JP2009217368A - Image processor - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an image processor for facilitating correcting a parameter by simultaneously displaying inspections having similar processing content. <P>SOLUTION: An image processor 10 performs appearance inspection including template matching to an object image of an object imaged by an image pickup device 20. A plurality of inspection items are prepared for the appearance inspection, and a plurality of types of image templates to be used for template matching are prepared. A reverse lookup part 14 classifies the inspection items for every type of the image templates, and displays the inspection items associated with the image templates on the screen of a monitor device 22 in a list. <P>COPYRIGHT: (C)2009,JPO&INPIT

Description

  The present invention relates to an image processing apparatus that performs template matching on an image of an object.

Conventionally, in image processing technology, template matching is known in which an input image captured by an imaging device and a reference image stored in advance are collated. In template matching, a plurality of reference images (templates) are sequentially displayed on the screen of the display device, and a reference image is selected by performing a selection operation while a desired reference image is displayed on the screen. It is considered to determine a reference image used for collation with an input image (see, for example, Patent Document 1).
JP 2001-165863 A

  By the way, when the appearance inspection is performed on the quality of the target object, as shown in FIG. Further, as shown in FIG. 7, different objects A1, A2 may be collated with the same reference image T.

  As in the examples of FIGS. 6 and 7, even when the same reference image T is used, if the collation positions are different, the parameters given to the respective reference images T for alignment are different. It is necessary to set the parameters. In other words, it is necessary to select the reference image T for each collation position and set parameters.

  Position correction is required for the verification position. In the position correction, the position is moved in parallel at a constant step size (for example, 5 pixels) or rotated at a constant step angle (for example, 1 degree). For the position correction, the same method is often selected even if the reference image T and the content of the inspection are different.

  Generally, since the reference image T and the position correction method to be used are set for each inspection, the reference image T is corrected even in the inspection using the same reference image T or the inspection using the same position correction method. If the position correction method is to be corrected, the processing parameters are called for each inspection to correct the parameters.

  On the other hand, since this type of correction often performs the same correction when the reference image T and the position correction method are common, an inspection using the same reference image T and the same position correction method are performed. In many cases, it is necessary to search for the inspections used individually and change the parameters, which is troublesome.

  The present invention has been made in view of the above-described reasons, and an object thereof is to provide an image processing apparatus that facilitates parameter correction work by collectively displaying examinations having the same processing contents. .

  The invention according to claim 1 is an image processing apparatus that performs an appearance inspection by performing a process including template matching using an image template selected from a plurality of types of image templates on a target image obtained by capturing an object. The apparatus includes a reverse lookup unit that classifies inspection items for each type of image template and displays a list of the inspection items in association with the image template on a screen of a display device.

  According to a second aspect of the present invention, in the first aspect of the invention, the reverse lookup unit displays a list of a plurality of image templates on the screen of the display device and associates inspection items for each image template. It is displayed on the screen.

  According to a third aspect of the present invention, in the first or second aspect of the invention, the reverse lookup unit is configured to set inspection items classified for each type of template and processing parameters in the inspection item on the screen of the display device. A window is associated with the display, and by selecting an inspection item, a process setting window for the inspection item is displayed on the screen of the display device.

  According to the configuration of the first aspect of the invention, paying attention to the image template used by each inspection item among a plurality of types of image templates, the inspection items are classified for each image template and displayed in a list on the screen of the display device. For inspection items that use the same image template, the same type of correction is often performed when correcting the processing parameters. Compared to the case where the inspection item that uses the same type of image template is searched and the parameters are corrected. This eliminates the trouble of searching for the inspection item and facilitates the parameter correction work.

  According to the configuration of the invention of claim 2, since a plurality of types of image templates are displayed in a list on the screen of the display device, which image template is used for which inspection item can be listed and recognized. The correction work becomes easier.

  According to the configuration of the invention of claim 3, since the setting window for setting the parameters can be displayed simply by selecting the desired inspection item from the inspection items displayed in the list, the inspection item using the same image template It becomes easy to correct the parameters.

  In the embodiment described below, a case where an appearance inspection of an object is performed using an image (grayscale image) obtained by imaging the object as a target image will be described as an example. In addition, the appearance inspection mainly includes a template matching process, and it is also assumed that the edge inspection and the area of the object are measured.

  An image processing apparatus that performs image processing on a target image includes a microcomputer as a main component, and is loaded with programs for performing various image processing such as position correction processing, position recognition processing, and edge detection processing. The program is independent for each process, and the user can select and combine the programs. In order to perform a desired visual inspection from an object, it is necessary not only to select and combine programs but also to give parameters for specifying operating conditions to each program. In this embodiment, a plurality of types of inspection items (edge inspection, area measurement, etc.) are inspected on the object, and a plurality of inspection regions are set in the target image as necessary. Assume that For one inspection area, an appearance inspection of one or more types of inspection items is performed. The appearance inspection performed on one type of object is hereinafter referred to as “project”. Therefore, a project includes a plurality of inspection items.

  When template matching is included in each inspection item of the project, the processing parameters include the type of image template to be matched with the image in the inspection area and the method for correcting the position of the image template in the inspection area. It is. The position correction method includes a step size for moving the image template in parallel, a necessity of rotation of the image template, and a step angle when rotation is necessary. Further, the position correction method may include an enlargement / reduction ratio as necessary.

  The image template is selected according to each inspection item from a plurality of types of options given in advance. The position correction method is the same, and is selected from options prepared in advance. Image template choices are extracted from previously captured images or created in advance as ideal forms.

  In the following, the type of image template used in the process is assigned an identification code by number for each type, and is designated in the form of “template No. xxx” such as “template No. 002”. Similarly, the position correction method is assigned a number for each content, and is specified in the format of “position correction No. xxx”. Further, “type of image template” is abbreviated as “template”, “position correction method” is abbreviated as “position correction”, and “inspection item” is abbreviated as “inspection”.

  As shown in FIG. 1, a personal computer (hereinafter abbreviated as “computer”) 21 is connected to the image processing apparatus for selecting and combining programs for processing, setting parameters, setting inspection areas, and the like. A connection port is provided that enables it. In addition, the image processing apparatus 10 is provided with a connection port for connecting a TV camera as the imaging device 20 for imaging an object and a connection port for connecting a monitor device 22 as a display device. A plurality of (four in the illustrated example) imaging devices 20 can be connected to the image processing device 10, and an image captured by each imaging device 20 can be selected and displayed on the screen of the monitor device 22, or a monitor can be displayed. It is possible to divide the screen of the device 22 and display all the images of the imaging device 20 on one screen at the same time. Note that the screen of the computer 21 may be used as a display device instead of the monitor device 22.

  The image processing apparatus 10 includes an image memory 11 that temporarily stores a target image captured by the imaging apparatus 20 and a storage device 12 that stores the target image. The storage device 12 stores a system program and a program for performing various processes on the target image (in many cases, only a program for a necessary process is selected and stored), setting values for attributes of each process, and the like. At least a part of the storage device 12 is a semiconductor memory (RAM), and provides a work area when processing a target image. In the illustrated example, a work area and a function for performing various processes are represented as a processing unit 13. That is, the processing unit 13 is configured by a storage device, a microprocessor, and the like that include an area for storing a program for performing processing and setting values related to processing attributes and a work area. Interfaces 15 and 16 for connecting the computer 21 and the monitor device 22 are also provided in the image processing apparatus 10.

  In this embodiment, the reverse lookup unit 14 is provided, and it is possible to extract a list of examinations using the same template or to extract a list of examinations using the same position correction. In short, paying attention to at least one of the template and the position correction, the reverse lookup unit 14 that searches for the examination by reverse lookup is provided.

  Therefore, the reverse lookup unit 14 can classify the inspections using either the template used for the project or the position correction. The examinations classified for each template by the reverse lookup unit 14 are displayed in association with each template on the template list screen P1 (see FIG. 2).

  Specifically, in the template list screen P1, a shape presentation window W1 for displaying the shape of the image template and an identifier presentation window W2 for displaying an identification code for distinguishing the image template are provided, and each shape presentation window W1 A list of examination list presentation windows W3 for displaying a list of examinations using the image template in association with each other is displayed. Since the size of the examination list presentation window W3 is such that about three examinations are displayed at a time, when one image template is used in four or more examinations, the examination list is scrolled. Therefore, other examinations can be displayed. The position correction is similar to the template, and a list of examinations is presented for each position correction by selecting a position correction list screen.

  Here, with respect to the inspection list, when any inspection is selected using the pointing device of the computer 21, a setting window for setting processing parameters including a template used for the inspection and position correction is monitored. It is displayed on the screen of the device 22. Since the parameters can be corrected in the setting window, the parameters can be adjusted so as to appropriately perform the target inspection. For example, the position correction can be changed by selecting an inspection using a specific template and opening the setting window. In this case, for example, it is possible to increase the accuracy of the position obtained as a result of position detection by template matching by changing the step size when the template is moved in parallel.

  Further, the inspection list can be cut (cut), pasted (pasted), and deleted for each inspection by using the pointing device of the computer 21. Although not shown in FIG. 2, an execution button is provided in association with each shape presentation window W1, and when selecting an image and selecting an examination from the list and pressing the execution button (equivalent to clicking with a mouse), An inspection may be performed on the image.

  Incidentally, the template list screen P1 and the position correction list screen are generated according to the procedure shown in FIG. The illustrated example is a procedure for generating a template list screen. First, an address table of image templates is created (S1). The address table is a data table that associates a set of a template and an address of a parameter table as shown in Table 1, and the addresses of the parameter table are related to all templates.

  On the other hand, the parameter table is a data table that is generated as necessary when registering the processing parameters used in each inspection. As shown in Table 2, the processing parameters are set in units of inspection for each image template. A group (hereinafter referred to as “inspection parameter registration”) is related. Each inspection parameter registration is given an identifier by number. In the parameter table, “use count” indicating the number of inspection parameter registrations for each image template is also registered.

  When the template list screen P1 is generated, the inspection parameter registration identifier is returned to the initial value (0) (S2), and the inspection parameter registration set in the storage device 12 is searched in the order of the identifier. That is, the inspection parameter registration to which the identifier “0” is assigned is searched first. If there is no parameter table including this inspection parameter registration (S3: Yes), the parameters of the image template (for example, No. N) used in the inspection parameter registration (in this case, the inspection parameter registration with an identifier of 0) are used. The table area is secured in the RAM constituting the storage device 12 (S4).

  Thereafter, the “use count” value in the parameter table is temporarily set to “0” (S5), and then “1” is added to the “use count” value (S6). Furthermore, inspection parameter registration (in this case, inspection parameter registration with an identifier of 0) is registered in the created parameter table (S7).

  That is, for the inspection parameter registration detected for the first time, a new parameter table is created, one inspection parameter registration is stored in the parameter table, and the use count is set to 1.

  Next, the inspection parameter registration identifier is incremented (S8), and the next inspection parameter registration is searched. In other words, the inspection parameter registration whose identifier is “1” is searched. Thus, each inspection parameter registration is searched one after another (S9: No). Here, when the searched inspection parameter registration uses the same image template as the searched inspection parameter registration (S3: No), the usage count is incremented in the existing parameter table (S6), and the inspection is performed. The parameter registration is added to the parameter table (S7).

  The reverse lookup unit 14 performs the above processing for all inspection parameter registrations (S9), and classifies and stores the inspection parameter registrations in the parameter table of each image template.

  With this procedure, a parameter table for an image template that is not used for inspection parameter registration is not generated, so that the consumption of the storage capacity of the storage device 12 can be suppressed. The parameter table is relocatable, and the address of the parameter table in the address table is changed as the parameter table is generated. The same processing is performed for position correction.

  As described above, since the inspection list is generated for the template and the position correction, for example, as shown in FIG. 4, by selecting the inspection areas D1 to D3 set in the target image, the inspection areas D1 to D3 are selected. It is possible to extract the template and position correction used in the above, and to extract a list of the template and the examination related to the position correction. The list of examinations is displayed in the examination list presentation window W4. Therefore, when there are a plurality of inspection areas D1 to D3 in the target image, a list of inspections can be displayed for each of the inspection areas D1 to D3. Similarly to the examination list presentation window W3, the examination list presentation window W4 can open a setting window for setting processing parameters used in the examination by selecting one of the examinations, and an execution button is provided. Thus, the effect on the image by the set parameters can be confirmed.

  In the example described above, the list of examinations is displayed in the examination list presentation window W3 associated with the shape presentation window W1 for displaying the shape of the image template. However, as shown in FIG. A list of inspection parameter registrations may be displayed in a hierarchical form. If it is displayed in a tree shape, it becomes obvious at a glance which inspection parameter registration is used for each image template. Even when displaying in a tree shape, the setting window can be opened by selecting desired inspection parameter registration.

It is a block diagram which shows embodiment. It is a figure which shows the example of a display in the same as the above. It is operation | movement explanatory drawing same as the above. It is a figure which shows the usage example same as the above. It is a figure which shows the usage example same as the above. It is a figure which shows the usage example of an image template. It is a figure which shows the usage example of an image template.

Explanation of symbols

DESCRIPTION OF SYMBOLS 10 Image processing apparatus 11 Image memory 12 Storage apparatus 13 Processing part 14 Reverse drawing part 15 Interface 16 Interface 20 Imaging device 21 Computer 22 Monitor apparatus

Claims (3)

  An image processing apparatus that performs appearance inspection by performing processing including template matching using an image template selected from a plurality of types of image templates on a target image obtained by imaging a target object, inspects each type of image template. An image processing apparatus, comprising: a reverse lookup unit that classifies items and displays a list of inspection items on a screen of a display device in association with an image template.   2. The reverse lookup unit displays a plurality of image templates in a list on the screen of the display device, and displays the image items on the screen of the display device in association with inspection items for each image template. Image processing device.   The reverse lookup unit associates an inspection item classified for each type of template on the screen of the display device and a setting window for setting a processing parameter in the inspection item, and selects the inspection item to select the inspection item. The image processing apparatus according to claim 1, wherein a processing setting window for the inspection item is displayed on a screen of the display device.

Images