JP7047725B2 - Inspection system, inspection method and program - Google Patents

Description

The present technology relates to inspection systems, inspection methods and programs.

Japanese Unexamined Patent Publication No. 2018-8471 (Patent Document 1) discloses a focus adjusting device having an autofocus function for searching the in-focus position of a focus lens based on a contrast evaluation value of a subject image. Further, Patent Document 1 discloses that such a focus adjusting device is applied to industrial equipment for inspection.

Japanese Unexamined Patent Publication No. 2018-8471 International Publication No. 17/056557 Japanese Unexamined Patent Publication No. 2010-78681 Japanese Unexamined Patent Publication No. 10-170817

When performing an inspection using an captured image, it is necessary to obtain an image in focus on the inspection target portion of the object. However, depending on the state of the object, there is a possibility that an image focused on a portion different from the inspection target portion of the object can be obtained. For example, the focus may shift from the inspection target location of the object due to individual differences in the size of the object. Alternatively, the focus may be deviated from the inspection target location of the object depending on the state of the transport device that conveys the object. In such a case, even though the object is defective, the image is focused on a portion different from the inspection target portion, so that the defect in the inspection target portion cannot be recognized and the defect is overlooked.

The present invention has been made in view of the above problems, and an object of the present invention is to provide an inspection system, an inspection method and a program capable of reducing the risk of overlooking a defect of an object.

According to an example of the present disclosure, an inspection system comprises an optical system with a variable focal position, an image pickup element that produces an image by receiving light from an object through the optical system, and a focus that adjusts the focal position. It includes an adjustment unit, an inspection unit, and an evaluation unit. The inspection unit inspects the object based on the first region of the inspection image generated when the focus position is adjusted by the focus adjustment unit, and outputs the inspection result. The evaluation unit evaluates the reliability of focusing on the inspection target portion of the object based on the second region of the inspection image, and outputs the evaluation result.

According to this disclosure, the reliability of focusing on the inspection target portion is evaluated based on the second region different from the first region. Therefore, for example, even when the contrast of the first region to be inspected is low, the reliability of focusing on the inspection target portion can be evaluated based on the second region different from the first region. Then, based on the evaluation result, it becomes possible to recognize that the inspection cannot be performed accurately due to the deviation of the focal position. As a result, it is possible to reduce the risk of overlooking a defective object as a good product by performing an inspection based on an image focused on a portion different from the inspection target location.

In the above disclosure, the inspection system relatives the first and second regions to the inspection image based on the deviation of the position and orientation of the object in the inspection image with respect to the position and orientation of the object in the pre-generated reference image. A correction unit for correcting the position and posture is further provided.

According to this disclosure, even if the position and orientation of the object in the inspection image are changed, it is possible to suppress the deterioration of the inspection accuracy and the evaluation accuracy of the reliability.

In the above disclosure, the inspection system determines that the object is a good product when the inspection result meets the predetermined first criterion and the evaluation result meets the predetermined second criterion. Further prepare.

According to this disclosure, it is easy to reduce the risk of overlooking a defective object as a good product by an image-based inspection focused on a portion different from the desired portion of the object.

In the above disclosure, the correction unit obtains the deviation based on the correlation value obtained by the correlation calculation between the reference image and the inspection image. The inspection system further satisfies the case where the inspection result meets the predetermined first criterion, the evaluation result meets the predetermined second criterion, and the correlation value meets the predetermined third criterion. Further, a determination unit for determining that the object is a good product is provided.

According to this disclosure, it is possible to further reduce the risk of overlooking a defective object as a good product even though the object cannot be imaged normally.

In the above disclosure, the evaluation result includes an evaluation value calculated based on the degree of focus in the second region of the inspection image. As a result, the degree of focusing can be easily recognized by confirming the evaluation value.

In the above disclosure, the inspection system further comprises a search unit that searches for a focus position, which is a focal position that focuses on the object. The inspection image is generated when the focus position is adjusted to the in-focus position by the focus adjustment unit. As a result, by confirming the evaluation result, it can be recognized that the inspection cannot be performed accurately due to the fact that the search for the in-focus position by the search unit is not properly executed.

According to an example of the present disclosure, an optical system having a variable focal position, an image pickup element that generates an image by receiving light from an object via the optical system, and a focus adjusting unit that adjusts the focal position are provided. The inspection method in the inspection system provided includes a step of inspecting an object based on the first region of the inspection image generated when the focus position is adjusted by the focus adjustment unit and outputting the inspection result, and an inspection image. Based on the second region of the above, the step of evaluating the reliability of focusing on the inspection target portion of the object and outputting the evaluation result is provided.

According to an example of the present disclosure, the program is a program for causing a computer to execute the above inspection method. These disclosures can also reduce the risk of overlooking defects in the object.

According to the present invention, the risk of overlooking a defect in an object can be reduced.

It is a schematic diagram which shows one application example of the inspection system which concerns on embodiment. It is a figure which shows an example of the internal structure of the image pickup apparatus provided in an inspection system. It is a schematic diagram for demonstrating autofocus. It is a figure which shows an example of the lens module which the focal position is variable. It is a figure which shows another example of the lens module which the focal position is variable. It is a block diagram which shows an example of the hardware composition of the image processing apparatus which concerns on embodiment. It is a figure which shows an example of the functional structure of an image processing apparatus. It is a figure which shows the image of the work W by the image pickup apparatus schematically. It is a figure which shows an example of the setting screen of an inspection area and a reliability evaluation area. It is a figure which shows another example of the setting screen of an inspection area and a reliability evaluation area. It is a figure which shows an example of the focusing degree waveform. It is a flowchart which shows an example of the flow of the inspection process of the inspection system which concerns on embodiment. It is a schematic diagram which shows the inspection system which concerns on modification 1. FIG. It is a figure which shows an example of the setting screen of an inspection area, a reliability evaluation area, and a model area. It is a figure explaining the process of a correction part. It is a flowchart which shows the flow of the inspection process of the inspection system which concerns on modification 1. It is a flowchart which shows the flow of the inspection process of the inspection system which concerns on modification 3. FIG.

Hereinafter, embodiments according to the present invention will be described with reference to the drawings. In the following description, the same parts and components are designated by the same reference numerals. Their names and functions are the same. Therefore, the detailed description of these will not be repeated.

§1 Application example First, an example of a situation in which the present invention is applied will be described with reference to FIGS. 1 and 2. FIG. 1 is a schematic diagram showing one application example of the inspection system according to the embodiment. FIG. 2 is a diagram showing an example of the internal configuration of the image pickup apparatus provided in the inspection system.

As shown in FIG. 1, the inspection system 1 according to the present embodiment is realized as, for example, a visual inspection system. The inspection system 1 takes an image of an inspection target portion on an object (work W) placed on the stage 90 in, for example, a production line of an industrial product, and uses the obtained image to inspect the appearance of the work W. I do. In the visual inspection, scratches, stains, the presence or absence of foreign matter, dimensions, etc. of the work W are inspected.

When the visual inspection of the work W placed on the stage 90 is completed, the next work (not shown) is conveyed onto the stage 90. When the work W is imaged, the work W may be stationary in a predetermined posture at a predetermined position on the stage 90. Alternatively, the work W may be imaged while the work W moves on the stage 90.

As shown in FIG. 1, the inspection system 1 includes an image pickup device 10 and an image processing device 20 as basic components. In this embodiment, the inspection system 1 further includes a PLC (Programmable Logic Controller) 30, an input device 40, and a display device 50.

The image pickup device 10 is connected to the image processing device 20. The image pickup apparatus 10 images a subject (work W) existing in the imaging field of view according to a command from the image processing apparatus 20, and generates image data including an image of the work W. The image pickup device 10 and the image processing device 20 may be integrated.

As shown in FIG. 2, the image pickup device 10 includes an illumination unit 11, a lens module 12, an image pickup element 13, an image pickup element control unit 14, a lens control unit 16, registers 15, 17, and communication I /. The F (interface) unit 18 is included.

The lighting unit 11 irradiates the work W with light. The light emitted from the illumination unit 11 is reflected on the surface of the work W and is incident on the lens module 12. The illumination unit 11 may be omitted.

The lens module 12 is an optical system for forming an image of light from the work W on the image pickup surface 13a of the image pickup element 13. The focal position of the lens module 12 is variable within a predetermined movable range. The focal position is the position of the point where the incident light ray parallel to the optical axis intersects the optical axis.

The lens module 12 includes a lens 12a, a lens group 12b, a lens 12c, a movable portion 12d, and a focus adjusting portion 12e. The lens 12a is a lens for changing the focal position of the lens module 12. The focus adjusting unit 12e controls the lens 12a to adjust the focal position of the lens module 12.

The lens group 12b is a lens group for changing the focal length. The zoom magnification is controlled by changing the focal length. The lens group 12b is installed in the movable portion 12d and moves along the optical axis direction. The lens 12c is a lens fixed at a predetermined position in the image pickup apparatus 10.

The lens control unit 16 controls the focus adjustment unit 12e so that the focus position is in accordance with the command stored in the register 17.

The lens control unit 16 may control the movable unit 12d to adjust the position of the lens group 12b so that the size of the region included in the imaging field of view of the work W is substantially constant. In other words, the lens control unit 16 can control the movable unit 12d so that the size of the region included in the imaging field of view of the work W is within a predetermined range. The lens control unit 16 may adjust the position of the lens group 12b according to the distance between the image pickup position and the work W. In this embodiment, the zoom adjustment is not essential.

The image pickup device 13 is a photoelectric conversion element such as a CMOS (Complementary Metal Oxide Semiconductor) image sensor, and generates an image signal by receiving light from the work W via the lens module 12.

The image sensor control unit 14 generates image data based on the image signal from the image sensor 13 when the focus position is adjusted by the focus adjustment unit 12e. At this time, the image sensor control unit 14 opens and closes the shutter so as to have a preset shutter speed (exposure time), and generates image data having a preset resolution. Information indicating the shutter speed and the resolution is stored in the register 15 in advance.

The communication I / F unit 18 transmits / receives data to / from the image processing device 20. The communication I / F unit 18 receives an image pickup instruction from the image processing device 20. The communication I / F unit 18 transmits the image data generated by the image sensor control unit 14 to the image processing device 20.

Returning to FIG. 1, the PLC 30 is connected to the image processing device 20 and controls the image processing device 20. For example, the PLC 30 controls the timing for the image processing device 20 to output an image pickup command (imaging trigger) to the image pickup device 10.

The input device 40 and the display device 50 are connected to the image processing device 20. The input device 40 receives user input regarding various settings of the inspection system 1. The display device 50 displays information regarding the settings of the inspection system 1, the result of image processing of the work W by the image processing device 20, and the like.

The image processing device 20 performs image processing on the image captured by the image pickup device 10. The image processing device 20 includes a setting unit 22, an inspection unit 25, and an evaluation unit 26.

The setting unit 22 sets the first region and the second region of the image indicated by the image data acquired from the image pickup apparatus 10 according to the input to the input device 40. The first area is an area (hereinafter referred to as “inspection area”) to be inspected by the inspection unit 25. The second area is an area used when evaluating the reliability of focusing on the inspection target portion of the work W (hereinafter, referred to as “reliability evaluation area”).

The inspection area is set according to the inspection target location. For example, when the work W is a glass substrate and it is desired to inspect the presence or absence of scratches near the center of the upper surface of the glass substrate, a region including the vicinity of the center of the upper surface is set as an inspection region.

Since the reliability evaluation area is used to evaluate the focus of the work W on the inspection target portion, a region having the same height as the inspection region at the inspection target portion of the work W and having high contrast is set. ..

The inspection unit 25 inspects the work W based on the inspection area in the inspection image indicated by the inspection image data received from the image pickup apparatus 10, and outputs the inspection result. Specifically, the inspection unit 25 inspects the work W by performing a process on the inspection area according to an inspection program registered in advance. The inspection unit 25 may perform the inspection using a known technique. If the inspection item is the presence or absence of scratches, the inspection result indicates "with scratches" or "without scratches". When the inspection item is a dimension, the inspection result indicates whether or not the measured value of the dimension is within a predetermined range.

The evaluation unit 26 evaluates the reliability of focusing on the inspection target portion of the work W based on the reliability evaluation area in the inspection image shown by the inspection image data, and outputs the evaluation result. Specifically, the evaluation unit 26 evaluates the reliability of focusing on the inspection target portion of the work W by performing processing according to the evaluation program registered in advance for the reliability evaluation area. For example, the evaluation unit 26 calculates an evaluation value that increases as the reliability increases, and outputs an evaluation result including the evaluation value.

As described above, the inspection system 1 according to the embodiment includes a lens module 12 having a variable focal position, an image pickup element 13 that generates an image by receiving light from the work W via the lens module 12, and a focal point. It is provided with a focus adjusting unit 12e for adjusting the position. Further, the inspection system 1 includes an inspection unit 25 and an evaluation unit 26. The inspection unit 25 inspects the work W based on the inspection area in the inspection image generated when the focus position is adjusted by the focus adjustment unit 12e, and outputs the inspection result. The evaluation unit 26 evaluates the reliability of focusing on the inspection target portion of the work W based on the reliability evaluation area in the inspection image, and outputs the evaluation result.

Thereby, by confirming the inspection result and the evaluation result, the risk of overlooking the defect of the work W can be reduced. For example, even if the inspection result indicates "no scratches", when an evaluation result indicating that the focusing reliability of the work W with respect to the inspection target portion is low is obtained, the operator shifts the focal position. It can be recognized that the inspection cannot be performed accurately due to the fact that the inspection is not possible. As a result, the worker can take appropriate measures such as re-inspection of the work W.

§2 Specific example <A. Configuration example for autofocus>
FIG. 3 is a schematic diagram for explaining autofocus. For simplicity of explanation, FIG. 3 shows only one lens of the lens module 12.

As shown in FIG. 3, the distance from the principal point O of the lens module 12 to the target surface (the surface of the work W) is defined as a, and the distance from the principal point O of the lens module 12 to the imaging surface 13a is defined as b. Let f be the distance (focal distance) from the principal point O of the 12 to the focal position (rear focal position) F of the lens module 12. When the image of the work W is formed at the position of the image pickup surface 13a, the following equation (1) is established.
1 / a + 1 / b = 1 / f ... (1)
That is, when the equation (1) holds, an image focused on the surface of the work W can be captured. “Focusing” means that an image of the work W is formed on the image pickup surface 13a (see FIG. 2) of the image pickup element 13.

The distance between the image pickup surface 13a and the surface of the work W may change depending on the height of the surface of the work W. Even when the distance between the image pickup surface 13a and the surface of the work W changes, the focal position F of the lens module 12 is adjusted in order to obtain an image focused on the surface of the work W. There are the following methods (A) and (B) as methods for adjusting the focal position F of the lens module 12.

The method (A) is a method of translating at least one lens (for example, the lens 12a) constituting the lens module 12 in the optical axis direction. According to the method (A), the principal point O of the lens module 12 moves in the optical axis direction, and the focal position F changes. As a result, the distance b changes. An image focused on the surface of the work W can be obtained at the focal position F corresponding to the distance b satisfying the equation (1).

The method (B) is a method of changing the refraction direction of the lens 12a fixed at a fixed position. According to the method (B), the focal position F changes as the focal length f of the lens module 12 changes. When the focal length F corresponds to the focal length f satisfying the equation (1), an image focused on the surface of the work W can be obtained.

The configuration of the lens 12a for changing the focal position F of the lens module 12 is not particularly limited. An example of the configuration of the lens 12a will be described below.

FIG. 4 is a diagram showing an example of a lens module having a variable focal position. In the example shown in FIG. 4, the lens 12a constituting the lens module 12 is translated. However, at least one lens (at least one lens of the lens 12a, the lens group 12b, and the lens 12c) constituting the lens module 12 may be translated.

By using the lens 12a having the configuration shown in FIG. 4, the focal position F of the lens module 12 changes according to the above method (A). That is, in the configuration shown in FIG. 4, the focus adjusting unit 12e moves the lens 12a along the optical axis direction. By moving the position of the lens 12a, the focal position F of the lens module 12 changes.

FIG. 4 shows an example of one lens 12a. Usually, the lens for focus adjustment is often composed of a plurality of sets of lenses. However, also in the assembled lens, the focal position F of the lens module 12 can be changed by controlling the amount of movement of at least one lens constituting the assembled lens.

FIG. 5 is a diagram showing another example of a lens module having a variable focal position. By using the lens 12a having the configuration shown in FIG. 5, the focal position F of the lens module 12 changes according to the above method (B).

The lens 12a shown in FIG. 5 is a liquid lens. The lens 12a includes a translucent container 70, electrodes 73a, 73b, 74a, 74b, insulators 75a, 75b, and insulating layers 76a, 76b.

The closed space in the translucent container 70 is filled with a conductive liquid 71 such as water and an insulating liquid 72 such as oil. The conductive liquid 71 and the insulating liquid 72 do not mix and have different refractive indexes from each other.

The electrodes 73a and 73b are fixed between the insulators 75a and 75b and the translucent container 70, respectively, and are located in the conductive liquid 71.

The electrodes 74a and 74b are arranged near the end of the interface between the conductive liquid 71 and the insulating liquid 72. An insulating layer 76a is interposed between the electrode 74a and the conductive liquid 71 and the insulating liquid 72. An insulating layer 76b is interposed between the electrode 74b and the conductive liquid 71 and the insulating liquid 72. The electrodes 74a and 74b are arranged at positions symmetrical with respect to the optical axis of the lens 12a.

In the configuration shown in FIG. 5, the focus adjusting unit 12e includes a voltage source 12e1 and a voltage source 12e2. The voltage source 12e1 applies a voltage Va between the electrodes 74a and 73a. The voltage source 12e2 applies a voltage Vb between the electrodes 74b and 73b.

When a voltage Va is applied between the electrode 74a and the electrode 73a, the conductive liquid 71 is pulled by the electrode 74a. Similarly, when a voltage Vb is applied between the electrode 74b and the electrode 73b, the conductive liquid 71 is pulled by the electrode 74b. As a result, the curvature of the interface between the conductive liquid 71 and the insulating liquid 72 changes. Since the refractive indexes of the conductive liquid 71 and the insulating liquid 72 are different, the focal position F of the lens module 12 changes due to the change in the curvature of the interface between the conductive liquid 71 and the insulating liquid 72.

The curvature of the interface between the conductive liquid 71 and the insulating liquid 72 depends on the magnitudes of the voltages Va and Vb. Therefore, the search unit 24 changes the focal position F of the lens module 12 by controlling the magnitudes of the voltages Va and Vb.

Normally, the voltage Va and the voltage Vb are controlled to the same value. As a result, the interface between the conductive liquid 71 and the insulating liquid 72 changes symmetrically with respect to the optical axis. However, the voltage Va and the voltage Vb may be controlled to different values. As a result, the interface between the conductive liquid 71 and the insulating liquid 72 becomes asymmetric with respect to the optical axis, and the direction of the image pickup field of view of the image pickup apparatus 10 can be changed.

Further, a liquid lens and a solid lens may be combined. In this case, the focal position F of the lens module 12 is changed by using both the above method (A) and the method (B).

<B. Image processing device hardware configuration>
FIG. 6 is a block diagram showing an example of the hardware configuration of the image processing apparatus according to the embodiment. The image processing device 20 of the example shown in FIG. 6 includes a CPU (Central Processing Unit) 210 which is an arithmetic processing unit, a main memory 232 and a hard disk 234 as a storage unit, a camera interface 216, an input interface 218, and a display controller. It includes 220, a PLC interface 222, a communication interface 224, and a data reader / writer 226. Each of these parts is connected to each other via bus 228 so as to be capable of data communication.

The CPU 210 expands the programs (codes) stored in the hard disk 234 into the main memory 232 and executes them in a predetermined order to perform various operations. The control program 236 includes an inspection program for inspecting the work W based on the inspection image and an evaluation program for evaluating the reliability of focusing on the work W.

The main memory 232 is typically a volatile storage device such as a DRAM (Dynamic Random Access Memory), and in addition to a program read from the hard disk 234, image data and work acquired by the image pickup device 10 Holds data etc. Further, various setting values and the like may be stored in the hard disk 234. In addition to the hard disk 234, or instead of the hard disk 234, a semiconductor storage device such as a flash memory may be adopted.

The camera interface 216 mediates data transmission between the CPU 210 and the image pickup device 10. That is, the camera interface 216 is connected to an image pickup device 10 for capturing an image of the work W and generating image data. More specifically, the camera interface 216 includes an image buffer 216a for temporarily storing image data from the image pickup apparatus 10. Then, when the image data of a predetermined number of frames is accumulated in the image buffer 216a, the camera interface 216 transfers the accumulated data to the main memory 232. Further, the camera interface 216 sends an image pickup command to the image pickup apparatus 10 according to an internal command generated by the CPU 210.

The input interface 218 mediates data transmission between the CPU 210 and the input device 40. That is, the input interface 218 receives an operation command given by the operator operating the input device 40.

The display controller 220 is connected to the display device 50 and notifies the user of the result of processing in the CPU 210 and the like. That is, the display controller 220 controls the screen of the display device 50.

The PLC interface 222 mediates data transmission between the CPU 210 and the PLC 30. More specifically, the PLC interface 222 transmits a control command from the PLC 30 to the CPU 210.

The communication interface 224 mediates data transmission between the CPU 210 and a console (or a personal computer or server device). The communication interface 224 typically comprises Ethernet (registered trademark), USB (Universal Serial Bus), or the like. As will be described later, instead of installing the program stored in the memory card 206 in the image processing device 20, the program downloaded from the distribution server or the like is installed in the image processing device 20 via the communication interface 224. You may.

The data reader / writer 226 mediates data transmission between the CPU 210 and the memory card 206, which is a recording medium. That is, the memory card 206 is distributed in a state in which a program or the like executed by the image processing device 20 is stored, and the data reader / writer 226 reads the program from the memory card 206. Further, the data reader / writer 226 writes the image data acquired by the image pickup apparatus 10 and / or the processing result in the image processing apparatus 20 to the memory card 206 in response to the internal command of the CPU 210. The memory card 206 is a general-purpose semiconductor storage device such as SD (Secure Digital), a magnetic storage medium such as a flexible disk, or an optical storage medium such as a CD-ROM (Compact Disk Read Only Memory). Etc.

<C. Functional configuration of image processing device>
An example of the functional configuration of the image processing apparatus 20 will be described with reference to FIG. 7. FIG. 7 is a diagram showing an example of the functional configuration of the image processing device. As shown in FIG. 7, the image processing device 20 includes a command generation unit 21, a setting unit 22, a calculation unit 23, a search unit 24, an inspection unit 25, an evaluation unit 26, and a determination unit 27. The output unit 28 and the storage unit 230 are included. The command generation unit 21, the setting unit 22, the calculation unit 23, the search unit 24, the inspection unit 25, the evaluation unit 26, and the determination unit 27 are realized by the CPU 210 shown in FIG. 6 executing the control program 236. The storage unit 230 is composed of the main memory 232 and the hard disk 234 shown in FIG. The output unit 28 is configured by the display controller 220 shown in FIG.

The command generation unit 21 receives a control command from the PLC 30 and outputs an image pickup command (imaging trigger) to the image pickup apparatus 10. The outline of the setting unit 22 is as described above.

The calculation unit 23 calculates the degree of focus from the image data generated by the image pickup apparatus 10. The degree of focus is a degree indicating how much the object is in focus, and is calculated by using various known methods. For example, the calculation unit 23 extracts high-frequency components by applying a high-pass filter to the image data, and calculates the integrated value of the extracted high-frequency components as the in-focus degree. Such a degree of focus indicates a value depending on the difference in brightness of the image.

The search unit 24 searches for a focusing position, which is a focal position for focusing on the work W. Specifically, the search unit 24 acquires the in-focus degree of each of the plurality of image data generated by changing the focal position of the lens module 12 from the calculation unit 23. The search unit 24 determines the focal position at which the acquired in-focus degree peaks as the in-focus position. The search unit 24 specifies the image data when the focal position of the lens module 12 is the in-focus position as the inspection image data. That is, the inspection image data is image data generated when the focus position is adjusted to the in-focus position by the focus adjustment unit 12e.

As a method for searching the in-focus position, there are a mountain climbing method and a full scan method, and either of them may be used.

In the hill climbing method, while changing the focal position of the lens module 12 within the set search range, the search ends when the focal position where the in-focus degree is maximized is found, and the focal point where the in-focus degree becomes maximum is found. This is a method of determining the position as the in-focus position. Specifically, in the hill climbing method, the direction of the focal position where the degree of focus increases is set as the search direction based on the magnitude relationship between the degree of focus at the focal position at the start of the search and the degree of focus at the adjacent focal position. decide. In addition, the hill climbing method sequentially calculates the difference between the degree of focus at the previous focal position and the degree of focus at the next focal position while changing the focal position in the search direction, and this difference is positive to zero or The focal position at the time of a negative change is determined as the in-focus position.

In the hill climbing method, the search unit 24 may specify the image data showing the maximum focus degree as the inspection image data.

In the full scan method, the focal position of the lens module 12 is changed over the entire set search range, the in-focus degree at each focal position is acquired, and the focal position where the in-focus degree is maximized is set as the in-focus position. How to decide. The full scan method also includes a method of performing a fine second search process after performing a coarse first search process. The first search process is a process of searching the focal position where the degree of focus is maximized by changing the focal position over the entire search range at coarse pitch intervals. The second search process is a process of changing the focal position at fine pitch intervals over the entire range including the focal position searched by the first search process, and searching for the focal position having the maximum focusing degree as the focusing position. Is.

In the full scan method, the search unit 24 stores the image data of each focal position, and from the stored image data, identifies the image data of the focal position having the maximum focusing degree as the inspection image data. do. Alternatively, the search unit 24 instructs the command generation unit 21 to adjust the focal position to the in-focus position and output a command for imaging, and in response to the command, the image data received from the image pickup device 10 is inspected image data. May be specified as.

The outline of the inspection unit 25 and the evaluation unit 26 is as described above. That is, the inspection unit 25 inspects the work W based on the inspection area in the inspection image indicated by the inspection image data specified by the search unit 24, and outputs the inspection result. The evaluation unit 26 evaluates the reliability of focusing on the inspection target portion of the work W based on the reliability evaluation area of the inspection image indicated by the inspection image data specified by the search unit 24, and evaluates the evaluation result. Output.

The determination unit 27 makes a comprehensive determination of the work W based on the inspection result output from the inspection unit 25 and the evaluation result output from the evaluation unit 26. The determination unit 27 works when the inspection result output from the inspection unit 25 satisfies the predetermined first criterion and the evaluation result output from the evaluation unit 26 satisfies the predetermined second criterion. It is determined that W is a good product.

The determination unit 27 determines that the work W is a defective product when the inspection result does not satisfy the first criterion and the evaluation result satisfies the second criterion. Further, the determination unit 27 determines that when the evaluation result does not satisfy the second criterion, there is a problem in the automatic adjustment of the focal position and the inspection cannot be performed accurately.

The output unit 28 outputs the determination result by the determination unit 27. For example, the output unit 28 causes the display device 50 to display the determination result. The output unit 28 may also display the inspection result and the evaluation result on the display device 50.

The storage unit 230 stores various data, programs, and the like. For example, the storage unit 230 stores the image data acquired from the image pickup apparatus 10 and the image data subjected to predetermined processing. The storage unit 230 may store the inspection result by the inspection unit 25, the evaluation result by the evaluation unit 26, and the determination result by the determination unit 27. Further, the storage unit 230 stores a program for causing the image processing device 20 to execute various processes.

<D. Work examples and autofocus issues>
FIG. 8 is a diagram schematically showing the imaging of the work W by the imaging device. In the example shown in FIG. 8, the work W has a region W1 and a region W2. The region W1 is, for example, the surface of a transparent body (glass, etc.). The region W2 is a region surrounding the region W1, for example, the surface of a housing of an electronic device. As an example of such a work W, an electronic device having a display (for example, a smartphone or a tablet) can be mentioned. That is, the area W1 can be a display screen. Also, the region W1 does not have a clear pattern. That is, the area W1 is a plain area.

When it is desired to inspect the inside of the area W1, the inspection area A1 is set in the area W1. The area including the inspection area A1 is imaged by the image pickup device 10, and the image of the inspection area A1 is the target of image processing by the image processing device 20. The image processing apparatus 20 inspects whether or not there are scratches, stains, or foreign substances in the inspection area A1 by using the image of the inspection area A1.

When the image is taken in a state where the inspection area A1 is not in focus, there is a possibility that scratches or the like in the inspection area A1 cannot be detected from the acquired image. In order to perform a highly accurate inspection, it is required to evaluate whether or not the image is in focus on the inspection region A1. However, as in the above example, when the inspection area A1 is a part of the plain area, a clear pattern is not formed in the inspection area A1. In such a case, since the contrast in the inspection area A1 is low, there is a problem that it is difficult to evaluate whether or not the image in the inspection area A1 is in focus only with the image of the inspection area A1.

<E. Setting of inspection area and reliability evaluation area>
According to the present embodiment, the setting unit 22 of the image processing apparatus 20 sets the reliability evaluation area together with the inspection area in advance for the work W.

The operator places the reference work W0 in a predetermined position on the stage 90 (see FIG. 1) in a predetermined posture. The image processing device 20 outputs an image pickup command to the image pickup device 10 and acquires reference image data from the image pickup device 10. The reference image data shows a reference image including the reference work W0 placed in a predetermined position in a predetermined posture.

The setting unit 22 of the image processing device 20 causes the display device 50 to display the reference image indicated by the reference image data acquired from the image pickup device 10, and prompts the operator to specify the inspection area and the reliability evaluation area.

FIG. 9 is a diagram showing an example of a setting screen of an inspection area and a reliability evaluation area. As shown in FIG. 9, the setting unit 22 causes the screen of the display device 50 to display the reference image 80 indicated by the reference image data acquired from the image pickup device 10.

The setting unit 22 sets the inspection area A1 and the reliability evaluation area B1 according to the input to the input device 40. For example, the operator inputs four vertices of each of the rectangular inspection area A1 and the reliability evaluation area B1. The operator designates a region having the same height as the inspection region A1 in the reference work W0 and including a portion having a high contrast as the reliability evaluation region B1. In the example shown in FIG. 9, the area including the edge portion of the reference work W0 is designated as the reliability evaluation area B1. In addition to the edge portion, the high-contrast portion includes characters printed on the surface, a pattern formed on the surface, and a portion to which parts such as screws are attached.

In the example shown in FIG. 9, a rectangular inspection area A1 and a reliability evaluation area B1 are set, but the shape of each area is not limited to this. For example, the shape of at least one of the inspection region A1 and the reliability evaluation region B1 may be circular or any free shape capable of forming the region. Further, at least one of the inspection area A1 and the reliability evaluation area B1 need not be limited to a single area. For example, at least one of the inspection area A1 and the reliability evaluation area B1 may be a plurality of dispersed areas.

FIG. 10 is a diagram showing another example of the setting screen of the inspection area and the reliability evaluation area. In the example shown in FIG. 10, a frame-shaped reliability evaluation region B1 is set along the edge portion of the reference work W0.

The setting unit 22 generates information for specifying each of the set inspection area A1 and the reliability evaluation area B1, and stores the generated information in the storage unit 230.

<F. Evaluation method>
Next, a reliability evaluation method by the evaluation unit 26 will be described. The evaluation unit 26 calculates an evaluation value indicating the reliability of focusing on the inspection target portion of the work W based on the focusing degree of the reliability evaluation region B1 in the inspection image shown by the inspection image data. The in-focus degree is, for example, an integrated value of high-frequency components extracted from the image of the reliability evaluation region B1.

For example, the evaluation unit 26 calculates the ratio (= c / d) of the in-focus degree c calculated from the reliability evaluation region B1 of the inspection image to the predetermined reference in-focus degree d as an evaluation value. In this case, the larger the evaluation value, the higher the reliability of focusing on the inspection target portion of the work W. The reference in-focus degree is, for example, the in-focus degree calculated from the reliability evaluation region B1 in the image focused on the inspection target portion of the reference work W0, and is calculated in advance by an experiment.

Alternatively, when the search unit 24 searches for the in-focus position according to the full scan method, the evaluation unit 26 uses the in-focus degree g of the first peak and the second in-focus degree g of the in-focus degree waveform obtained in the in-focus position search process. The ratio (= g / h) of the peak to the in-focus degree h may be calculated as an evaluation value. The in-focus waveform is a waveform showing a change in the in-focus degree with respect to the focal position when the focal position of the lens module 12 is changed. The first peak is the peak with the highest degree of focus. The second peak is the peak with the second highest degree of focus.

FIG. 11 is a diagram showing an example of a focus waveform. The focus waveform of the example shown in FIG. 11 includes two peaks at the focal positions F1 and F2. The focal position F1 is the focal position when focusing on the inspection target portion of the work W. Therefore, when the autofocus process is normally performed, the focus waveform includes only one peak at the focal position F1. However, for some reason, a peak may occur at a focal position other than the focal position F1. For example, when a sheet having a high-contrast pattern is reflected in the inspection image, a peak occurs at a focal position different from the focal position F1.

When the in-focus degree waveform of the example shown in FIG. 11 is obtained, the focal position F2 different from the focal position F1 is erroneously determined as the in-focus position, and the image data when adjusted to the focal position F2 is the inspection image data. Can be identified as.

Therefore, the evaluation unit 26 acquires the in-focus degree calculated from the reliability evaluation region B1 of the inspection image as the in-focus degree g of the first peak. Further, the evaluation unit 26 acquires the in-focus degree of the second peak having the second largest in-focus degree as the in-focus degree h of the second peak. The evaluation unit 26 calculates an evaluation value (= g / h) based on the degree of focus g and h.

In the above example, the higher the reliability of focusing on the inspection target portion of the work W, the larger the evaluation value is calculated. However, the evaluation unit 26 may calculate an evaluation value that becomes smaller as the reliability of focusing on the inspection target portion of the work W becomes higher.

In addition, the evaluation unit 26 may calculate the evaluation value using a known technique. For example, the evaluation unit 26 describes the techniques described in International Publication No. 17/056557 (Patent Document 2), Japanese Patent Application Laid-Open No. 2010-78681 (Patent Document 3), and Japanese Patent Application Laid-Open No. 10-170817 (Patent Document 4). It may be used to calculate the evaluation value.

<G. Comprehensive judgment method>
As described above, the determination unit 27 of the image processing apparatus 20 satisfies the case where the inspection result satisfies the predetermined first criterion and the evaluation result output from the evaluation unit 26 satisfies the predetermined second criterion. In addition, it is determined that the work W is a good product. For example, when the inspection item is the presence or absence of scratches, the first criterion indicates that the inspection result is "no scratches". When the inspection item is a dimension, the first criterion indicates that the measured value of the dimension is within a predetermined range. Further, when the evaluation result includes an evaluation value that increases as the reliability of focusing on the inspection target portion of the work W increases, the second criterion indicates that the evaluation value exceeds a predetermined threshold value.

The first reference and the second reference are created in advance and stored in the storage unit 230. The determination unit 27 reads out the first reference and the second reference from the storage unit 230, and makes a comprehensive determination.

<H. Inspection flow>
Next, with reference to FIG. 12, the flow of the inspection process according to the present embodiment will be described. FIG. 12 is a flowchart showing an example of the flow of the inspection process of the inspection system according to the embodiment. Prior to the inspection method shown in FIG. 12, the setting unit 22 of the image processing apparatus 20 sets the inspection area A1 and the reliability evaluation area B1 by using the image data including the reference work W0.

Each time the work W to be inspected is conveyed to the stage 90 (see FIG. 1) by a transfer device (not shown), the inspection process shown in FIG. 12 is executed. In the present embodiment, the work W is placed in a predetermined position on the stage 90 in a predetermined posture by the transport device.

First, the image pickup apparatus 10 and the image processing apparatus 20 execute the in-focus position search process (step S1). In step S1, the lens control unit 16 of the image pickup apparatus 10 changes the focal position of the lens module 12 within the search range. The calculation unit 23 of the image processing device 20 calculates the in-focus degree of the entire region for each of the plurality of image data generated by changing the focal position. The search unit 24 of the image processing device 20 searches for the focal position where the calculated degree of focus peaks as the focus position.

Next, the search unit 24 identifies the image data when the focal position of the lens module 12 is adjusted to the in-focus position as inspection image data (step S2).

Next, the inspection unit 25 of the image processing apparatus 20 inspects the work W based on the inspection area A1 in the inspection image shown by the inspection image data, and outputs the inspection result (step S3).

Further, the evaluation unit 26 of the image processing apparatus 20 calculates an evaluation value indicating the reliability of focusing on the inspection target portion of the work W based on the reliability evaluation area B1 of the inspection image, and the calculated evaluation value. The evaluation result including is output (step S4). The processing order of steps S3 and S4 is not limited to this, and step S3 may be executed after step S4, or step S3 and step S4 may be executed in parallel.

Next, the determination unit 27 of the image processing device 20 makes a comprehensive determination based on the inspection result and the evaluation result (step S5). After that, the output unit 28 causes the display device 50 to display the determination result (step S6). After step S6, the inspection process ends.

The determination result may be output to the PLC 30 in addition to the display device 50 and used for controlling other devices. For example, when the determination result indicates that the work W is a non-defective product, the transport device (not shown) transports the work W on a transport path for transporting the work W to the next process. If the determination result indicates that the work W is a defective product, the transport device transports the work W to the defective product storage area. If the determination result indicates that the inspection has not been performed with high accuracy, the transport device transports the work W to the re-inspected product storage area.

§3 Modification example <Modification example 1>
In the above description, the work W to be inspected is placed in a predetermined position on the stage 90 in a predetermined posture by a transfer device (not shown). However, if the transport accuracy of the transport device is low, the position and orientation of the work W included in the inspection image may fluctuate. Therefore, the image processing apparatus of the inspection system according to the first modification has the inspection area A1 and the reliability evaluation for the inspection image based on the deviation of the position and orientation of the work W in the inspection image with respect to the position and orientation of the reference work in the reference image. Correct the relative position and orientation of the area B1. As a result, even if the position and orientation of the work W included in the inspection image fluctuates, it is possible to suppress a decrease in inspection accuracy and reliability evaluation accuracy.

FIG. 13 is a schematic diagram showing an inspection system according to the first modification. The inspection system 1A according to the first modification is different from the inspection system 1 shown in FIG. 1 in that the image processing device 20A is provided instead of the image processing device 20. The image processing device 20A is different from the image processing device 20 shown in FIG. 1 in that the setting unit 22A is provided instead of the setting unit 22 and the correction unit 29 is further provided.

The setting unit 22A sets the inspection area A1 and the reliability evaluation area B1 from the reference image in the same manner as the setting unit 22 described above. Further, the setting unit 22A sets a model area from the reference image, and the model area is an area including a characteristic portion of the reference work W0 placed at a predetermined position in a predetermined posture. The characteristic portion is a portion where the position and orientation of the reference work W0 can be specified.

FIG. 14 is a diagram showing an example of a setting screen of an inspection area, a reliability evaluation area, and a model area. In the example shown in FIG. 14, in the reference image 80, the regions including each of the two corners of the reference work W0 having a rectangular shape in a plan view and not adjacent to each other are set as the model regions C1 and C2. The setting unit 22A stores in the storage unit 230 each image of the set model areas C1 and C2 and information indicating the position and orientation of the model areas C1 and C2 in the reference image.

Next, the processing of the correction unit 29 will be described with reference to FIG. FIG. 15 is a diagram illustrating the processing of the correction unit.

The correction unit 29 searches the inspection image 81 for the same partial image as the image of the model areas C1 and C2 in the reference image 80 by using a known template matching method. The correction unit 29 reads out the images of the model areas C1 and C2 from the storage unit 230 as first and second template images, respectively. The correction unit 29 searches the inspection image 81 for the first partial image D1 having the same pattern as the first template image corresponding to the model area C1, and the second portion of the same pattern as the second template image corresponding to the model area C2. The image D2 is searched from the inspection image 81.

Specifically, the correction unit 29 performs a correlation calculation between the first template image and the inspection image 81 while changing the position and orientation of the first template image, and the first template having the highest degree of similarity indicated by the correlation value. Search for the position and orientation of the image. Then, the correction unit 29 specifies the image of the region overlapping with the first template image of the searched position / posture as the first partial image D1. Similarly, by the method, the correction unit 29 specifies the image of the region overlapping with the second template image of the position and orientation having the highest degree of similarity indicated by the correlation value as the second partial image D2.

As the correlation value, known SSD (Sum of Squared Difference), SAD (Sum of Absolute Difference), NCC (Normalized Cross-Correlation) and the like can be used. When SSD or SAD is used as the correlation value, the correction unit 29 may search for the position and orientation of the template image that minimizes the correlation value. When NCC is used as the correlation value, the correction unit 29 may search for the position and orientation of the template image whose correlation value is closest to 1.

The correction unit 29 compares the position and orientation of the searched partial images D1 and D2 with the positions and orientations of the model areas C1 and C2, respectively, so that the position and orientation of the reference work W0 in the reference image 80 (hereinafter, “reference position”). The deviation of the position and orientation of the work W in the inspection image 81 with respect to (referred to as "posture") is obtained (calculated). The deviation indicates the deviation amounts ΔX, ΔY and Δθ in the X direction, the Y direction and the rotation direction (θ direction), respectively.

The correction unit 29 corrects the relative position / orientation of the inspection area A1 and the reliability evaluation area B1 with respect to the inspection image 81 based on the calculated deviation. That is, the correction unit 29 corrects the position and orientation of the inspection area A1 and the reliability evaluation area B1 by the calculated deviation. Specifically, with the inspection image 81 fixed, the correction unit 29 translates the inspection area A1 and the reliability evaluation area B1 by ΔX in the X direction, translates by ΔY in the Y direction, and Δθ. Rotate and move only.

The correction unit 29 may correct the position and orientation of the inspection image 81 while keeping the inspection area A1 and the reliability evaluation area B1 fixed. In this case, the correction unit 29 may perform the conversion opposite to the conversion of the position and orientation of the inspection area A1 and the reliability evaluation area B1 with respect to the position and orientation of the inspection image 81.

FIG. 16 is a flowchart showing a flow of inspection processing of the inspection system according to the first modification. The flowchart shown in FIG. 16 is different from the flowchart shown in FIG. 12 in that steps S11 and S12 are further included.

When the inspection image data is acquired from the image pickup apparatus 10 (step S2), in step S11, the correction unit 29 of the image processing apparatus 20A calculates the deviation of the position / orientation of the work W in the inspection image 81 with respect to the reference position / orientation.

Next, in step S12, the correction unit 29 corrects the relative position / orientation of the inspection area A1 and the reliability evaluation area B1 with respect to the inspection image 81 based on the calculated deviation. After that, the inspection of the work W is executed using the corrected inspection area A1 (step S3), and the reliability evaluation is executed using the corrected reliability evaluation area B1 (step S4).

In the above description, the model areas C1 and C2 and the reliability evaluation area B1 are set separately. However, the same area as the reliability evaluation area B1 may be set as the model area. That is, the reliability evaluation area B1 may be shared as a model area.

<Modification 2>
The inspection system according to the modification 2 is a further modification of the inspection system according to the modification 1. In the inspection system according to the second modification, the determination unit 27 performs the following processing.

The determination unit 27 works when the inspection result satisfies the first criterion, the evaluation result satisfies the second criterion, and the correlation value calculated by the correction unit 29 satisfies the predetermined third criterion. It is determined that W is a good product. When the correlation value calculated by the correction unit 29 does not satisfy the third criterion, the determination unit 27 determines that the work W cannot be imaged normally.

The correlation value calculated by the correction unit 29 indicates the degree of similarity between the template images of the model areas C1 and C2 and the partial images D1 and D2 searched from the inspection image. If the similarity indicated by the correlation value is low, it is highly possible that the work W to be inspected cannot be imaged normally for some reason. For example, there is a case where the work W does not fit in the image because the position of the work W is greatly deviated from the predetermined position on the stage 90.

The third criterion is, for example, that the similarity indicated by the correlation value between the template image of the model regions C1 and C2 and the partial images D1 and D2 is higher than the predetermined similarity. For example, if the higher the similarity, the smaller the correlation value, the third criterion indicates that the correlation value is below a predetermined threshold.

According to the second modification, it is possible to further reduce the risk of overlooking a defective work W as a good product even though the work W cannot be imaged normally.

<Modification 3>
The inspection system according to the modification 3 is a further modification of the inspection system according to the modification 1. In the inspection system according to the third modification, the autofocus process is executed using the reliability evaluation area B1 corrected by the correction unit 29.

FIG. 17 is a flowchart showing the flow of the inspection process of the inspection system according to the modified example 3. The flowchart shown in FIG. 17 is different from the flowchart shown in FIG. 16 in that steps S21 to S23 are included instead of steps S2, S11 and S12, and steps S24 and S25 are further included.

After step S1, the search unit 24 of the image processing apparatus 20 identifies the image data when the focal position of the lens module 12 is adjusted to the in-focus position in step S21 as the correction image data.

Next, the correction unit 29 calculates the deviation of the position / orientation of the work W in the correction image indicated by the correction image data with respect to the reference position / orientation (step S22). The correction unit 29 corrects the relative position / orientation of the inspection area A1 and the reliability evaluation area B1 with respect to the correction image based on the calculated deviation (step S23). Specifically, the correction unit 29 corrects the position and orientation of the inspection area A1 and the reliability evaluation area B1 while keeping the correction image fixed, as in the modification 1. Alternatively, the correction unit 29 may correct the position and orientation of the correction image while keeping the inspection area A1 and the reliability evaluation area B1 fixed.

Next, the image processing device 20 executes a search process for the in-focus position based on the corrected reliability evaluation region B1 (step S24). Specifically, the calculation unit 23 calculates the in-focus degree of each of the reliability evaluation regions B1 of the plurality of image data. The search unit 24 determines the focal position at which the calculated in-focus degree peaks as the in-focus position.

Next, the search unit 24 identifies the image data generated at the searched focus position as inspection image data (step S25). After that, the inspection of the work W is executed using the corrected inspection area A1 in the inspection image shown by the inspection image data (step S3), and the reliability is evaluated using the corrected reliability evaluation area B1. Is executed (step S4).

According to the third modification, the in-focus position search process is executed again based on the corrected reliability evaluation region B1, and the inspection image data is generated. Therefore, it becomes easy to obtain the inspection image data focused on the inspection target portion.

<Other variants>
In the above description, the output unit 28 outputs the determination result by the determination unit 27. However, the inspection system does not include the determination unit 27, and the output unit 28 may output the inspection result by the inspection unit 25 and the evaluation result by the evaluation unit 26. By checking the evaluation result, the operator can also recognize that there is some problem in adjusting the focal position and the inspection cannot be performed accurately. As a result, it is possible to reduce the risk of overlooking a defective work W as a good product by performing an inspection based on an image focused on a portion different from the inspection target portion of the work W.

In the above description, the search unit 24 searches for a focusing position to be focused on the work W based on a plurality of image data generated by changing the focal position of the lens module 12. However, the image pickup apparatus 10 may include a distance measuring sensor for measuring the distance to the work W, and the search unit 24 may search for the in-focus position based on the measurement result of the distance measuring sensor. The distance measuring sensor, for example, has a distance a from the lens module 12 to the work W based on the time from when infrared rays or ultrasonic waves are emitted toward the work W to when it is reflected by the work W and returned (FIG. 3). See). The search unit 24 may determine the focal position F in which the measured distance a satisfies the above equation (1) as the in-focus position. However, in this case, since a distance measuring sensor is required, the number of parts of the image pickup apparatus 10 increases. In order to suppress an increase in the number of parts of the image pickup apparatus 10, it is preferable that the search unit 24 searches for the in-focus position based on a plurality of image data generated by changing the focal position of the lens module 12.

In the above description, the image pickup apparatus 10 outputs a plurality of image data by changing the focal position. Then, the image processing device 20 searches for a focusing position that focuses on the inspection target portion of the work W from a plurality of focal positions. However, the lens control unit 16 of the image pickup apparatus 10 may control the focal position of the lens module 12 so as to be a predetermined fixed position according to the type of the work W and the inspection target location. That is, the focus adjusting unit 12e adjusts the focal position of the lens module 12 to a predetermined fixed position. In this case, the image processing device 20 does not have to include the search unit 24.

Even if the focal position of the lens module 12 is adjusted to a predetermined fixed position, the image pickup device 10 and the work W may be affected by individual differences in the size of the work W or the state of the transport device that conveys the work W. The distance to the inspection target fluctuates. Therefore, it is not always possible to obtain an inspection image focused on the inspection target portion of the work W. In such a case, by providing the evaluation unit 26 in the image processing device 20, it becomes possible to recognize that the inspection cannot be performed accurately due to the deviation of the focal position.

§4 Addendum As described above, the embodiments and modifications include the following disclosures.

(Structure 1)
An optical system (12) with a variable focal position and
An image pickup device (13) that generates an image by receiving light from an object (W) via the optical system (12), and an image pickup device (13).
The focus adjustment unit (12e) for adjusting the focus position and
The inspection unit (25) inspects the object (W) based on the first region of the inspection image generated when the focus position is adjusted by the focus adjustment unit (12e), and outputs the inspection result. , 210),
An inspection system (1) including an evaluation unit (26,210) that evaluates the reliability of focusing on the inspection target portion of the object based on the second region of the inspection image and outputs the evaluation result. , 1A).

(Structure 2)
The first region and the second region with respect to the inspection image based on the deviation of the position and orientation of the object (W) in the inspection image with respect to the position and orientation of the object (W) in the reference image generated in advance. The inspection system (1A) according to configuration 1, further comprising a correction unit (29,210) for correcting the relative position / orientation of the region.

(Structure 3)
A determination unit (27,210) for determining that the object is a non-defective product when the inspection result satisfies the predetermined first criterion and the evaluation result satisfies the predetermined second criterion. The inspection system (1, 1A) according to configuration 1 or 2, further comprising.

(Structure 4)
The correction unit (29,210) obtains the deviation based on the correlation value obtained by the correlation calculation between the reference image and the inspection image.
The inspection system (1A) further comprises
The subject when the inspection result satisfies a predetermined first criterion, the evaluation result satisfies a predetermined second criterion, and the correlation value satisfies a predetermined third criterion. The inspection system (1A) according to configuration 2, further comprising a determination unit (27, 210) for determining that the product is a non-defective product.

(Structure 5)
The inspection system (1, 1A) according to any one of configurations 1 to 4, wherein the evaluation result includes an evaluation value calculated based on the degree of focus in the second region of the inspection image.

(Structure 6)
Further, a search unit (24) for searching the in-focus position, which is the focal position for focusing on the object (W), is further provided.
The inspection system (1, 1A) according to any one of configurations 1 to 5, wherein the inspection image is generated when the focus position is adjusted to the in-focus position by the focus adjustment unit (12e).

(Structure 7)
An optical system (12) with a variable focal position and
An image pickup device (13) that generates an image by receiving light from an object (W) via the optical system (12), and an image pickup device (13).
An inspection method in an inspection system including a focus adjustment unit (12e) for adjusting the focus position.
A step of inspecting the object (W) based on the first region of the inspection image generated when the focus position is adjusted by the focus adjustment unit (12e) and outputting the inspection result.
An inspection method comprising a step of evaluating the reliability of focusing on an inspection target portion of the object based on a second region of the inspection image and outputting an evaluation result.

(Structure 8)
An optical system (12) with a variable focal position and
An image pickup device (13) that generates an image by receiving light from an object (W) via the optical system (12), and an image pickup device (13).
A program for causing a computer to execute an inspection method in an inspection system including a focus adjustment unit (12e) for adjusting the focus position.
The inspection method is
A step of inspecting the object (W) based on the first region of the inspection image generated when the focus position is adjusted by the focus adjustment unit (12e) and outputting the inspection result.
A program including a step of evaluating the reliability of focusing on the inspection target portion of the object based on the second region of the inspection image and outputting the evaluation result.

Although embodiments of the present invention have been described, it should be considered that the embodiments disclosed this time are exemplary in all respects and not restrictive. The scope of the present invention is indicated by the scope of claims and is intended to include all modifications within the meaning and scope equivalent to the scope of claims.

1,1A inspection system, 10 image pickup device, 11 lighting unit, 12 lens module, 12a, 12c lens, 12b lens group, 12d movable part, 12e1, 12e2 voltage source, 12e focus adjustment unit, 13 image pickup element, 13a image pickup surface, 14 Image sensor control unit, 15,17 register, 16 lens control unit, 18 communication I / F unit, 20,20A image processing device, 21 command generation unit, 22,22A setting unit, 23 calculation unit, 24 search unit, 25 Inspection unit, 26 evaluation unit, 27 judgment unit, 28 output unit, 29 correction unit, 30 PLC, 40 input device, 50 display device, 70 translucent container, 71 conductive liquid, 72 insulating liquid, 73a, 73b, 74a, 74b Electrode, 75a, 75b Insulation, 76a, 76b Insulation Layer, 80 Reference Image, 81 Inspection Image, 90 Stage, 206 Memory Card, 216 Camera Interface, 216a Image Buffer, 218 Input Interface, 220 Display Controller, 222 PLC Interface, 224 communication interface, 226 data reader / writer, 228 bus, 230 storage, 232 main memory, 234 hard disk, 236 control program, A1 inspection area, B1 reliability evaluation area, C1, C2 model area, D1 first part Image, D2 second partial image, W work, W0 reference work.

Claims (7)

An optical system with a variable focal position and
An image sensor that generates an image by receiving light from an object via the optical system,
The focus adjustment unit that adjusts the focus position and
An inspection unit that inspects the object based on the first region of the inspection image generated when the focus position is adjusted by the focus adjustment unit and outputs an inspection result.
An evaluation unit that evaluates the reliability of focusing on the inspection target portion of the object based on the second region of the inspection image and outputs the evaluation result .
Based on the deviation of the position and orientation of the object in the inspection image with respect to the position and orientation of the object in the reference image generated in advance, the relative position and orientation of the first region and the second region with respect to the inspection image are determined. An inspection system equipped with a correction unit for correction . A claim further comprising a determination unit for determining that the object is a non-defective product when the inspection result satisfies a predetermined first criterion and the evaluation result satisfies a predetermined second criterion. The inspection system according to 1 . The correction unit obtains the deviation based on the correlation value obtained by the correlation calculation between the reference image and the inspection image.
The inspection system further
The subject when the inspection result satisfies a predetermined first criterion, the evaluation result satisfies a predetermined second criterion, and the correlation value satisfies a predetermined third criterion. The inspection system according to claim 1 , further comprising a determination unit for determining that the product is a non-defective product. The inspection system according to any one of claims 1 to 3 , wherein the evaluation result includes an evaluation value calculated based on the degree of focus in the second region of the inspection image. Further, a search unit for searching the in-focus position, which is the focal position in which the object is in focus, is provided.
The inspection system according to any one of claims 1 to 4 , wherein the inspection image is generated when the focus position is adjusted to the in-focus position by the focus adjustment unit. An optical system with a variable focal position and
An image sensor that generates an image by receiving light from an object via the optical system,
It is an inspection method in an inspection system provided with a focus adjustment unit for adjusting the focus position.
A step of inspecting the object based on the first region of the inspection image generated when the focus position is adjusted by the focus adjustment unit and outputting the inspection result.
A step of evaluating the reliability of focusing on the inspection target portion of the object based on the second region of the inspection image and outputting the evaluation result.
Based on the deviation of the position and orientation of the object in the inspection image with respect to the position and orientation of the object in the reference image generated in advance, the relative position and orientation of the first region and the second region with respect to the inspection image are determined. An inspection method with a step to correct . An optical system with a variable focal position and
An image sensor that generates an image by receiving light from an object via the optical system,
A program for causing a computer to execute an inspection method in an inspection system provided with a focus adjustment unit for adjusting the focus position.
The inspection method is
A step of inspecting the object based on the first region of the inspection image generated when the focus position is adjusted by the focus adjustment unit and outputting the inspection result.
A step of evaluating the reliability of focusing on the inspection target portion of the object based on the second region of the inspection image and outputting the evaluation result.
Based on the deviation of the position and orientation of the object in the inspection image with respect to the position and orientation of the object in the reference image generated in advance, the relative position and orientation of the first region and the second region with respect to the inspection image are determined. A program with steps to correct .

Images