Image inspection apparatus, control unit for the same, image inspection method, image inspection program, computer-readable recording medium, and recorded device

Abstract

To easily capture an image for inspection.SOLUTION: An image inspection apparatus 100 includes: an image score calculation unit 22 which calculates image scores of work images generated in different image generation conditions; and an image generation condition setting unit 23 which receives, while thumbnail images corresponding to the work images having higher image score are displayed on a display unit 4, a selection of one thumbnail image, to receive settings for image generation condition corresponding to the selected thumbnail image. The image generation conditions include a single condition of generating an image captured in a single image generation condition and a composition condition of generating a composite image from images captured in different image generation conditions. The display unit 4 includes a reference information display column 205 for displaying reference information to identify whether each of the thumbnail images having higher image scores has been generated in the single condition or the composition condition when displaying the thumbnail images.SELECTED DRAWING: Figure 4

Description

[Technical field]

[0001] The present invention relates to an image inspection apparatus, a control unit for an image inspection apparatus, an image inspection method, an image inspection program, a computer-readable recording medium, and an apparatus having the program recorded thereon. [Background technology]

[0002] Image inspection devices such as image sensors are used to capture images of inspection objects such as workpieces and judge the quality of the inspection objects based on the captured images. Image inspections performed with such image inspection devices are generally performed by registering a master image and setting various image inspection tools on the registered master image.

[0003] When there are a wide variety of combinations of imaging conditions for image sensors such as lighting and cameras, it is difficult for users to empirically find optimal imaging conditions. In response to this, there is known an image inspection device that determines optimal imaging conditions by changing various imaging conditions and evaluating images (for example, Patent Document 1).

[0004] However, since the image suitable for the inspection varies depending on the inspection content that the user wants to perform, it has been difficult for the image inspection device to automatically determine the optimal imaging conditions. For example, if you want to inspect the shape of the workpiece to be inspected, an image in which the edges related to the shape are displayed sharply will generally be the optimal image, but on the other hand, if you want to inspect the color of the workpiece to be inspected, an image in which the color differences are clear will generally be the optimal image. Also, if you want to inspect from various perspectives, an image in which various feature quantities are displayed in a balanced manner will be the optimal image.

[0005] Furthermore, to optimize an image for inspection, it may be necessary to combine multiple images. For example, HDR processing, which combines multiple images captured with different exposure times to expand the dynamic range, and processing that combines images illuminated from multiple different directions, are examples of such processing. However, in order to improve image quality through these processes, the tact time is worsened by capturing multiple images. For a user, the truly optimal image must be selected by considering not only the image quality but also the tact time required to obtain the image. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] JP 2017-223458 A Summary of the Invention [Problem to be solved by the invention]

[0007] An object of the present invention is to provide an image inspection device, a control unit for the image inspection device, an image inspection method, an image inspection program, a computer-readable recording medium, and a device having the same, which are capable of easily capturing an image for inspection.

[0008] According to an image inspection device according to one aspect of the present invention, there is provided an illumination unit which irradiates an object to be inspected with illumination light, a camera unit which receives light irradiated from the illumination unit and reflected by the object to be inspected and generates a workpiece image, a display unit which displays the workpiece image generated by the camera unit, an image generation condition control unit which controls the camera unit so as to generate a plurality of workpiece images by changing the image generation conditions when generating the workpiece image to a plurality of different conditions, an image score calculation unit which calculates an image score, which is an evaluation value of each of the plurality of workpiece images, based on a plurality of feature amounts which characterize each of the workpiece images, for the plurality of workpiece images generated under different image generation conditions by the image generation condition control unit, and a thumbnail display unit which displays thumbnails corresponding to the plurality of workpiece images having a high image score. and an image generation condition setting unit that accepts the selection of one thumbnail image from among the plurality of thumbnail images while displaying the thumbnail image on the display unit, and accepts settings of image generation conditions corresponding to the selected thumbnail image, wherein the plurality of image generation conditions include a single condition for generating an image captured under a single image generation condition and a synthesis condition for synthesizing images captured under a plurality of different image generation conditions, and the display unit has a reference information display field that displays reference information for identifying whether each thumbnail image was generated under the single condition or the synthesis condition when displaying the plurality of thumbnail images having the top image scores. With the above configuration, when a user is prompted to select a desired image from the plurality of thumbnail images, the reference information as well as the image score can be taken into consideration, making it easier to select an appropriate image, and therefore image generation conditions for generating an image can be easily set.

[0009] In addition, according to another embodiment of the image inspection device of the present invention, there is provided an image inspection device comprising: an illumination unit that irradiates an object to be inspected with illumination light; a camera unit that receives light reflected from the object to be inspected and generates a work image; an image score calculation unit that controls the camera unit so as to change the image generation conditions when generating the work image to a plurality of different conditions, and calculates an image score, which is an evaluation value of each of the generated work images, based on a plurality of feature amounts that characterize each work image; a display unit that displays a plurality of thumbnail images corresponding to the work images having the highest image scores among the plurality of work images based on the image scores calculated by the image score calculation unit; and an image generation condition setting unit that accepts settings of inspection conditions corresponding to a thumbnail image selected from the plurality of thumbnail images, wherein the image score calculation unit is configured to calculate the image scores of the work images for each feature amount for a plurality of different feature amounts, and to determine the plurality of thumbnail images based on the plurality of image scores.

[0010] Furthermore, according to another aspect of the present invention, there is provided an image inspection device comprising: an illumination unit which irradiates an object to be inspected with illumination light; a camera unit which receives light irradiated from the illumination unit and reflected by the object to be inspected and generates a workpiece image; a display unit which displays the workpiece image generated by the camera unit; and a processor unit which controls the camera unit so as to generate a plurality of workpiece images by changing image generation conditions when generating the workpiece images to a plurality of different conditions, calculates an image score, which is an evaluation value of each of the plurality of workpiece images generated under the different image generation conditions, based on a plurality of feature amounts which characterize each of the workpiece images, displays thumbnail images corresponding to the plurality of workpiece images having a high image score on the display unit, and accepts selection of one thumbnail image from the plurality of thumbnail images displayed on the display unit, thereby accepting setting of the image generation condition corresponding to the selected thumbnail image, wherein the plurality of image generation conditions include a single condition for generating an image captured under a single image generation condition, and a synthesis condition for synthesizing images captured under a plurality of different image generation conditions. and the display unit has a reference information display field for displaying reference information for identifying whether each thumbnail image was generated under the single condition or the composite condition when displaying the plurality of thumbnail images having the top image scores. With the above configuration, when a user is prompted to select a desired image from a plurality of thumbnail images, the image score and the reference information are taken into consideration, making it easier to select an appropriate image, and therefore image generation conditions for generating an image can be easily set.

[0011] Furthermore, according to a control unit for an image inspection device according to another aspect of the present invention, the control unit is connected to an illumination unit which irradiates an object to be inspected with illumination light, a camera unit which receives the light irradiated from the illumination unit and reflected by the object to be inspected and generates a work image, and a display unit which displays the work image generated by the camera unit, the control unit including an image generation condition control unit which controls the camera unit so as to generate a plurality of work images by changing the image generation conditions when generating the work image to a plurality of different conditions, an image score calculation unit which calculates an image score, which is an evaluation value of each work image, based on a plurality of feature amounts which characterize each work image, for the plurality of work images generated under different image generation conditions by the image generation condition control unit, and The display unit includes an image generation condition setting unit that accepts the selection of an inspection image from among the thumbnail images while displaying thumbnail images corresponding to a plurality of workpiece images having image scores, and sets inspection conditions corresponding to the selected inspection image, the plurality of image generation conditions including a single condition for generating an image captured under a single image generation condition and a synthesis condition for synthesizing images captured under a plurality of different image generation conditions, and when the display unit displays the plurality of thumbnail images having the highest image scores, a reference information display field is displayed to indicate whether each thumbnail image was generated under the single condition or the synthesis condition. With the above configuration, when a user is prompted to select a desired image from a plurality of thumbnail images, the image score and the reference information are taken into consideration, making it easier to select an appropriate image, and therefore image generation conditions for generating an image can be easily set.

[0012] Furthermore, according to another embodiment of the image inspection method of the present invention, an image inspection method is provided in which an illumination unit irradiates an object to be inspected, a camera unit captures a workpiece image by receiving the light reflected by the object to be inspected, and an image generation condition control unit generates a plurality of image generation conditions including a single condition for generating an image captured under a single image generation condition and a synthesis condition for synthesizing images captured under a plurality of different image generation conditions, and the camera unit is controlled under the plurality of image generation conditions to generate a plurality of workpiece images, and an image score calculation unit calculates an image score, which is an evaluation value of each workpiece image, based on a plurality of feature amounts that characterize each workpiece image, for the workpiece images generated under the plurality of different image generation conditions, and a display unit displays thumbnail images corresponding to the plurality of workpiece images having the highest image scores, and a display unit displays a selection of an inspection image from the plurality of thumbnail images displayed on the display unit to set the inspection conditions corresponding to the selected inspection image. This allows the user to select a desired image from a plurality of thumbnail images, making it easy to set the image generation conditions for generating an appropriate image.

[0013] Furthermore, according to another embodiment of the image inspection program of the present invention, there is provided an image inspection program for performing image inspection by irradiating an object to be inspected with illumination light from an illumination unit, receiving the light reflected by the object to be inspected, and capturing a workpiece image with a camera unit, and the image inspection program has the following functions: an image generation condition control unit generates a plurality of image generation conditions, including a single condition for generating an image captured under a single image generation condition and a synthesis condition for synthesizing images captured under a plurality of different image generation conditions, as image generation conditions for generating the workpiece image, and the camera unit is controlled under each of the plurality of image generation conditions to generate a plurality of workpiece images; an image score calculation unit calculates an image score, which is an evaluation value of each workpiece image, based on a plurality of feature amounts that characterize each workpiece image, for the work images generated under the plurality of different image generation conditions; a display unit displays thumbnail images corresponding to a plurality of workpiece images having a high image score; and a computer can realize a function of accepting the selection of one inspection image from the plurality of thumbnail images displayed on the display unit and setting inspection conditions corresponding to the selected inspection image. With the above configuration, by having the user select a desired image from among a plurality of thumbnail images, image generating conditions for generating an appropriate image can be easily set.

[0014] Furthermore, a computer-readable recording medium or a device that stores the program according to another embodiment of the present invention stores the program. The recording medium includes a CD-ROM, a CD-R, a CD-RW, a flexible disk, a magnetic tape, an MO, a DVD-ROM, a DVD-RAM, a DVD-R, a DVD+R, a DVD-RW, a DVD+RW, a Blu-ray, a HD DVD (AOD), a UHD (all of which are product names), a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, and other media that can store the program. The program includes a program that is stored in the recording medium and distributed, as well as a program that is distributed by downloading through a network line such as the Internet. The device that stores the program includes a general-purpose or dedicated device in which the program is implemented in an executable state in the form of software or firmware. Furthermore, each process or function included in the program may be executed by a program software that can be executed by a computer, or the process of each part may be realized by hardware such as a predetermined gate array (FPGA, ASIC), or a form in which the program software and a partial hardware module that realizes some elements of the hardware are mixed. [Brief description of the drawings]

[0015] [Figure 1] 1 is a schematic diagram showing a configuration of an image inspection device according to an embodiment of the present invention. [Diagram 2] FIG. 2 is a diagram showing a hardware configuration of an image inspection device. [Diagram 3] FIG. 2 is a block diagram showing the functions of a processor unit. [Figure 4] FIG. 13 is a schematic diagram showing an example of a user interface screen of an image inspection program. [Diagram 5] FIG. 5 is a schematic diagram showing an example in which the thumbnail image display area is switched from FIG. 4. [Figure 6] 13 is a schematic diagram showing another example of a user interface screen of the image inspection program. FIG. [Figure 7] 13 is a flowchart showing a procedure for displaying candidate images in order of image score. [Figure 8] FIG. 13 is a schematic diagram showing an image generating condition setting screen. [Figure 9] FIG. 13 is a schematic diagram showing a region designation screen. [Figure 10] FIG. 13 is a schematic diagram showing the “AI is creating imaging conditions” screen. [Figure 11] FIG. 13 is a schematic diagram showing an image generating condition setting screen. [Figure 12] FIG. 13 is a schematic diagram illustrating an image score map created from image scores of a group of candidate images. [Figure 13] 13 is a flowchart showing a procedure for determining a ranking from the image scores of a group of candidate images. [Figure 14] FIG. 2 is a schematic diagram showing a procedure for generating an ideal image. [Figure 15] FIG. 1 is a schematic diagram showing an example of generating an ideal color image. [Figure 16] This is a schematic diagram showing the reason for separating chromatic colors from other colors. [Figure 17] FIG. 13 is a schematic diagram showing an example of calculation of an image score. [Figure 18] 1 is a schematic diagram showing a procedure for generating an ideal image of color and shape. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0016] Hereinafter, the embodiments of the present invention will be described with reference to the drawings. However, the embodiments shown below are examples of an image inspection device, an image inspection method, an image inspection program, a computer-readable recording medium, and an apparatus for recording the same, which are intended to embody the technical ideas of the present invention, and the present invention does not specify the image inspection device, the image inspection method, the image inspection program, the computer-readable recording medium, and the apparatus for recording the same as those described below. Furthermore, this specification does not specify the members shown in the claims to be the members of the embodiments. In particular, the dimensions, materials, shapes, and relative positions of the components described in the embodiments are merely illustrative examples, unless otherwise specified. Note that the size and positional relationship of the members shown in each drawing may be exaggerated to clarify the explanation. Furthermore, in the following explanation, the same names and symbols indicate the same or similar members, and detailed explanations will be omitted as appropriate. Furthermore, each element constituting the present invention may be configured as a form in which multiple elements are composed of the same member, and one member serves multiple elements, or conversely, the function of one member may be shared by multiple members. [Embodiment 1]

[0017] An image inspection device according to a first embodiment of the present invention is shown in a schematic diagram in Fig. 1. The image inspection device is a device for determining the quality of an inspection object, such as various parts or products, based on an image of the inspection object, and is called an image sensor or the like, and can be used at production sites such as factories. The inspection object may be the inspection object in its entirety, or only a part of it. Furthermore, one inspection object may include multiple inspection objects. Furthermore, one image may include multiple inspection objects.

[0018] Here, we will explain an example of an image inspection device that captures the appearance of an inspection object and judges whether it is good or bad according to predefined inspection conditions. For example, predefined pass / fail judgment conditions for judging whether an item is good or bad are set at the time of setup, and during operation or driving, an image of the inspection object is captured and the pass / fail judgment condition is used to judge the inspection object.

[0019] The image inspection device 100 comprises a control unit 2 which constitutes the device main body, an imaging unit 3, a display section 4, a personal computer 5, and an operation section 6. An image inspection program for operating the image inspection device 100 is installed in the personal computer 5. A user interface screen of the image inspection program can be displayed on the monitor of the personal computer 5 or on the display section 4. The personal computer 5 is not essential and can be omitted. In this case, the control unit 2 executes the image inspection. The control unit 2 may also be configured to execute the image inspection program.

[0020] Furthermore, a display of a personal computer can be used instead of the display unit 4. In FIG. 1, the control unit 2, the imaging unit 3, the display unit 4, the personal computer 5, and the operation unit 6 are described as separate components as an example of the configuration of the image inspection device 100, but any two or more of these can be combined and integrated. For example, the control unit 2 and the imaging unit 3 can be integrated, or the control unit 2 and the display unit 4 can be integrated. The control unit 2 can be divided into a plurality of units and some of them can be incorporated into the imaging unit 3 or the display unit 4, or the imaging unit 3 can be divided into a plurality of units and some of them can be incorporated into other units. Furthermore, the operation unit 6 can be provided separately, or can be integrated into other members, such as by using an input device provided in the personal computer or by using a touch panel as the display unit.

[0021] 1, the control unit 2 is connected to the imaging unit 3, the display unit 4, and the personal computer 5 via cables. However, the present invention does not limit the connections of the various components to wired connections, and wireless connections via radio waves such as wireless LAN, public communication lines, and NFC, infrared rays, light, and other media may be used. In addition, standardized general-purpose communication standards such as Ethernet, IEEE802.1x, USB, Bluetooth, and ZigBee (all of which are registered trademarks or product names), as well as dedicated protocols and interfaces, may be used as appropriate.

[0022] The hardware configuration of an image inspection device 100 according to the first embodiment of the present invention is shown in the block diagram of Fig. 2. The image inspection device 100 shown in this figure includes a control unit 2, an imaging unit 3, a display unit 4, and a personal computer 5. (Control unit 2)

[0023] The control unit 2 includes a main board 13, a connector board 16, a communication board 17, and a power supply board 18. The main board 13 is equipped with a processor unit 20 and a memory 133. The memory 133 is composed of a RAM, a ROM, or the like.

[0024] The connector board 16 receives power from an external power source via a power connector provided in the power interface 161. The power supply board 18 distributes the received power to each board. In this embodiment, power is supplied to the camera unit 14 via the main board 13. A motor driver 181 on the power supply board 18 supplies driving power to the motor 141 of the camera unit 14 to achieve autofocus.

[0025] The communication board 17 transmits an OK / NG signal (judgment signal) indicating the pass / fail judgment result of the object to be inspected output from the main board 13, image data, and the like to the display unit 4. The display unit 4 receives the judgment signal and displays the judgment result. Note that, although the present embodiment is configured to output the judgment signal via the communication board 17, it may also be configured to output the judgment signal via the connector board 16, for example. (Operation unit 6)

[0026] The image inspection device 100 also includes an operation unit 6 that accepts user operations. The operation unit 6 can use existing input devices such as a keyboard, a mouse, and a touch panel. In the example of FIG. 2, the communication board 17 is configured to be able to accept various user operations input from the touch panel 41 of the display unit 4 or the keyboard 51 of the personal computer 5. The touch panel 41 of the display unit 4 is a known touch-type operation panel equipped with, for example, a pressure sensor, and detects touch operations by the user and outputs them to the communication board 17. In addition to the keyboard 51, the personal computer 5 is equipped with a mouse and a touch panel, and is configured to be able to accept various user operations input from these operation devices. The communication may be wired or wireless, and either form of communication can be realized by a conventionally known communication module.

[0027] The illumination unit 15 includes a plurality of LEDs 11 that irradiate illumination light onto an imaging area for imaging an object to be inspected. The LEDs 11 may be provided with a lens or a reflector. The lens may be replaceable as a short-distance or long-distance lens unit. In this specification, illumination light mainly refers to light irradiated by the illumination unit 15, but is also used to include ambient light, such as natural light, that exists regardless of the illumination unit.

[0028] The imaging unit 3 includes a camera section 14 and an illumination section 15. The camera section 14 can control autofocus operation by being driven by a motor 141. The camera section 14 captures an image of an object to be inspected in response to an imaging instruction signal from the main board 13. In this embodiment, the CMOS board 142 is provided as an imaging element. The captured color image is converted into an HDR image by the CMOS board 142 based on conversion characteristics that widen the dynamic range, and is output to the processor section 20 of the main board 13.

[0029] The main board 13 controls the operation of each board connected to it. For example, for the illumination unit 15, it transmits a control signal for controlling the turning on / off of the multiple LEDs 11 to the LED driver 151. The LED driver 151 adjusts, for example, the turning on / off and light amount of the LEDs 11 according to a control signal from the processor unit 20. In addition, it transmits a control signal for controlling the autofocus operation to the motor 141 of the camera unit 14 via the motor driver 181 of the power supply board 18. Furthermore, it transmits an image capture instruction signal to the CMOS board 142. (Storage unit 19)

[0030] The control unit 2 is provided with a storage unit 19 such as a hard disk drive or a semiconductor memory. The storage unit 19 stores program files, setting files, images, judgment results, and the like for enabling various controls and processes to be executed by the above hardware. The program files and setting files can be stored in a portable storage medium such as a USB memory or an optical disk, and the program files and setting files stored in this storage medium can be read into the control unit 2. (Processor section 20)

[0031] The processor unit 20 of the main board 13 is a control circuit or control element that processes given signals and data, performs various calculations, and outputs the calculation results. The processor unit 20 is not limited to processors such as CPU, MPU, GPU, and TPU for general-purpose PCs, but can be configured with LSI, FPGA, gate arrays such as ASIC, microcomputers, or chip sets or packages such as SoCs customized for specific applications. The processor unit 20 realizes multiple functions, which will be described later. Note that the present invention is not limited to an example in which the processor unit is configured physically as one unit, and the processor unit may be configured with multiple CPUs, etc. The multiple CPUs may be physically multiple CPUs, or may be a so-called multi-core MPU in which multiple CPU cores are incorporated into one package. In this case, in addition to realizing each function with multiple CPUs or CPU cores, different functions may be assigned to each CPU or CPU core for execution. Furthermore, the processor unit may be configured with a combination of a CPU and a GPU. In this case, the GPU may be configured to execute part or all of the functions assigned to the processor unit in addition to performing the function of the display control unit described above.

[0032] In the example of FIG. 2, the processor unit 20 of the main board 13 is composed of an FPGA and a DSP. The FPGA performs lighting control and imaging control, and also performs image processing on the acquired image data. The DSP performs edge detection processing, pattern search processing, and the like on the image data. As a result of the pattern search processing, a judgment result indicating the quality of the object to be inspected is output to the communication board 17. The calculation processing results, etc. are stored in the memory 133. In the above example, the FPGA performs lighting control, imaging control, and the like, but the DSP may perform them. Also, instead of the combination of the FPGA and the DSP, one main control circuit or main control unit may be provided. For example, one CPU serves as the main control unit and performs functions such as transmitting a control signal for controlling the on / off of the multiple LEDs 11 to the LED driver 151, transmitting a control signal for controlling the autofocus operation to the motor 141 of the camera unit 14, and transmitting an imaging instruction signal, etc. to the CMOS board 142.

[0033] 3 shows a block diagram of the processor unit 20. As shown in this figure, the processor unit 20 realizes the functions of an image generation condition control unit 21, an image score calculation unit 22, and an image generation condition setting unit 23.

[0034] The image generation condition control unit 21 controls the camera unit 14 so as to generate a plurality of workpiece images by changing the image generation conditions when generating the workpiece image to a plurality of different conditions. The image generation condition control unit 21 also functions as an imaging condition control unit that controls the camera unit 14 according to imaging conditions, which are one aspect of the image generation conditions, when capturing a workpiece image with the camera unit 14. Note that the workpiece image means an image of the workpiece captured. (Image score calculation unit 22)

[0035] The image score calculation unit 22 calculates an image score, which is an evaluation value of each work image, based on a plurality of feature amounts that characterize each work image, for a plurality of work images generated under different image generation conditions by the image generation condition control unit 21, and displays a plurality of images having a high image score on the display unit 4 as thumbnail images. When, for example, a first feature amount and a second feature amount are set as a plurality of different feature amounts, the image score calculation unit 22 calculates image scores for the first feature amount and the second feature amount for each work image. Then, for the image score of the first feature amount and the image score of the second feature amount, a work image having a high image score only on one side is displayed on the display unit 4 as a thumbnail image having a high image score. In this way, by calculating image scores for a plurality of different feature amounts individually and making work images having a high feature amount only into thumbnail images, images having special features can be displayed as thumbnail images and selected.

[0036] Alternatively, an image with a high overall image score may be used as the thumbnail image. In this case, the image score calculation unit 22 calculates the image scores of the first feature amount and the second feature amount for each workpiece image, and displays the workpiece image with a high image score for both on the display unit 4 as a thumbnail image with a high image score. In this way, by calculating image scores for multiple different feature amounts individually and using workpiece images with high image scores for both feature amounts as thumbnail images, inspections from different inspection perspectives can be performed based on the same image.

[0037] The image score calculation unit 22 calculates an image score for a feature included in a specific inspection target area specified in the image of the inspection target object. For example, when the shape of the image is specified as the first feature and the color of the image is specified as the second feature, the image score calculation unit 22 calculates an image score for the shape, which is the first feature, based on the edge of the inspection target object included in the inspection target area, and calculates an image score for the color, which is the second feature, based on the color information of the inspection target object. By having the user specify a specific inspection target area in advance before calculating the image score in this way, it is possible to avoid a situation in which the image score fluctuates due to information other than the inspection target area. This realizes stable image inspection that is not affected by color or shape information included in unnecessary areas. (Image generation condition setting unit 23)

[0038] The image generation condition setting unit 23 accepts a selection of one thumbnail image from among the multiple thumbnail images displayed on the display unit 4, and sets image generation conditions corresponding to the selected thumbnail image. (User interface screen of image inspection program)

[0039] Here, an example of a user interface screen of the image inspection program displayed on the display unit 4 is shown in Fig. 4. This figure shows an AI-generated imaging condition list screen 200 of the image inspection program, with an image display area 201 on the left side of the screen and a thumbnail image display area 202 on the right edge. The image display area 201 is an area for displaying an image captured by the camera unit 14. The image display area 201 constitutes an inspection target area designation section for designating an inspection target area. (Thumbnail image display area 202)

[0040] The thumbnail image display area 202 is an area for displaying a list of multiple thumbnail images. In the example of Fig. 4, four thumbnail images LI1 to LI4, numbered 1 to 4, are displayed on one screen, and other thumbnail images can be displayed by switching the screen with the left and right arrow buttons 203 and 204. For example, when the right arrow button 203 is pressed on the screen of Fig. 4, the screen switches to that of Fig. 5, and four thumbnail images LI5 to LI8, numbered 5 to 8, are displayed in the thumbnail image display area 202B. When the left arrow button 204 is pressed on the screen of Fig. 5, the screen returns to that of Fig. 4. Note that instead of the arrow buttons, a known screen switching method such as a scroll bar or a flick can be appropriately adopted.

[0041] The thumbnail image display area 202 also functions as a thumbnail image selection section for allowing the user to select a desired workpiece image. The user can select a desired workpiece image from among multiple thumbnail images displayed in the thumbnail image display area 202 using an input device such as a mouse or a touch panel. The selected thumbnail image becomes a selected image for image inspection, and image generation conditions corresponding to the selected thumbnail image are set. For example, if the image inspection is a pass / fail judgment for judging whether a product is good or bad, it is necessary to register a master image that is a good product. By registering the master image, the feature amount of the selected thumbnail image, such as color, edges, image brightness and focus level, or image generation conditions such as the amount of illumination light at the time of image capture, exposure time, and focus position, are extracted from the thumbnail image or extracted from data saved in association with the thumbnail image, and registered as settings for image inspection. In addition to the master image that is a good product, by registering a master image that is a bad product, it is also possible to automatically extract and set the conditions that are the boundary between good products and bad products.

[0042] To display such thumbnail images in a list, it is necessary to generate multiple thumbnail images. Here, the image generation condition control unit 21 automatically generates multiple different image generation conditions, and operates the camera unit 14 and the lighting unit 15 under each image generation condition to acquire each workpiece image. Then, for the acquired workpiece images, the image score calculation unit 22 calculates an image score, which is an evaluation value of the workpiece image, and extracts multiple workpiece images having high image scores as thumbnail images and displays them in the thumbnail image display area 202 of the display unit 4. At this time, a predetermined number of workpiece images are extracted as thumbnail images in descending order of image score, and are also displayed in the thumbnail image display area 202 in descending order of image score. (Simple and Compound Conditions)

[0043] Here, the multiple image generation conditions include single conditions and composite conditions. The single conditions are conditions for generating a workpiece image captured under a single image generation condition. The composite conditions are conditions for compositing workpiece images captured under multiple different image generation conditions. In this way, the workpiece image includes a single image captured under a single condition and a composite image captured under a composite condition. The composite image is a composite of multiple optical images captured under different image generation conditions of the same inspection object, and an example of sequential image composition will be described here. In other words, the composite image is captured in real time, and the multiple optical images captured to generate the composite image are not stored as data but are discarded. However, the present invention is not limited to a configuration in which a composite image is captured in real time, and may be configured to store single images captured in advance and later combine them to obtain a composite image.

[0044] The composition conditions include a first composition process that combines images illuminated from multiple directions to emphasize the edges of the workpiece shape, and a second composition process that combines images captured with multiple different exposure times to expand the dynamic range. The second composition process is called HDR, etc.

[0045] Furthermore, in the thumbnail image display area 202, both the image under the single condition having the highest image score and the image under the composite condition having the highest image score are displayed as thumbnail images. When the image scores are simply compared, the images under the composite condition tend to occupy the top positions. Therefore, images under the single condition having the highest image score are also included. For example, if the top image is the image with the highest image score regardless of whether it is under the single condition or the composite condition, there is a high possibility that the top image is an image captured under the composite condition. Therefore, the second-placed image is the image with the highest image score among the images captured under the single condition. (Reference information display column 205)

[0046] Furthermore, when displaying a plurality of thumbnail images having high image scores, the display unit 4 may display reference information on each thumbnail image. In the example of Fig. 4, the display unit 4 is provided with a reference information display field 205 for displaying reference information. The reference information display field 205 is displayed alongside each thumbnail image displayed in the thumbnail image display area 202. In the example of Fig. 4, the reference information display field 205 is provided at the bottom left of each thumbnail image. (Reference information)

[0047] The reference information is information for identifying whether the thumbnail image displayed in the thumbnail image display area 202 was generated under a single condition or a composite condition. Examples of the reference information include the time required to generate the work image, the value of the image score, and if the work image is a composite image, the number of images used for the composite, the number of shots, and the type of composite such as "HDR" or "light division". Alternatively, flags such as "single" or "composite" may be used. In the example of FIG. 4, "x4" is displayed superimposed on the camera icon as the reference information, indicating that four images are captured and composited. In addition, the thumbnail image selected in the thumbnail image display area 202 is highlighted, making it easy for the user to know which thumbnail image is currently selected.

[0048] Furthermore, the thumbnail image selected in the thumbnail image display area 202 may be enlarged and displayed in the image display area 201. In this case, a reference information display field 205B may also be provided in the image display area 201. In the example of FIG. 4, the thumbnail image LI1 displayed in the upper row "1" of the thumbnail image display area 202 is selected, and the thumbnail image LI1 of "1" is enlarged and displayed in the image display area 201, and reference information is displayed in the reference information display field 205B in the upper right. Here, in addition to the number of images, the exposure time is also displayed as more detailed reference information. When the user refers to such reference information and selects a desired image from multiple thumbnail images, an environment is provided in which the user can easily select an appropriate image by taking into consideration the reference information as well as the image of the thumbnail image.

[0049] The thumbnail image display area 202 may be configured to display the topmost thumbnail image among the multiple thumbnail images in an initial state relatively larger than the multiple thumbnail images ranked second and lower. Such an example is shown in FIG. 6. Here, the thumbnail image LI1 with the highest image score "1" is displayed slightly larger than the thumbnail images LI2 to LI4 with "2" and after. This allows the currently selected thumbnail image to be presented to the user in a visually easy-to-understand manner. Also, when another thumbnail image is selected from a state in which the thumbnail image LI1 with "1" is selected, the selected thumbnail image is displayed slightly larger, and the thumbnail image LI1 with "1" returns to a display state of normal size. This allows the transition of the selected thumbnail image to be presented to the user in a visually easy-to-understand manner. In this way, the enlarged display of the thumbnail image in the thumbnail image display area 202 indicates that it is the selected thumbnail image. Also, in the initial stage when the thumbnail images are extracted, the default setting is to select the thumbnail image LI1 with the highest image score "1". This inevitably results in the topmost thumbnail image being emphasized in the initial state.

[0050] Furthermore, the display unit 4 may display images displayed in the image display area 201 while updating them in real time when workpiece images are captured sequentially while changing the image generation conditions in various ways. When multiple thumbnail images are determined by the image score calculation unit 22, the topmost thumbnail image is displayed relatively large in the initial state. Furthermore, the image generation condition control unit 21 may be configured to set image generation conditions including the brightness of the workpiece image displayed on the display unit 4 and the focus of the camera unit 14.

[0051] In the past, image sensors had a wide variety of combinations of image generation conditions, and users empirically searched for good conditions from hundreds of combinations depending on the object to be inspected (workpiece) through trial and error. On the other hand, even image sensors with built-in lighting have been equipped with additional lighting or changed the way the lighting is turned on to create better images, and the combinations of shooting conditions have become even more complex. Therefore, the image inspection device 100 according to this embodiment is configured to present multiple image generation conditions that are considered appropriate and allow the user to select one of them. Here, multiple workpiece images are captured, and an ideal image is generated from the multiple workpiece images obtained. In addition, the image generation conditions are determined by scoring the candidate images. When scoring, multiple different evaluation indices are set, and multiple ideal images that have the maximum evaluation indices are created. Note that the candidate image refers to the workpiece image with the highest image score among the workpiece images. Also, the thumbnail image refers to a thumbnailed image corresponding to the candidate image.

[0052] The image score calculation unit 22 calculates the image score based on the degree of coincidence between the ideal image and each workpiece image. Here, the ideal image is created, and the image score is calculated based on the distance from the ideal image. Alternatively, multiple ideal images may be generated for each feature amount, and the image score for each feature amount may be calculated. (Ideal image)

[0053] As described above, the feature amount includes the shape (edge) and color of the image. Therefore, the ideal image can be an ideal image of shape or an ideal image of color. When generating an ideal image of color, a priority order can be set for the conditions. For example, chromatic color, achromatic color, and saturation can be used in order of priority. Also, the user may specify the feature amount to be used from among a plurality of feature amounts. In this case, a feature amount specification unit is prepared that accepts specification of the feature amount to be used for the inspection from among the plurality of feature amounts. As an example of the feature amount specification unit, for example, the image inspection program displays a feature amount specification screen on the display unit 4, and the user operates an input device such as a mouse to specify the feature amount to be used for the inspection from among the plurality of feature amounts. In response to this, the image score calculation unit 22 calculates an image score based on the specified feature amount, and the thumbnail image having the calculated higher image score is displayed on the display unit 4. In this way, the user can select and specify a specific feature amount, thereby making it possible to display candidate images with the desired feature amount.

[0054] Here, an overview of the procedure for displaying candidate images in order of image score will be described with reference to the flowchart in Fig. 7 and Figs. 8 to 11. Here, an image inspection program is used to register a non-defective inspection object as a master image, and the inspection conditions for the image inspection that distinguishes its features such as contour, area, edges, etc. are set. After the master image is registered and the settings are completed, it is assumed that during operation, pass / fail judgment will be made based on the difference between the inspection object and the master image.

[0055] First, in step S701 in FIG. 7, autofocus (AF) and automatic exposure (AE) are provisionally performed so that the inspection target is captured. For example, in an image inspection program, a dialogue "brightness & focus automatic adjustment in progress" is displayed. Next, in step S702, the user specifies the area of ​​interest. The area can be specified in the inspection target area specification section. For example, in the operation area 222 provided on the right side of the image generation condition setting screen 220 shown in FIG. 8, when the "AI imaging" button 223 is pressed, the area specification screen 230 of FIG. 9, which is one embodiment of the inspection target area specification section, is displayed. In the image display area 201 provided on the left side of the area specification screen 230, a live image of the inspection target captured by the camera unit 14 is displayed. The live image is displayed as a moving image that is updated sequentially. In this state, the user is prompted to specify the inspection target area in the image display area 201 using an input device such as a mouse. Here, the target area is specified so as to surround the entire inspection target displayed in the image display area 201, or a part of the inspection target that is to be noted. Furthermore, in step S703, autofocus is executed again on the designated area to bring it into focus.

[0056] Next, in step S704, the image generation conditions, here the imaging conditions, are a combination of ON / OFF of the inner lighting, ON / OFF of the outer lighting, and multiple imaging, and the candidate images are captured while changing the brightness. Here, as shown in FIG. 10, a dialogue "AI is creating imaging conditions" is displayed, and the workpiece images captured sequentially are updated in real time in the image display area 201. Furthermore, in step S705, a combination of ON / OFF of the lighting, etc. is set as one condition, and all candidate images are selected from one condition, and they are synthesized to first create an "ideal image of color." Here, the selected candidate images are called a candidate image group. Next, in step S706, the degree of agreement between the candidate image group and the "ideal image of color" is set as a "color image score." Also, in step S707, an "ideal image of shape" is created from the candidate image group and the "ideal image of color." Furthermore, in step S708, the degree of agreement between the candidate image group and the "ideal image of shape" is set as an "image score of shape." Then, in step S709, an "overall image score" is calculated from the "color image score" and the "shape image score." In addition, in step S710, a ranking is calculated from the candidate image group and the "overall image score."

[0057] Once the image scores have been calculated in this manner, the order in which the candidate images are displayed in thumbnail image display area 202 is determined based on the calculated ranking. Then, in step S711, the candidate images are displayed in thumbnail image display area 202 as shown in Fig. 4. Also, in image display area 201, a work image is displayed with brightness and focus adjusted so as to achieve image generation conditions corresponding to the top candidate image. At this time, the first ranked thumbnail image may be displayed relatively large as shown in Fig. 6.

[0058] Furthermore, when displaying thumbnail images, reference information may be displayed (step S712). In the example of FIG. 4, an icon is displayed in the reference information display field 202 for an image that has been captured multiple times and synthesized. In this way, the user is prompted to select a desired thumbnail image as a selected image. This causes the screen to switch from the AI-generated imaging conditions list screen 200 in FIG. 4, FIG. 5, etc. to the image generation conditions setting screen 240 in FIG. 11. (Ranking procedure)

[0059] Next, a procedure for determining the order from the image scores of the candidate image group will be described with reference to the schematic diagram in FIG. 12 and the flowchart in FIG. 13. In FIG. 12, it is assumed that there are four candidate image groups, A to D. First, in step S1301, an "ideal image for color" is created from the candidate image group. For example, an "ideal image for color" E is created from the four candidate image groups, A to D. Here, as shown in FIG. 14, a color-coded image group is first created from the candidate image group. Then, an ideal image for color is created from the candidate image group and the color-coded image group. Furthermore, in step S1302, the degree of coincidence between the candidate image group and the "ideal image for color" is calculated to obtain a "color image score." Here, the color image score is calculated from the candidate image group, the color-coded image group, and the ideal image for color.

[0060] Meanwhile, in step S1303, an "ideal image for shape" is generated from the group of candidate images and the "ideal image for color." For example, an "ideal image for shape" F is created from a group of four candidate images A to D. Then, in step S1304, the degree of match between the group of candidate images and the "ideal image for shape" is calculated to obtain a "shape image score." Note that the calculation of the "color image score" and the "shape image score" may be performed in parallel, or the "shape image score" may be calculated first and then the "color image score."

[0061] Then, in step S1305, an "overall image score" is calculated from the "color image score" and the "shape image score." For example, image score map G shows an image score map SM in which the horizontal axis is plotted with the "color image score" and the vertical axis is plotted with the "shape image score." In G of FIG. 12, 0 indicates the image score of each candidate image: A, 1 indicates B, 2 indicates C, and 3 indicates D. Then, in step S1306, a ranking is calculated from the group of candidate images and the "overall image score." For example, in the image score map of G, the best candidate image for each item (color, shape) is selected and the ranking is determined. (Ideal color image)

[0062] The way an object to be inspected appears changes depending on the image generation conditions, in this case the shooting conditions. For example, when looking at multiple candidate images taken under different shooting conditions, some are good and some are bad from the viewpoint of color. From such a group of candidate images taken under different shooting conditions, the best possible image is extracted and the best possible image, that is, an ideal image in terms of color, is synthesized. In this case, "color coding" and "color priority order" are used as methods for determining whether an image is good or bad from the viewpoint of color. (Color coding, color priority)

[0063] The color priority order is chromatic, achromatic, and saturated. Each candidate image is color-coded and determined to be correct in order of color priority. The most likely correct colors are collected from the group of candidate images to synthesize an ideal color image. Each candidate image is then evaluated based on the synthesized ideal color image. Specifically, the image score of each candidate image is defined so that the closer it is to the ideal image, the higher the value, and the image score is calculated by the image score calculation unit 22. (How to generate an ideal color image)

[0064] Here, the procedure for generating an ideal color image will be described with reference to FIG. 15. Here, an example is considered in which an ideal color image is generated from two candidate images shown as A to B. First, each candidate image is color-coded. Here, each candidate image is color-coded as chromatic, achromatic, and saturated. Specifically, A is color-coded as chromatic color C, achromatic color E, and saturated color G. B is color-coded as chromatic color D, achromatic color F, and saturated color H. Then, pixels with high priority are collected from each of the obtained images to generate an ideal color image. Here, image I is generated as the ideal color image from candidate images A to B. (Color-coded judgment)

[0065] Here, the reason for separating chromatic colors from other colors when color-coding will be explained with reference to FIG. 16. Even when images of the same inspection object are captured, there are two main reasons for the difference depending on the shooting method: the amount of light and the components. First, the image is crushed and blown out due to the change in the amount of illumination light. For example, for image B in FIG. 16, the crushed and blown out image is A and C, respectively. On the other hand, the components are the components of the reflected light of the illumination light reflected by the inspection object, and include regular reflection and diffuse reflection. For example, for image E, the regular reflected image is D and the diffuse reflected image is F. In this way, the chromatic colors of the captured image may change to other colors depending on the amount of light and components of the illumination light. On the other hand, non-chromatic colors do not basically change to chromatic colors. Therefore, when the same inspection object appears as both chromatic and other colors depending on the shooting method, it can be said that the chromatic color is correct.

[0066] In this way, by giving a high priority to chromatic colors, it is possible to perform a highly reliable judgment. Also, when chromatic colors are photographed with a monochrome camera, they become achromatic colors, so achromatic colors are the second most reliable after chromatic colors. On the other hand, saturated colors are relatively less reliable than chromatic and achromatic colors because all color information is lost. However, they are not worthless because they may contain information other than color, such as the presence or absence of gloss and the continuity of a three-dimensional shape. As a result, the priority order of colors is chromatic, achromatic, and saturated. In the examples of Figures 17E to 17T, the higher the image, the higher the priority. (Color image)

[0067] Here, we will explain the color classification method for classifying each pixel of an image as either chromatic, achromatic, or saturated. First, the conditions for determining a color as chromatic are that the color saturation is high, the surrounding hue is constant, and the color is non-saturated. (Achromatic image)

[0068] The next condition for determining an achromatic color is that it has low saturation, constant brightness around it, and is non-saturated. Here, saturation is excluded from achromatic colors, but crushed black is not excluded. This is because, as can be seen by considering a black glossy surface, the information obtained from saturation is only the presence or absence of gloss that is unrelated to the color, whereas crushed black can indicate the correct color information of black. (Saturated image)

[0069] The conditions for determining saturation are that all of the above-mentioned conditions for chromatic and achromatic colors are met except for the condition for non-saturation, and only the condition for non-saturation is not met. (Image score calculation for each candidate image)

[0070] Next, the procedure for calculating the image score for each candidate image will be described with reference to FIG. 17. FIG. 17 shows the image scores for each of eight combinations of ideal and candidate images. The image score is defined so that the closer to the ideal image, the higher the image score. Here, the image score is expressed as a percentage from 0 to 100%. For pixels where the color coding of the ideal and candidate images matches, as shown in FIG. 17, if the colors match, the score is 100%, and if they do not match, the score is 0%, and the image score is the average of all pixels.

[0071] For example, as shown in FIG. 17, when the ideal image is chromatic and the candidate image is chromatic of the same color and is a perfect match, the image score is 100%. As shown in 2, when the ideal image is chromatic and the candidate image is different in saturation or brightness, the image score is determined according to the difference, and is 75% here. Here, the image score is {1-(absolute value of difference of maximum RGB values)} / 255. As shown in 3, when the ideal image is chromatic and the candidate image is chromatic but has a different hue, the image score is 0%. Furthermore, as shown in 4, when the ideal image is chromatic and the candidate image is achromatic, the color division is different and the image score is 0%.

[0072] On the other hand, as shown by 5 in FIG. 17, when the ideal image is achromatic and the candidate image is also achromatic, the image score is 100% because the achromatic colors match perfectly. Although chromatic colors have a higher priority than achromatic colors when generating the ideal image, chromatic colors and achromatic colors are weighted equally when calculating the image score. If the image score does not reach 100% when both colors are achromatic, the achromatic inspection object will be determined only by its shape. If the ideal image is achromatic and the candidate image is achromatic but has a different brightness, as shown by 6, the image score is determined according to the difference in brightness, which is 75% in this case.

[0073] On the other hand, as shown by 7 in Fig. 17, if the ideal image is a saturated image and the candidate image is also a saturated image in chroma, the saturated images match, so the image score is 100%. As will be described later, there may be cases where achromatic colors are better, or where saturated images are better. The image scores for chromatic and saturated images are weighted equally. Also, as shown by 8, if the ideal image is a saturated image and the candidate image is a saturated image with some differences, the image score is determined according to the difference, and is 50% in this case. (Ideal image of shape)

[0074] Next, we will explain how to generate an ideal image of a shape. The shapes contained in each workpiece image, for example the edge information obtained from the shape, can be insufficient or excessive. There may be cases where there is insufficient edge information when calculating the image score, in which case the edge information must be supplemented. Conversely, if there is excess edge information, it may be necessary to select what to use. For example, when it is too bright and saturated, minute shapes disappear and only large shapes remain. Also, when lighting is reflected on the gloss, shapes unrelated to the target object appear in the workpiece image. Or the lighting may cast a shadow of a three-dimensional object, causing the shape to appear double.

[0075] In such a case, even if it is not possible to judge whether the image is excessive or insufficient from an image of a single image generation condition, valuable information on the shape can be extracted by comparing workpiece images of multiple image generation conditions. For example, a shape that is common to workpiece images of multiple image generation conditions is more reliable than a shape that is only present in a workpiece image of a single image generation condition. In the above example of a shadow of a three-dimensional object, the shape of the shadow when illuminated from a certain direction does not appear when illuminated from a different direction. (Procedure for generating ideal color images and ideal shape images)

[0076] Here, the procedure for generating an ideal color image and an ideal shape image will be described with reference to Fig. 18. First, an ideal color image is generated from an original workpiece image. Here, it is assumed that C is obtained as an ideal color image from original workpiece images A to B.

[0077] Meanwhile, edge information is extracted from each original workpiece image. For the process of extracting the image contour, i.e., edge information, from the workpiece image, existing algorithms can be used as appropriate. For example, the Canny edge detector, differential filter, Prewitt filter, Sobel filter, etc. can be used. Here, it is assumed that edge images D to E are obtained from each of the workpiece images A to B, respectively. Then, only the edges of pixels whose color coding matches the ideal image of color are made valid, and the maximum value of all edge images is taken as the ideal image of shape. Here, it is assumed that for each of the candidate images A to B, the areas whose color coding matches the ideal image of color of C are F to G. For the above-mentioned D to E, only the areas F to G are made valid, resulting in H to I. Furthermore, J, which takes the maximum value of H to I, is the ideal image of shape. As shown in J, in the ideal image of shape, it can be confirmed that fine textures that are different for each candidate image are suppressed, and the shape common to all the candidate images, in this example, the engraved part, is emphasized. (Removal of texture information)

[0078] Next, the procedure for removing texture information will be described. If an ideal image of shape is created by synthesizing images including texture information without selecting edges, the image will be the ideal image of shape. As a result of the texture information remaining in the ideal image of shape, the image score of the image including the texture information will be high, and there is a concern that an image including unnecessary texture information will be selected as the ideal image, resulting in low accuracy. For example, the workpiece images shown in A and B of FIG. 18 have high edge strength due to texture information. In addition, the spatial frequency also differs depending on the object to be inspected, so it is difficult to remove the texture information using a filter based on the edge strength or spatial frequency of each workpiece image. Therefore, in order to suppress such texture information, processing is performed using information on the entire image, not for each workpiece image. In addition, the evaluation index other than edge strength and spatial frequency is used for the judgment. Here, the edge information is sorted using the ideal image of color. (Edge extraction method)

[0079] When sorting edge information using the ideal color image, edge extraction is performed. Here, a Sobel filter is used as the edge extraction method, and the sum of the absolute values ​​in the X and Y directions is used. [Industrial Applicability]

[0080] The image inspection device, control unit for the image inspection device, image inspection method, image inspection program, and computer-readable recording medium and equipment having the program recorded thereon can be suitably used for applications such as determining whether an object to be inspected is good or bad based on an image of the workpiece to be inspected. [Explanation of symbols]

[0081] 100...Image inspection device 2. Control unit 3…Imaging unit 4...Display section 5. Personal computer 6...Operation unit 11...LED 13…Main circuit board 14…Camera section 15…Lighting section 16…Connector board 17…Communication board 18…Power supply board 19...Storage section 20...Processor section 21...Image generation condition control section 22...Image score calculation unit 23...Image generation condition setting unit 41...Touch panel 51…Keyboard 100...Image inspection device 133…Memory 141...Motor 142... Circuit board 151...Driver 161...Power supply interface 181...Motor driver 200…AI-generated imaging conditions list screen 201...Image display area 202, 202B: Thumbnail image display area 203...Right arrow button 204...Left arrow button 205, 205B…Reference information display column 220...Image generation condition setting screen 222…Operation area 223…"AI Imaging" button 224…Trigger condition button 230…Area specification screen 240...Image generation condition setting screen LI1~LI8…Thumbnail images SM: Image score map

Claims

1. an illumination unit that irradiates an object to be inspected with illumination light; a camera unit that receives light irradiated from the illumination unit and reflected by an object to be inspected, and generates a workpiece image; A display unit that displays a workpiece image generated by the camera unit; An image generation condition control unit that controls the camera unit so as to change the image generation conditions when generating the workpiece image to a plurality of different conditions to generate a plurality of workpiece images; An image score calculation unit that calculates an image score, which is an evaluation value of each work image, based on a plurality of feature amounts that characterize each work image, for a plurality of work images generated under different image generation conditions by the image generation condition control unit; an image generation condition setting unit that accepts a selection of one thumbnail image from among a plurality of thumbnail images displayed on the display unit, the thumbnail images corresponding to the plurality of work images having a high image score, and accepts settings of image generation conditions corresponding to the selected thumbnail image; An image inspection apparatus comprising: The plurality of image generating conditions include: A single condition for generating an image captured under the single image generation condition; A synthesis condition for synthesizing images captured under a plurality of different image generation conditions; Includes: When the display unit displays the plurality of thumbnail images having the top image scores, each thumbnail image is Was it generated under the single condition? Was it produced under the above synthesis conditions? The image inspection device is provided with a reference information display field for displaying reference information for identifying the object.

2. 2. The image inspection device according to claim 1, The image score calculation unit calculates image scores for a first feature amount and a second feature amount, which are a plurality of different feature amounts, for each workpiece image, An image inspection device configured to display on the display unit a work image having a high image score only for one of the image scores of the first feature amount and the second feature amount as a thumbnail image having a higher image score.

3. 2. The image inspection device according to claim 1, The image score calculation unit calculates image scores for a first feature amount and a second feature amount, which are a plurality of different feature amounts, for each workpiece image, An image inspection device configured to display on the display unit a work image having a high image score for both the first feature amount and the second feature amount as a thumbnail image having a higher image score.

4. The image inspection device according to any one of claims 1 to 3, further comprising: The inspection target area designation unit is provided for accepting designation of an inspection target area, the plurality of feature amounts include a shape set as a first feature amount and a color set as a second feature amount, The image score calculation unit is configured to calculate an image score for an object to be inspected, the image score calculation unit being ... Calculating an image score related to the shape, which is the first feature amount, based on an edge of the object to be inspected; An image inspection device configured to calculate an image score relating to color, which is the second feature amount, based on color information of the object to be inspected.

5. The image inspection device according to any one of claims 1 to 4, further comprising: a feature amount designation unit that accepts designation of a feature amount to be used for inspection from among a plurality of feature amounts; The image score calculation unit calculates an image score based on a specified feature amount, An image inspection device configured so that thumbnail images having high image scores calculated by the image score calculation unit are displayed on the display unit.

6. The image inspection device according to any one of claims 1 to 5, The image inspection device is configured such that the image score calculation unit calculates an image score based on the degree of match between an ideal image generated to perform inspection based on the features and each work image.

7. The image inspection device according to any one of claims 1 to 6, An image inspection device in which the image score calculation unit calculates an image score so that both a work image under a single condition having a higher image score and a thumbnail image corresponding to a work image under a composite condition having a higher image score are displayed on the display unit.

8. The image inspection device according to any one of claims 1 to 7, The image inspection device is configured such that the reference information display field displays, as reference information for the thumbnail image generated under the synthesis conditions, the number of times the camera unit took images to generate the thumbnail image.

9. The image inspection device according to any one of claims 1 to 8, The synthesis conditions are A first synthesis process synthesizes images illuminated from multiple directions to emphasize the edges of the workpiece shape; Secondary synthesis process that synthesizes images taken with multiple different exposure times to expand the dynamic range An image inspection device comprising:

10. The image inspection device according to any one of claims 1 to 9, The image inspection device according to the present invention, wherein the display unit is configured to display the topmost thumbnail image among the plurality of thumbnail images relatively larger than the second and subsequent thumbnail images.

11. an illumination unit that irradiates an object to be inspected with illumination light; A camera unit that receives light reflected from an object to be inspected and generates a workpiece image; An image score calculation unit that controls the camera unit so as to change the image generation conditions when generating the work image to a plurality of different conditions, and calculates an image score, which is an evaluation value of each work image, for the generated plurality of work images based on a plurality of feature amounts that characterize each work image; A display unit that displays a plurality of thumbnail images corresponding to workpiece images having a high image score among the plurality of workpiece images based on the image score calculated by the image score calculation unit; an image generation condition setting unit that receives settings of inspection conditions corresponding to a thumbnail image selected from the plurality of thumbnail images; An image inspection apparatus comprising: The image score calculation unit is Calculating an image score for the workpiece image for each of a plurality of different feature amounts; determining the plurality of thumbnail images based on the plurality of image scores; An image inspection device configured as above.

12. an illumination unit that irradiates an object to be inspected with illumination light; a camera unit that receives light irradiated from the illumination unit and reflected by an object to be inspected, and generates a workpiece image; A display unit that displays a workpiece image generated by the camera unit; Controlling the camera unit so as to change image generation conditions when generating the workpiece image to a plurality of different conditions to generate a plurality of workpiece images; A plurality of workpiece images generated under different image generation conditions are subjected to calculation of an image score, which is an evaluation value of each workpiece image, based on a plurality of feature amounts that characterize each workpiece image, and thumbnail images corresponding to the plurality of workpiece images having a high image score are displayed on the display unit; a processor unit that accepts a selection of one thumbnail image from among the plurality of thumbnail images displayed on the display unit, and thereby accepts settings of image generation conditions corresponding to the selected thumbnail image; An image inspection apparatus comprising: The plurality of image generating conditions include: A single condition for generating an image captured under the single image generation condition; A synthesis condition for synthesizing images captured under a plurality of different image generation conditions; Includes: When the display unit displays the plurality of thumbnail images having the top image scores, each thumbnail image is Was it generated under the single condition? Was it produced under the above synthesis conditions? The image inspection device is provided with a reference information display field for displaying reference information for identifying the object.

13. The image inspection device according to any one of claims 1 to 12, The image inspection device is an image sensor that performs pass / fail judgment.

14. an illumination unit that irradiates an object to be inspected with illumination light; a camera unit that receives light irradiated from the illumination unit and reflected by an object to be inspected, and generates a workpiece image; A display unit that displays a workpiece image generated by the camera unit; a control unit connected to the An image generation condition control unit that controls the camera unit so as to change the image generation conditions when generating the workpiece image to a plurality of different conditions to generate a plurality of workpiece images; An image score calculation unit that calculates an image score, which is an evaluation value of each work image, based on a plurality of feature amounts that characterize each work image, for a plurality of work images generated under different image generation conditions by the image generation condition control unit; an image generation condition setting unit that accepts a selection of an inspection image from among a plurality of thumbnail images displayed on the display unit, the selection being in a state in which thumbnail images corresponding to a plurality of workpiece images having a high image score are displayed on the display unit, and sets inspection conditions corresponding to the selected inspection image; Equipped with The plurality of image generating conditions include: A single condition for generating an image captured under the single image generation condition; A synthesis condition for synthesizing images captured under a plurality of different image generation conditions; Includes: When the display unit is caused to display a plurality of thumbnail images having the top image scores, each thumbnail image is Was it generated under the single condition? Was it produced under the above synthesis conditions? The control unit for an image inspection device is configured to display reference information for identifying the object in a reference information display field.

15. An image inspection method for performing an image inspection by irradiating an inspection object with illumination light from an illumination unit, receiving light reflected by the inspection object, and capturing a workpiece image with a camera unit, comprising: As image generation conditions when generating the workpiece image, A single condition for generating an image captured under the single image generation condition; A synthesis condition for synthesizing images captured under a plurality of different image generation conditions A step of generating a plurality of image generating conditions including the above by an image generating condition control unit, and controlling the camera unit under the plurality of image generating conditions to generate a plurality of workpiece images; A step of calculating an image score, which is an evaluation value of each work image, based on a plurality of feature amounts that characterize each work image, for the work images generated under the plurality of different image generation conditions by an image score calculation unit; displaying thumbnail images corresponding to the workpiece images having the highest image scores on a display unit; accepting a selection of one inspection image from among the plurality of thumbnail images displayed on the display unit, thereby setting inspection conditions corresponding to the selected inspection image; An imaging inspection method comprising:

16. The image inspection method according to claim 15, further comprising: In the step of displaying a plurality of thumbnail images having the top image scores on the display unit, each thumbnail image is Was it generated under the single condition? Was it produced under the above synthesis conditions? The image inspection method comprises displaying reference information for identifying the object in a reference information display field.

17. An image inspection program for performing an image inspection by irradiating an object to be inspected with illumination light from an illumination unit, receiving light reflected by the object to be inspected, and capturing a workpiece image with a camera unit, As image generation conditions when generating the workpiece image, A single condition for generating an image captured under the single image generation condition; A synthesis condition for synthesizing images captured under a plurality of different image generation conditions A function of generating a plurality of image generating conditions including the above in an image generating condition control unit, and controlling the camera unit under the plurality of image generating conditions to generate a plurality of workpiece images; A function of calculating an image score, which is an evaluation value of each work image, based on a plurality of feature amounts that characterize each work image, for the work images generated under the plurality of different image generation conditions in an image score calculation unit; A function of displaying thumbnail images corresponding to a plurality of workpiece images having a high image score on a display unit; a function of accepting a selection of one inspection image from among the plurality of thumbnail images displayed on the display unit, and setting inspection conditions corresponding to the selected inspection image; An image inspection program to make this possible on a computer.

18. The image inspection program according to claim 17, further comprising: When the display unit is caused to display a plurality of thumbnail images having the top image scores, each thumbnail image is Was it generated under the single condition? Was it produced under the above synthesis conditions? An image inspection program for enabling a computer to perform a function of displaying reference information for identifying the object in a reference information display field.

19. A computer-readable recording medium or storage device having the program according to claim 17 or 18 recorded thereon.

Images