WO2020012939A1

WO2020012939A1 - Image processing device, image processing method and image processing program

Info

Publication number: WO2020012939A1
Application number: PCT/JP2019/024996
Authority: WO
Inventors: 藤枝　紫朗
Original assignee: オムロン株式会社
Priority date: 2018-07-11
Filing date: 2019-06-24
Publication date: 2020-01-16
Also published as: JP7194348B2; JP2020008488A

Abstract

An image processing device, image processing method and image processing program are provided which enable easily generating good product images from bad product images. This image processing device is provided with: a designation unit which designates a defect image, corresponding to a defect, in a defective product image taken of a defective product including the defect; a determination unit which determines peripheral images from the images present in the periphery of a designated defect image; and a synthesis unit which synthesizes peripheral images determined in the designated defect image. Here, it is thought that there are images of defect-free regions in the periphery of the defect image. Therefore, the images of the defect-free regions in the periphery of the defect image are determined as peripheral images, and, by synthesizing the peripheral images with the defect image, it is possible to repair the defect image.

Description

Image processing apparatus, image processing method, and image processing program

The present invention relates to an image processing device, an image processing method, and an image processing program.

Conventionally, a photographing unit for photographing the edge of a substrate, a defect detecting unit for detecting a defect based on an image of the edge of the substrate acquired by the photographing unit, and determining the degree of the defect detected by the defect detecting unit A defect state determination unit; and a defect registration unit that registers the position of the defect detected by the defect detection unit 7 and the degree of the defect determined by the defect state determination unit in association with each other. There is known a defect monitoring system that determines the degree of a defect registered in a defect registration unit over time (see Patent Document 1). In this defect monitoring system, the defect state determination unit determines the degree of the registered defect over time, thereby making it possible to monitor a change in the degree of the defect. Even if there is, if it is growing in the subsequent judgment, it can be repaired before it becomes unrecoverable.

JP 2008-82949 A

When a non-defective product image is generated from a defective product image of a defective product including a defect, it is necessary to repair a defective image corresponding to the defect in the defective product image. However, in the conventional image processing apparatus, it takes a long time to repair a defective image, and it is not easy to generate a good image from a defective image.

Therefore, the present invention provides an image processing apparatus, an image processing method, and an image processing program that can easily generate a good-quality image from a defective product image obtained by photographing a defective product including a defect.

An image processing apparatus according to one embodiment of the present invention includes a specification unit that specifies a defect image corresponding to a defect in a defective product image obtained by capturing a defective product including a defect, and a peripheral unit that determines a peripheral image from an image existing around the specified defect image. The image processing apparatus includes a determining unit that determines an image, and a combining unit that combines the determined peripheral image with the designated defect image.

According to this aspect, the determined peripheral image is combined with the designated defect image. Here, it is considered that there is an image of a region without a defect around the defect image. Therefore, it is possible to repair the defective image by determining the image of the area without the defect around the defective image as the peripheral image and combining the peripheral image with the defective image. Therefore, a good image can be easily generated from the defective image.

In the aspect described above, the specifying unit may specify the defective image by using the pointer displayed on the defective product image, and the determining unit may determine the peripheral image based on the moving direction of the pointer.

According to this aspect, the peripheral image is determined based on the moving direction of the pointer. Thus, the peripheral image based on the moving direction of the pointer is automatically determined without selecting from the images existing around the defective image. Therefore, a good image can be easily generated from the defective image.

In the aspect described above, the determining unit may determine the peripheral image based on the moving direction of the pointer and from the image on the center side of the defective image.

According to this aspect, the peripheral image is determined from the image on the center side of the defective image based on the moving direction of the pointer. Generally, it is considered that the possibility that a defect exists at the center of a defective product image is smaller. Therefore, the defective image can be easily repaired by determining the peripheral image from the image on the center side of the defective image based on the moving direction of the pointer.

In the aspect described above, the determining unit may determine the peripheral image by the peripheral pointer displayed at a position in a predetermined direction with respect to the pointer in the defective product image.

According to this aspect, the peripheral image is determined by the peripheral pointer displayed at a position in a predetermined direction with respect to the pointer. This makes it possible to select an image in a region where no defect exists around the defect image. Therefore, a good image can be more easily generated from a defective image.

In the above-described embodiment, a setting unit for setting the size of the peripheral pointer may be further provided.

According to this aspect, the size of the peripheral pointer is set. This makes it possible to determine a peripheral image having a desired size.

In addition, an image processing method according to another aspect of the present invention includes a specifying step of specifying a defect image corresponding to a defect in a defective product image obtained by photographing a defective product including a defect, wherein the specifying step exists around the specified defect image. A determining step of determining a peripheral image from the image; and a combining step of combining the determined peripheral image with the designated defect image.

In the aspect described above, the specifying step may include specifying a defective image with a pointer displayed on the defective product image, and the determining step may include determining a peripheral image based on a moving direction of the pointer.

In the aspect described above, the determining step may include determining a peripheral image from an image on the center side of the defective image based on the moving direction of the pointer.

In the aspect described above, the determining step may include determining the peripheral image using a peripheral pointer displayed at a position in a predetermined direction with respect to the pointer in the defective product image.

In the above-described embodiment, a setting step of setting the size of the peripheral pointer may be further included.

An image processing program according to another aspect of the present invention is an image processing program to be executed by a computer, comprising: a designation step of designating a defect image corresponding to a defect in a defective product image obtained by photographing a defective product including a defect. A determining step of determining a peripheral image from an image existing around the designated defect image; and a combining step of combining the determined peripheral image with the designated defect image.

According to the present invention, it is possible to provide an image processing apparatus, an image processing method, and an image processing program that can easily generate a good-quality image from a defective-quality image.

FIG. 1 is a block diagram illustrating a schematic configuration of an image processing apparatus according to an embodiment. FIG. 2 is a diagram illustrating a setting screen of the image processing apparatus illustrated in FIG. FIG. 3 is a diagram illustrating an example of combining images in the image processing apparatus illustrated in FIG. 1. FIG. 4 is a flowchart illustrating a first example of a schematic operation of the image processing apparatus illustrated in FIG. FIG. 5 is a diagram illustrating a defective product image of the image processing apparatus shown in FIG. FIG. 6 is a diagram illustrating a non-defective image of the image processing apparatus illustrated in FIG. FIG. 7 is a flowchart illustrating a second example of the schematic operation of the image processing apparatus illustrated in FIG. FIG. 8 is a diagram illustrating peripheral images in a second example of the schematic operation of the image processing apparatus illustrated in FIG. 1.

A preferred embodiment of the present invention will be described with reference to the accompanying drawings. In each of the drawings, the components denoted by the same reference numerals have the same or similar configurations.

First, an example of the configuration of the image processing apparatus according to the present embodiment will be described with reference to FIGS. FIG. 1 is a block diagram illustrating a schematic configuration of an image processing apparatus 100 according to an embodiment. FIG. 2 is a diagram illustrating a setting screen of the image processing apparatus 100 shown in FIG.
FIG. 3 is a diagram exemplifying image synthesis in the image processing apparatus 100 shown in FIG.

The image processing apparatus 100 is for generating a good image from a defective image. The defective image and the good image are both images of the target object. The defective product image is obtained by photographing an object including a defect. Therefore, the defective product image includes a defect image corresponding to the defect. Although the type of the defect is not particularly limited, for example, the defect is a visible one such as a scratch, a crack, an attached matter, and a dent. On the other hand, the non-defective image is obtained by photographing an object that does not include the defect described above. In addition, the non-defective image can be generated from the defective image by repairing a defective image included in the defective image. The non-defective image is used, for example, as learning data for constructing a determination model for determining the acceptability of an object from an image of the object. Alternatively, the non-defective image may be used as evaluation data for evaluating the quality of the target from an image of the target.

。As shown in FIG. 1, the image processing apparatus 100 includes an image processing device 100, a calculation device 50, an imaging device 60, an input device 70 and an output device 80.

The arithmetic device 50 is, for example, an information processing device such as a computer. The arithmetic device 50 includes an input / output I / F (interface) 10, a storage unit 20, and a control unit 30. The arithmetic device 50 further includes a bus 40 configured to transmit signals and data between the units of the arithmetic device 50.

The input / output I / F 10 is an interface between the arithmetic unit 50 and an external device. The input / output I / F 10 is configured to exchange data and signals with external devices. Further, the input / output I / F 10 is configured to control communication with an external device. The input / output I / F 10 includes, for example, connection terminals of standardized interfaces such as USB (Universal Serial Bus), HDMI (registered trademark) (High-Definition Multimedia Interface), and IEEE1394. The input / output I / F 10 is connected to the imaging device 60, the input device 70, and the output device 80.

The storage unit 20 is configured to store programs, data, and the like. The storage unit 20 includes, for example, a hard disk drive, a solid state drive, and the like. The storage unit 20 stores in advance various programs executed by the control unit 30, data necessary for executing the programs, and the like. Further, the storage unit 20 stores a defective product image 21 input from the imaging device 60 via the input / output I / F 10 and a good product image 22 generated from the defective product image 21 by the control unit 30.

The control unit 30 is configured to control the operation of each unit of the arithmetic device 50, such as the input / output I / F 10 and the storage unit 20. Further, the control unit 30 is configured to realize each function described later by executing a program stored in the storage unit 20 or the like. The control unit 30 includes, for example, a processor such as a CPU (Central Processing Unit), a memory such as a ROM (Read Only Memory), a RAM (Random Access Memory), and a buffer storage device such as a buffer. The control unit 30 includes, for example, a setting unit 31, a specifying unit 32, a determining unit 33, and a combining unit 34 as its functional configuration.

The setting unit 31 is configured to set a plurality of items in a non-defective image generation process described later. The content of each item is input by the user (user) operating the input device 70 or the like. The setting unit 31 causes the output device 80 or the like to display a setting screen for the user to input each item.

As shown in FIG. 2, the setting screen 310 includes, for example, “mode”, “brightness setting area”, and “paint radius” as parameter items. In the example shown in FIG. 2, “composite (4)” is selected as the mode, “10” is set in the brightness setting area, and “10” is set in the paint radius. The paint radius corresponds to an example of the “size of the peripheral pointer” of the present invention.

The setting screen 310 also includes “folder name” and “file name” as image items. For example, by inputting a “folder name” and a “file name” and pressing a read button, it is possible to set a defective image 21 read from the storage unit 20. By inputting the “folder name” and the “file name” and pressing the save button, the non-defective image 22 generated from the defective image 21 to be stored (written) in the storage unit 20 can be set. It becomes possible.

Returning to FIG. 1, the specifying unit 32 is configured to specify a defect image corresponding to a defect in the defective product image 21. Specifically, the specifying unit 32 displays a pointer on the defective product image 21 displayed on the output device 80 or the like. The pointer is for designating a widened area. Then, by moving the pointer in accordance with the operation of the user via the input device 70 or the like, the specifying unit 32 can specify the defective image with the pointer.

The determiner 33 is configured to determine a peripheral image from images existing around the defective image designated in the defective product image 21. The number of peripheral images to be determined is not limited to one, and may be plural. Various methods can be adopted for determining the peripheral image. Some of the methods for determining the peripheral image will be described later, but are not particularly limited.

The synthesizing unit 34 is configured to synthesize the peripheral image determined on the defective image 21 with the designated defective image. For example, as shown in FIG. 3, the designated defect image is set as the center image CI, and four images, which are the same size as the center image CI and are upper, lower, left, and right with respect to the center image CI, are set as peripheral images ((a)). reference). Then, the synthesis unit 34 calculates the density average value of the four peripheral images, and replaces the calculated density average value with the density value of the center image CI. As a result, the four peripheral images are combined with the center image CI. Alternatively, the synthesizing unit 34 may set eight surrounding images as the peripheral images with respect to the central image CI (see (b)), and replace the density average value of the eight peripheral images with the density value of the central image CI. Thus, eight peripheral images are combined with the center image CI.

When the defective image 21 is a color image, the combining unit 34 calculates an average value of RGB (Red, Green, Blue), and calculates a density average value based on the average value. Alternatively, the combining unit 34 calculates an average value for each of the R image, the G image, and the B image, and calculates based on each average value.

Here, it is considered that an image of an area without a defect exists around the defect image. Therefore, it is possible to repair the defective image by determining the image of the area without the defect around the defective image as the peripheral image and combining the peripheral image with the defective image. Therefore, the good image 22 can be easily generated from the defective image 21.

FIG. 3 shows an example in which the density value of the center image CI, which is the designated defect image, is replaced with the density average value of four or eight peripheral images and synthesized, but the present invention is not limited to this. The combining unit 34 may combine the designated defect image with the determined peripheral image by Poisson image combining (Poisson Image Editing). As a result, the defect image and the peripheral image can be blended (blending), and it is possible to generate the non-defective image 22 in which the boundary of the original defect image is smooth (seamless).

In the present application, “synthesis” of images is not limited to the meaning of combining two or more images into one image, and one image is copied to another image in two or more images. That is, it includes replacing another image with the average value of the density of one image, and mixing one image with another image.

Returning to FIG. 1, each function of the control unit 30 can be realized by a program executed by a computer (microprocessor). Therefore, each function of the control unit 30 can be realized by hardware, software, or a combination of hardware and software, and is not limited to any one of the cases.

When each function of the control unit 30 is realized by software or a combination of hardware and software, the processing can be executed by multitasking, multithreading, or both multitasking and multithreading. It is not limited to such a case.

The imaging device 60 is configured to capture an image and record it as data. The imaging device 60 is a digital camera, and includes, for example, optical components such as a lens and electronic components such as an imaging device (light receiving device). Note that the optical system component may include a plurality of lenses. The electronic component may include a light emitting device such as a flash. The imaging device 60 outputs the captured image to the arithmetic device 50 via the input / output I / F 10. The control unit 30 performs necessary processing on the image input from the imaging device 60 to generate a file of the non-defective product image or the defective product image 21, and causes the storage unit 20 to store the file of the defective product image 21.

The input device 70 is configured so that information can be input by an operation of a user (user). The input device 70 includes, for example, a keyboard, a keypad, a mouse, a trackball, a touch panel, a microphone, and the like. It is possible to do. For example, when the user operates a keyboard, a keypad, a mouse, a trackball, a touch panel, a microphone, and the like (including a voice operation using a microphone), the input device 70 transmits data or a signal corresponding to the operation. The data is output to the arithmetic unit 50 via the input / output I / F 10. When the control unit 30 generates data based on the data or the signal, it becomes possible to input information to the arithmetic unit 50.

The output device 80 is configured to output information. The output device 80 includes, for example, a display device such as a liquid crystal display, an EL (Electro Luminescence) display, and a plasma display. For example, the output device 80 can output information by displaying image data on a display device.

Next, a first example of the operation of the image processing apparatus 100 according to the present embodiment will be described with reference to FIGS. FIG. 4 is a flowchart illustrating a first example of the schematic operation of the image processing apparatus 100 shown in FIG. FIG. 5 is a diagram illustrating a defective product image 21 of the image processing apparatus 100 shown in FIG. FIG. 6 is a diagram illustrating a non-defective image 22 of the image processing apparatus 100 illustrated in FIG.

The image processing apparatus 100 executes the non-defective image generation processing S200 shown in FIG. 3 when the program is activated by, for example, a user operation. In the first embodiment, an example in which “automatic combination” is set as the “mode” on the setting screen 310 will be described.

First, the setting unit 31 outputs the setting screen 310 shown in FIG. 2 to the output device 80 and displays it (S201). As a result, parameters can be input.

Next, when the user inputs a folder name and a file name on the setting screen 310 via the input device 70 and presses the read button, the setting unit 31 stores the data in the storage unit according to the input folder name and the file name. The defective image 21 stored in the storage unit 20 is read, and the read defective image 21 is output to the output device 80 and displayed together with the setting screen 310 (S202).

Next, the designation unit 32 displays a pointer on the defective product image 21 (S203). Thus, a defect image included in the defective product image 21 can be specified.

Next, based on the operation of the user via the input device 70, the specifying unit 32 specifies a defect image corresponding to the defect in the defective product image 21 (S204). For example, as shown in FIG. 5, when the defective product image 21 includes a linear defect image 21a, the user moves the pointer P1 displayed on the defective product image 21 using the input device 70, and moves the pointer P1. By overlapping with a part of the defect image 21a, the specifying unit 32 specifies the defect image 21a.

Next, the determination unit 33 determines the peripheral image of the defect image 21a specified in Step S204 (S205). In the case of the example shown in FIG. 5, by moving the pointer P1 by a user's operation so that the pointer P1 follows the defect image 21a, the determination unit 33 determines the peripheral image based on the moving direction of the pointer P1. To determine. That is, for example, when the pointer P1 moves in the vertical direction of the defective product image 21, the determination unit 33 determines the images in the left and right regions of the pointer P1 as peripheral images. On the other hand, for example, when the pointer P1 is moved in the left-right direction of the defective product image 21, the determination unit 33 determines the image in the area above and below the pointer P1 as the peripheral image. In this manner, by determining the peripheral image based on the moving direction of the pointer P1, the peripheral image based on the moving direction of the pointer P1 is automatically determined without selecting from the images existing around the defective image 21a. You. Therefore, the good image 22 can be easily generated from the defective image 21.

Note that the determination unit 33 may determine the peripheral image based on the moving direction of the pointer P1 and from the image on the center side of the defective image 21. In the example shown in FIG. 5, the linear defect image 21a extends in the vertical direction, and one end (the upper end in FIG. 4) is located on the left side when viewed from the center of the defective product image 21, and the other end (in FIG. (Lower end) is located on the right side when viewed from the center of the defective product image 21. When the pointer P1 is moved by following the defective image 21a, the determination unit 33 determines the image in the area on the right side of the pointer P1 as the peripheral image at one end of the defective image 21a, and the other end of the defective image 21a halfway. In, the image in the area on the side of the pointer P1 is determined as the peripheral image. Generally, it is considered that the possibility that a defect exists at the center of the defective product image 21 is smaller. Therefore, the defective image 21a can be easily repaired by determining the peripheral image from the image on the center side of the defective product image 21 based on the moving direction of the pointer P1.

Next, the combining unit 34 combines the peripheral image determined in step S205 with the defect image 21a specified in step S204 (S206). In the case of the above-described example, the combining unit 34 combines the images of the left and right regions of the pointer P1 with the defect image 21a by moving the pointer P1 downward so as to follow the linear defect image 21a. As a result, the defect image 21a shown in FIG. 5 is repaired as shown in FIG.

Next, when the “folder name” and “file name” of the setting screen 310 are input by the user via the input device 70 and the save button is pressed, the combining unit 34 displays the input folder name and file name. The restored defective image 21 is stored in the storage unit 20 as a good image 22 (S207).

(4) After step S207, the control unit 30 ends the non-defective image generation processing S200.

In the first embodiment, an example is shown in which the defective image 21 has one defect image 21a corresponding to the defect, but the present invention is not limited to this. For example, when the defective image 21 includes a plurality of defective images 21a, the processing from step S203 to step S206 may be repeated by the number of defective images 21a in the non-defective image generation processing S200.

Next, a second example of the operation of the image processing apparatus 100 according to the present embodiment will be described with reference to FIGS. FIG. 7 is a flowchart illustrating a second example of the schematic operation of the image processing apparatus 100 illustrated in FIG. FIG. 8 is a diagram illustrating a peripheral image in a second example of the schematic operation of the image processing apparatus 100 shown in FIG.

The image processing apparatus 100 executes a non-defective image generation process S250 shown in FIG. 7 when the program is started by, for example, a user operation. In the second embodiment, an example will be described in which “synthesis” is set as the “mode” of the setting screen. In the second embodiment, the same parts as those in the above-described first embodiment are denoted by the same reference numerals, and description thereof will be omitted as appropriate.

Steps S201 to S204 are the same as those in the first embodiment described above, and thus description thereof is omitted. After step S204, the determination unit 33 displays a peripheral pointer on the defective product image 21 (S251). The peripheral pointer is for designating a widened area, similarly to the pointer P1 described above. The peripheral pointer is displayed at a position in a predetermined direction with respect to the pointer P1. Therefore, the peripheral pointer moves together with the pointer P1. The setting unit 31 sets the size of the peripheral pointer based on the value input to “paint radius” on the setting screen 310 via the input device 70 by the user. This makes it possible to determine a peripheral image having a desired size.

Next, the determination unit 33 determines a peripheral image using the peripheral pointer (S252). For example, as shown in FIG. 8, the determining unit 33 first displays the peripheral pointer P2 on the pointer P1 (see (a)). In response to a user operation via the input device 70, for example, a right click of a mouse, the determination unit 33 moves the position of the peripheral pointer P2 to the upper right of the pointer P1 (see (b)) and to the right of the pointer P1 ((c)). Reference), lower right of pointer P1 (see (d)), lower pointer P1 (see (e)), lower left of pointer P1 (see (f)), left of pointer P1 (see (g)), pointer P1 In the upper left (see (h)). As described above, by determining the peripheral image by the peripheral pointer P2 displayed at a position in the predetermined direction with respect to the pointer P1, it is possible to select an image of a region where no defect exists around the defect image 21a. Therefore, the good image 22 can be more easily generated from the defective image 21.

Steps S206 and S207 performed after step S252 are the same as those in the first embodiment described above, and thus description thereof will be omitted.

The exemplary embodiments of the present invention have been described above. According to the image processing apparatus 100, the image processing method, and the image processing program according to the embodiment of the present invention, the determined peripheral image is combined with the designated defect image 21a. Here, it is considered that an image of a region without a defect exists around the defect image 21a. Therefore, it is possible to repair the defect image 21a by determining an image of a region without a defect around the defect image 21a as the peripheral image and combining the peripheral image with the defect image 21a. Therefore, the good image 22 can be easily generated from the defective image 21.

The embodiments described above are intended to facilitate understanding of the present invention, and are not intended to limit the present invention. The components included in the embodiment and their arrangement, material, condition, shape, size, and the like are not limited to those illustrated, but can be appropriately changed. It is also possible to partially replace or combine the configurations shown in different embodiments.

(Appendix)
1. A designation unit (32) for designating a defect image (21a) corresponding to a defect in a defective product image (21) obtained by photographing a defective product including a defect;
A determining unit (33) for determining a peripheral image from images existing around the designated defect image (21a);
A combining unit (34) for combining the determined peripheral image with the designated defect image (21a).
Image processing device (100).
6. A designation step of designating a defect image (21a) corresponding to a defect in a defective product image (21) obtained by photographing a defective product including a defect;
A determination step of determining a peripheral image from images existing around the designated defect image (21a);
Synthesizing the determined peripheral image with the designated defect image (21a).
Image processing method.
11. An image processing program to be executed by a computer,
A designation step of designating a defect image (21a) corresponding to a defect in a defective product image (21) obtained by photographing a defective product including a defect;
A determination step of determining a peripheral image from images existing around the designated defect image (21a);
Synthesizing the determined peripheral image with the designated defect image (21a).
Image processing program.

Reference numeral 20: storage unit, 21: defective image, 21a: defective image, 22: good image, 30: control unit, 31: setting unit, 32: specifying unit, 33: determining unit, 34: combining unit, 40: bus, 50 arithmetic unit, 60 imaging device, 70 input device, 80 output device, 100 image processing device, 310 setting screen, CI central image, P1 pointer, P2 peripheral pointer, S200, S250 non-defective Image generation processing.

Claims

A designation unit that designates a defect image corresponding to the defect in a defective product image of a defective product including a defect,
A determining unit that determines a peripheral image from an image present around the designated defect image;
A synthesizing unit that synthesizes the determined peripheral image with the specified defect image,
Image processing device.
The specifying unit specifies the defective image by a pointer displayed on the defective image,
The determining unit determines the peripheral image based on a moving direction of the pointer,
The image processing device according to claim 1.
The determining unit is configured to determine the peripheral image from an image on the center side of the defective image based on a moving direction of the pointer,
The image processing device according to claim 2.
The determining unit determines the peripheral image by a peripheral pointer displayed at a position in a predetermined direction with respect to the pointer in the defective product image,
The image processing device according to claim 2.
Further comprising a setting unit for setting the size of the peripheral pointer,
The image processing device according to claim 4.
A designation step of designating a defect image corresponding to the defect in a defective product image of a defective product including a defect,
A determining step of determining a peripheral image from an image present around the specified defect image;
Synthesizing the determined peripheral image with the specified defect image,
Image processing method.
The specifying step includes specifying the defective image by a pointer displayed on the defective product image,
The determining step includes determining the peripheral image based on a moving direction of the pointer,
The image processing method according to claim 6.
The determining step is based on a moving direction of the pointer, and includes determining the peripheral image from an image on the center side of the defective image.
The image processing method according to claim 7.
The determining step includes determining the peripheral image by a peripheral pointer displayed at a position in a predetermined direction with respect to the pointer in the defective product image,
The image processing method according to claim 7.
The method further includes a setting step of setting a size of the peripheral pointer,
The image processing method according to claim 9.
An image processing program to be executed by a computer,
A designation step of designating a defect image corresponding to the defect in a defective product image of a defective product including a defect,
A determining step of determining a peripheral image from an image present around the specified defect image;
Synthesizing the determined peripheral image with the specified defect image,
Image processing program.