displayed. A control unit;
An image processing sensor comprising: The image processing sensor according to claim 1, further comprising:
A setting mode for calculating a threshold value used for the quality determination by the quality determination unit by the threshold value calculation unit, and an operation for determining the quality of the inspection object by the quality determination unit using the threshold value calculated in the setting mode. It has an operation / setting mode switching part that switches between modes,
The display control unit displays the threshold value calculated in the setting mode switched by the driving / setting mode switching unit as a numerical value in the driving mode switched by the driving / setting mode switching unit. Sensor. The image processing sensor according to claim 1, further comprising:
The outer shape is rectangular and includes a casing having a plurality of outer surfaces,
The display unit is provided on one surface of the rectangular casing,
The display control unit is an image processing sensor configured to display a past maximum and a past minimum coincidence during driving on the display unit in parallel. The image processing sensor according to any one of claims 1 to 4,
The display control unit is an image processing sensor configured to be able to alternately switch and display a past maximum coincidence during driving and a past minimum coincidence during driving. An image processing sensor according to any one of claims 1 to 5,
The display control unit, as a third display format, causes the display unit to numerically display the threshold calculated by the threshold calculation unit and the degree of coincidence of the latest input image with respect to the pattern model, and the latest input image Display the display format larger than the size of the number constituting the numerical value constituting the numerical value representing the threshold value calculated by the threshold value calculation unit, the size of the numerical value constituting the numerical value representing the degree of coincidence of
An image processing sensor that performs switching control to display in the third display format in addition to display in the first display format and display in the second display format. The image processing sensor according to any one of claims 1 to 6,
The display control unit displays, as a fourth display format, a numerical value indicating a past maximum or past minimum coincidence among the degrees of coincidence exceeding the threshold calculated by the threshold calculation unit during operation on the display unit. Display the display format to be
An image processing sensor that performs switching control to display in the fourth display format in addition to display in the first display format and display in the second display format. The image processing sensor according to claim 1,
The display control unit performs display of a display format for displaying the first or second good product image registered by the image registration unit and the latest input image on the display unit as a fifth display format,
An image processing sensor that performs switching control to display in the fifth display format in addition to display in the first display format and display in the second display format. The image processing sensor according to claim 1,
The threshold value calculation unit is configured to be able to calculate a first threshold value and a second threshold value with respect to the matching degree calculated by the matching degree calculation unit,
The image processing sensor further includes:
Based on the comparison between the degree of coincidence of the input image and the first threshold and the second threshold, there are two channels that respectively output the first discrimination result and the second discrimination result by the pass / fail judgment unit, An image processing sensor including a channel selection unit that selects two channels. The image processing sensor according to claim 1, further comprising:
A bank setting storage unit that stores a plurality of bank settings associated with the first or second non-defective image registered by the image registration unit and the threshold value calculated by the threshold value calculation unit;
A bank switching unit for switching to any of a plurality of bank settings stored in the bank setting storage unit;
An image processing sensor comprising: The image processing sensor according to claim 1, further comprising:
An image processing sensor comprising: a rotation allowable range setting unit that sets an angle range that allows posture rotation of an input image acquired by the imaging unit when calculating the coincidence by the coincidence calculation unit. An image processing method for detecting that an inspection object is a non-defective product or a defective product by performing image processing on an image of the inspection object,
Registering an image including an inspection object to be determined as a first non-defective image,
A step of acquiring a background image from which a characteristic part as a non-defective product to be determined as a non-defective product is removed by the imaging unit and registering it as a first background image;
Generating a first non-defective background difference image from the first non-defective image registered by the image registering unit and the first background image registered by the image registering unit;
Based on the first non-defective background difference image generated by the differential image generating unit, a degree of coincidence indicating the degree of feature matching of the first background image with respect to the pattern model corresponding to the first non-defective background difference image is calculated. Process,
Calculating a threshold value used for pass / fail judgment based on the calculated degree of coincidence;
In the display unit, a first display format for displaying numerically the degree of coincidence of the latest input image with the calculated threshold value and the pattern model, and displaying the latest input image, the calculated threshold value and the pattern model A step of performing switching control between two display formats, the second display format for numerically displaying the degree of coincidence of the latest input image and the past maximum and / or the past minimum coincidence during operation;
An image processing method including: An image processing method for detecting that an inspection object is a non-defective product or a defective product by performing image processing on an image of the inspection object,
Registering an image including an inspection object to be identified as a non-defective product as a second non-defective image;
Registering an image containing an inspection object to be identified as a defective product as a defective product image;
A step of acquiring a background image from which a characteristic part as a non-defective product of the inspection object is removed by the imaging unit and registering it as a second background image;
The second good product background difference image from the second good product image registered by the image registration unit and the second background image registered by the image registration unit, the defective product image registered by the image registration unit, and the A step of generating a defective product background difference image from the second background image registered by the image registration unit;
Calculating a degree of coincidence indicating a degree of feature coincidence of a defective product background difference image with respect to a pattern model corresponding to the generated second good product background difference image;
Calculating a threshold value used for pass / fail judgment based on the calculated degree of coincidence;
The display unit displays numerically the degree of coincidence of the latest input image with respect to the calculated threshold value and the pattern model, and displays a first display format for displaying the latest input image, the calculated threshold value and the pattern model A step of performing switching control between two display formats, a second display format for displaying numerically the degree of coincidence of the latest input image and the past maximum and / or past minimum coincidence during operation;
An image processing method including: An image processing program for detecting that an inspection object is a non-defective product or a defective product by performing image processing on an image of the inspection object,
A function for registering an image including an inspection object to be determined as a non-defective product as a first non-defective image;
A function of acquiring an image of a background from which a characteristic part as a non-defective product to be determined as non-defective is removed by the imaging unit and registering it as a first background image;
A function for generating a first non-defective background difference image from the first non-defective image registered by the image registering unit and the first background image registered by the image registering unit;
Based on the first non-defective background difference image generated by the differential image generating unit, a degree of coincidence indicating the degree of feature matching of the first background image with respect to the pattern model corresponding to the first non-defective background difference image is calculated. Function and
A function for calculating a threshold value used for pass / fail judgment based on the calculated degree of coincidence;
In the display unit, a first display format for displaying numerically the degree of coincidence of the latest input image with the calculated threshold value and the pattern model, and displaying the latest input image, the calculated threshold value and the pattern model A function of performing switching control between two display formats, the second display format for numerically displaying the degree of coincidence of the latest input image with respect to and the past maximum and / or past minimum coincidence during operation,
An image processing program for realizing a computer. An image processing program for detecting that an inspection object is a non-defective product or a defective product by performing image processing on an image of the inspection object,
A function for registering an image including an inspection object to be identified as a non-defective product as a second non-defective image;
A function for registering an image including an inspection object to be identified as a defective product as a defective product image;
A function of acquiring an image of a background from which a characteristic part as a non-defective product of an inspection object is removed by the imaging unit and registering it as a second background image;
The second good product background difference image from the second good product image registered by the image registration unit and the second background image registered by the image registration unit, the defective product image registered by the image registration unit, and the A function to generate a defective product background differential image from the second background image registered by the image registration unit;
A function of calculating a degree of coincidence indicating a feature coincidence degree of the defective product background difference image with respect to the pattern model according to the generated second good product background difference image;
A function for calculating a threshold value used for pass / fail judgment based on the calculated degree of coincidence;
The display unit displays numerically the degree of coincidence of the latest input image with respect to the calculated threshold value and the pattern model, and displays a first display format for displaying the latest input image, the calculated threshold value and the pattern model A function for performing switching control between two display formats, a second display format for numerically displaying the coincidence degree of the latest input image and the past maximum and / or past minimum coincidence during operation;
An image processing program for realizing a computer.   A computer-readable recording medium or a device storing the program according to claim 14 or 15.