Appearance inspection device, appearance inspection method, and appearance inspection program

Abstract

According to the present invention, a conversion equation calculation unit 81 calculates, on the basis that a marker-attached defect image in which a marker of a predetermined size that can be recognized regardless of the color of the appearance of an object to be inspected and a defect of the object to be inspected are image-captured, an equation of conversion from the size of the marker-attached defect image to the actual size. A defect type determination unit 82 determines the type of defect included in the marker-attached defect image, by using a model that detects a defect of the object to be inspected from the image and determines the type of the defect. A defect measuring unit 83 measures the size of the defect included in the marker-attached defect image by using the conversion equation. A defect content output unit 84 outputs the type of the determined defect and the measured defect size.

Description

[Technical field]

[0001] The present invention relates to an appearance inspection device, an appearance inspection method, and an appearance inspection program for inspecting the appearance of a product. [Background technology]

[0002] Painted products such as automobile bodies can have various defects during the manufacturing and distribution processes. For example, defects include unevenness in the paint caused by dirt getting caught in the paint line, uneven coloring when painting, scratches during painting or transportation, etc. Inspection for such defects is generally carried out during manufacturing or before sale by a dealer.

[0003] For example, Patent Document 1 describes a surface inspection device that inspects defects on the surface of an automobile. The surface inspection device described in Patent Document 1 irradiates light onto an inspected surface of an object to be inspected, forms a received-light image based on the light reflected from the inspected surface, and detects defects present on the inspected surface based on the received-light image. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 11-63959 Summary of the Invention [Problem to be solved by the invention]

[0005] The surface inspection device described in Patent Document 1 detects defects by forming a received light image on the production line. In other words, by placing this surface inspection device at a specific position on the production line, it is possible to obtain the location of defects, the details of the defects, the size of the defects, etc.

[0006] On the other hand, when inspecting the appearance at a location away from the production line (such as a retail store), defect detection is usually performed manually. For example, when a defect is detected at a retail store, an image of the defective area is generally taken manually at the retail store, and the manufacturer that obtained the image determines the type and size of the defect from the image. However, unlike a production line, the circumstances under which the defect is photographed are not fixed, so the image of the defect taken will differ depending on the position and angle at which the defect is photographed. Therefore, it takes a lot of time to determine the nature of the defect from such an image.

[0007] It is difficult for each retailer to introduce a surface inspection device such as that described in Patent Document 1. For this reason, it is preferable to be able to acquire images including defects in a simple manner and to automate the work of inspecting the contents of the defects, such as the type and size of the defects, using the images.

[0008] Therefore, the present invention aims to provide an appearance inspection device, an appearance inspection method, and an appearance inspection program that can reduce the amount of work required to inspect the contents of defects occurring in the appearance of an object being inspected from images containing defects that can be obtained by a simple method. [Means for solving the problem]

[0009] The appearance inspection apparatus according to the present invention comprises: a conversion equation calculation means for calculating a conversion equation from the size of the marked defect image to an actual size based on a marked defect image obtained by capturing an image of a defect on an object to be inspected and a marker of a predetermined size that is affixed to the object to a position that does not overlap the defect and is within a predetermined distance from the defect; a defect type determination means for determining the type of a defect contained in the marked defect image using a model that detects a defect on the object to be inspected from the image and determines the type of the defect; a defect measurement means for measuring the size of the defect contained in the marked defect image using the conversion equation; and a defect content output means for outputting the determined type of the defect and the measured size of the defect, wherein the defect content output means The defect is identified based on a defect occurrence master in which the defect occurrence process is associated with each type of defect. According to the type of defect judged handleThe process in which defects occur is the transportation process and the manufacturing process. The process The present invention is characterized in that it outputs a generation process including the above.

[0010] The appearance inspection method according to the present invention includes the steps of: calculating a conversion equation from the size of the marked defect image to an actual size based on an image of a defect on an object to be inspected, the image showing a defect on the object to be inspected and a marker of a predetermined size that is affixed to the object to a position that does not overlap the defect and is within a predetermined distance from the defect; determining the type of the defect included in the marked defect image using a model that detects the defect on the object to be inspected from the image and determines the type of the defect; measuring the size of the defect included in the marked defect image using the conversion equation; The defect is identified based on a defect occurrence master in which the defect occurrence process is associated with each type of defect. The type of defect judged and the size of the defect measured, and the type of defect judged handle The process in which defects occur is the transportation process and the manufacturing process. The process The present invention is characterized in that it outputs a generation process including the above.

[0011] The appearance inspection program according to the present invention causes a computer to execute a conversion equation calculation process for calculating a conversion equation from the size of the marked defect image to an actual size based on an image of a defect on an object to be inspected and a marker of a predetermined size that is affixed to a position on the object to be inspected that does not overlap the defect and is within a predetermined distance from the defect; a defect type determination process for determining the type of a defect contained in the marked defect image using a model that detects a defect on the object to be inspected from the image and determines the type of the defect; a defect measurement process for measuring the size of the defect contained in the marked defect image using the conversion equation; and a defect content output process for outputting the determined type of the defect and the measured size of the defect, wherein in the defect content output process: The defect is identified based on a defect occurrence master in which the defect occurrence process is associated with each type of defect. According to the type of defect judged handle The process in which defects occur is the transportation process and the manufacturing process. The process The present invention is characterized in that it outputs a generation process including the above. Effect of the Invention

[0012] According to the present invention, it is possible to reduce the number of steps required to inspect the contents of defects occurring in the external appearance of an object to be inspected from an image including the defects that can be acquired by a simple method. [Brief description of the drawings]

[0013] [Figure 1] 1 is a block diagram showing an example of the configuration of a first embodiment of a visual inspection apparatus according to the present invention; [Diagram 2] FIG. 11 is an explanatory diagram showing an example of a marker. [Diagram 3] 11 is an explanatory diagram showing an example of a process for capturing a defect image with a marker; FIG. [Figure 4] 4 is a flowchart showing an example of the operation of the visual inspection apparatus according to the first embodiment; [Diagram 5] FIG. 11 is a block diagram showing an example of the configuration of a second embodiment of a visual inspection device according to the present invention. [Figure 6] 10 is a flowchart showing an example of the operation of the visual inspection apparatus according to the second embodiment. [Figure 7] 1 is a block diagram showing an outline of a visual inspection apparatus according to the present invention; DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0014] Hereinafter, an embodiment of the present invention will be described with reference to the drawings.

[0015] Embodiment 1. 1 is a block diagram showing an example of the configuration of a first embodiment of a visual inspection apparatus according to the present invention. A visual inspection apparatus 20 of this embodiment is connected to an imaging apparatus 10 via a communication network.

[0016] The imaging device 10 is a device that captures an external appearance of an object to be inspected and generates an image. The imaging device 10 includes an imaging section 11 and a transmission section 12. As a prerequisite for capturing an image of the external appearance of the object to be inspected, a user affixes a marker near a defect that has occurred on the object to be inspected. The vicinity of the defect refers to a position that does not overlap the defect and is within a predetermined distance from the defect, for example, a position within 1 cm from the defect.

[0017] The marker to be affixed is a marker of a predetermined size that can be recognized regardless of the color of the exterior of the object to be inspected. For example, if the object to be inspected is an automobile, the marker to be affixed is a marker that can be recognized regardless of the body color (painted color), and its size is predetermined. Since an image including the marker and defects of the object to be inspected is captured by the imaging unit 11, the marker is preferably approximately the same size as the defects that may occur, and is formed, for example, as a square of about 2 cm in length and width, or a circle of about 2 cm in diameter.

[0018] FIG. 2 is an explanatory diagram showing an example of a marker. The marker shown in FIG. 2 is an example of a marker that can be recognized regardless of the color of the appearance of the object to be inspected. Marker 41 is a circular marker using two colors, with each semicircle being represented in a different color. Marker 42 is a circular marker using four colors, with each of the four equal parts of the circle being represented in a different color. Marker 43 is a marker in which a square area inscribed in a circle and an area other than the square within the circle are each represented in a different color. Marker 44 is a marker in which a slightly smaller square is placed inside a square, with the inner square area and the area of ​​the outer square area excluding the inner square area being each represented in a different color.

[0019] The markers shown in Fig. 2 are merely examples, and the form of the markers is not limited to the example shown in Fig. 2. Specifically, the markers are formed using two or more colors so that a part or all of a square or circle can be identified with each of at least two colors. For ease of illustration, the markers shown in Fig. 2 are shown in white and black or in white and black shading, but the white or black and the shaded areas may each be shown in a color other than white and black.

[0020] It is also preferable to use a marker that allows easy calculation of a conversion equation by conversion equation calculation unit 23, which will be described later. For example, by using marker 41 or marker 42 as exemplified in Fig. 2, it becomes possible to use a diameter to derive a conversion equation. Also, by using marker 43 or marker 44 as exemplified in Fig. 2, it becomes possible to use the length of one side of the central square to derive a conversion equation.

[0021] The imaging unit 11 captures an image of the marker and the defect of the object to be inspected. Hereinafter, the image of the marker and the defect of the object to be inspected is referred to as a "defect image with marker." In other words, the defect image with marker can be said to be an image captured with a marker attached near the defect.

[0022] Fig. 3 is an explanatory diagram showing an example of a process for capturing a defect image with a marker. As shown in Fig. 3, a user 54 attaches a marker 52 near a defect 53 of an automobile 50, which is an object to be inspected, and the imaging unit 11 captures a close-up image of the defect and the marker in response to an operation by the user, thereby capturing an image of the defect 51 with the marker.

[0023] The transmitting unit 12 transmits the defect image with the marker to the appearance inspection device 20 .

[0024] The appearance inspection device 20 includes a storage unit 21 , an input unit 22 , a conversion equation calculation unit 23 , a defect area extraction unit 24 , a defect type determination unit 25 , a defect measurement unit 26 , and an output unit 27 .

[0025] The storage unit 21 stores various information necessary for the visual inspection device 20 to perform processing. Specifically, the storage unit 21 stores a model used for processing by the defect type determination unit 25 described later. The model used in this embodiment is a model that detects defects in an inspected object from an image and determines the type of the defect, and a model generated in advance by machine learning or the like is stored in the storage unit 21. Note that any learning method may be used to generate the model, and the form of the model is not particularly limited. The storage unit 21 may also store features of a marker to be affixed.

[0026] The input unit 22 accepts an input of a defect image with a marker captured by the imaging device 10. The input unit 22 may directly accept an input of a defect image with a marker from the transmission unit 12 of the imaging device 10, or may accept an input of a defect image with a marker via a storage (not shown).

[0027] The conversion equation calculation unit 23 calculates a conversion equation from the size of the marked defect image to the actual size based on the marked defect image. Specifically, the conversion equation calculation unit 23 calculates the ratio of the actual size to one pixel in the image based on the marked defect image. The conversion equation calculation unit 23 may calculate, for example, a conversion equation between pixels in the image and the actual size (for example, in mm).

[0028] In this embodiment, the size of the marker included in the marked defect image is predetermined, so the conversion equation calculation unit 23 extracts how many pixels the predetermined size of the marker is represented in the image, and calculates the conversion equation based on the correspondence between the extracted number of pixels and the size of the marker.

[0029] The defective area extraction unit 24 extracts an image including the marker and within a predetermined range from the marker from the marked defect image as an image including a defective portion. For example, the defective area extraction unit 24 may predetermine an extraction range within several hundred pixels vertically and horizontally from the center of the marker, and extract an image within the range from the center of the marker from the marked defect image as an image including a defective portion.

[0030] Depending on the shape of the object to be inspected, disturbance light or the like may be reflected, resulting in an image that is different from the actual state of the object to be inspected. For example, since the body of an automobile includes an R-shape, disturbance light may be transferred to the image when a wide area including a defect is imaged. On the other hand, in this embodiment, the defect area extraction unit 24 extracts an image including a defective portion, so that the accuracy with which the defect type determination unit 25 described later determines defects can be improved.

[0031] In addition, if the marked defect image is an image captured in an appropriate range, it is not necessary to extract an image including the defective portion again. Therefore, in this case, the appearance inspection device 20 does not need to include the defective area extraction unit 24.

[0032] The defect type determination unit 25 determines the type of the defect included in the marked defect image by using the model (i.e., a model for detecting a defect in an inspected object from an image and determining the type of the defect) stored in the storage unit 21. Note that, when an image including a defective portion is extracted by the defect area extraction unit 24, the defect type determination unit 25 may determine the type of the defect included in the extracted image.

[0033] The defect measuring unit 26 measures the size of the defect included in the marked defect image by using the conversion equation calculated by the conversion equation calculation unit 23. For example, if the object to be inspected has a scratch as a defect, the defect measuring unit 26 may measure the length of the scratch included in the marked defect image by using the conversion equation.

[0034] The output unit 27 outputs the determined type of defect and the measured size of the defect. The output unit 27 may display the type and size of the defect on a display device (not shown), or may notify a predetermined notification destination by e-mail or the like.

[0035] The input unit 22, the conversion formula calculation unit 23, the defect area extraction unit 24, the defect type determination unit 25, the defect measurement unit 26, and the output unit 27 are realized by a computer processor (e.g., a CPU (Central Processing Unit), a GPU (Graphics Processing Unit)) that operates according to a program (appearance inspection program).

[0036] For example, the program may be stored in the storage unit 21, and the processor may read the program and operate as the input unit 22, the conversion formula calculation unit 23, the defect area extraction unit 24, the defect type determination unit 25, the defect measurement unit 26, and the output unit 27 in accordance with the program. Furthermore, the functions of the visual inspection apparatus 20 may be provided in a SaaS (Software as a Service) format.

[0037] Also, the input section 22, the conversion formula calculation section 23, the defect area extraction section 24, the defect type determination section 25, the defect measurement section 26, and the output section 27 may each be realized by dedicated hardware. Also, a part or all of the components of each device may be realized by a general-purpose or dedicated circuit, processor, etc., or a combination of these. These may be configured by a single chip, or may be configured by multiple chips connected via a bus. A part or all of the components of each device may be realized by a combination of the above-mentioned circuits, etc., and programs.

[0038] Furthermore, when some or all of the components of the visual inspection apparatus 20 are realized by a plurality of information processing devices, circuits, etc., the plurality of information processing devices, circuits, etc. may be arranged in a centralized manner or in a distributed manner. For example, the information processing devices, circuits, etc. may be realized as a client-server system, a cloud computing system, etc., in a form in which each is connected via a communication network.

[0039] The storage unit 21 is realized by, for example, a magnetic disk.

[0040] Next, an example of the operation of this embodiment will be described with reference to Fig. 4, which is a flow chart showing an example of the operation of the visual inspection apparatus of this embodiment.

[0041] When the input unit 22 receives the input of the marked defect image, the conversion equation calculation unit 23 calculates a conversion equation from the image to the actual size based on the marked defect image (step S11). The defect type determination unit 25 determines the type of defect included in the marked defect image using a model for determining the type of defect from an image (step S12). Note that the defect type determination unit 25 may determine the type of defect based on an image including the defective portion extracted by the defect area extraction unit 24.

[0042] The defect measuring unit 26 measures the size of the defect included in the marked defect image by using a conversion formula (step S13). Then, the output unit 27 outputs the determined type of the defect and the measured size of the defect (step S14).

[0043] As described above, in this embodiment, the conversion formula calculation unit 23 calculates a conversion formula based on the marked defect image, and the defect type determination unit 25 determines the type of defect included in the marked defect image using a model for determining the type of defect from the image. The defect measurement unit 26 measures the size of the defect included in the marked defect image using the conversion formula, and the output unit 27 outputs the determined type of defect and the measured size of the defect. This reduces the amount of work required to inspect the contents of defects occurring in the appearance of the inspected object from an image containing defects that can be obtained by a simple method. In addition, since the determination criteria are clearer than the vague manual confirmation used until now, it is also possible to reduce unnecessary repairs for defects occurring in the appearance.

[0044] Embodiment 2. Next, a second embodiment of the visual inspection apparatus of the present invention will be described. In the second embodiment, the subsequent action to be taken is automatically determined based on the acquired defect details (defect type and size).

[0045] 5 is a block diagram showing an example of the configuration of a second embodiment of a visual inspection apparatus according to the present invention. Similar to the first embodiment, a visual inspection apparatus 30 of this embodiment is connected to an imaging apparatus 10 via a communication network.

[0046] Appearance inspection apparatus 30 includes a memory unit 31, an input unit 22, a conversion formula calculation unit 23, a defect area extraction unit 24, a defect type determination unit 25, a defect measurement unit 26, a correspondence determination unit 32, and an output unit 33. That is, appearance inspection apparatus 30 of the present embodiment differs from appearance inspection apparatus 20 of the first embodiment in that it further includes a correspondence determination unit 32, and includes a memory unit 31 and an output unit 33 instead of the memory unit 21 and the output unit 27.

[0047] The storage unit 31 stores a rule master that specifies the response content for the type of defect and the size of the defect, in addition to the content stored in the storage unit 21 of the first embodiment. For example, if the object to be inspected is an automobile, the response content may be the manufacturer's warranty content for the defect (for example, whether the manufacturer provides a warranty and pays for repairs to the dealer, etc.). The warranty content is determined in advance according to the type of defect and the size of the defect. Furthermore, this rule master may be determined for each object to be inspected and for each responder.

[0048] Furthermore, the storage unit 31 may store a defect occurrence master that associates each type of defect with the process in which the defect occurred. For example, in the case of an automobile, if the defect is a line scratch, it can be determined that the defect occurred during the transportation process (during the transportation of the vehicle from the factory to the dealer), and if the defect is a dust particle or uneven paint, it can be determined that the defect occurred during the manufacturing process. These associations may be held in the defect master.

[0049] The action determination unit 32 determines the action to be taken according to the output defect type and defect size based on the rule master stored in the storage unit 31 .

[0050] The output unit 33 outputs the determined countermeasure content in addition to the output content by the output unit 27 of the first embodiment. The output unit 33 may also output the defect occurrence process based on the defect type based on the defect occurrence master. This makes it possible to improve the occurrence process.

[0051] The input unit 22, the conversion formula calculation unit 23, the defect area extraction unit 24, the defect type determination unit 25, the defect measurement unit 26, the correspondence determination unit 32, and the output unit 33 are realized by a processor of a computer that operates according to a program (visual inspection program). The storage unit 31 is realized by, for example, a magnetic disk or the like.

[0052] Next, an operation example of this embodiment will be described. Fig. 6 is a flowchart showing an operation example of the visual inspection device of this embodiment. Note that the processes from step S11 to step S13, in which the input unit 22 accepts the input of a defect image with a marker, determines the type of the defect, and measures the size of the defect, are the same as the operation exemplified in Fig. 4.

[0053] The action determination unit 32 determines the action content according to the output defect type and defect size based on the rule master stored in the storage unit 31 (step S21). Then, the output unit 27 outputs the determined defect type, the measured defect size, and the action content (step S22).

[0054] As described above, in this embodiment, the action determination unit 32 determines the action content according to the output defect type and defect size based on the rule master. Therefore, in addition to the effect of the first embodiment, it is possible to automate decision-making regarding defects.

[0055] Next, an outline of the present invention will be described below. Fig. 7 is a block diagram showing an outline of a visual inspection device according to the present invention. An appearance inspection apparatus 80 (e.g., appearance inspection apparatus 20) according to the present invention includes a conversion equation calculation unit 81 (e.g., conversion equation calculation unit 23) that calculates a conversion equation from the size of a marked defect image to an actual size, based on a marked defect image in which a marker (e.g., markers 41-44 illustrated in FIG. 2) of a predetermined size that can be recognized regardless of the appearance color of the object being inspected (e.g., an automobile) (e.g., the body color of the automobile, the paint color) and a defect (e.g., a scratch, dust particles, color unevenness, etc.) of the object being inspected is captured; a defect type determination unit 82 (e.g., defect type determination unit 25) that determines the type of defect included in the marked defect image using a model that detects a defect of the object being inspected from the image and determines the type of the defect; a defect measurement unit 83 (e.g., defect measurement unit 26) that measures the size of the defect included in the marked defect image using the conversion equation; and a defect content output unit 84 (e.g., output unit 27) that outputs the determined type of defect and the measured size of the defect.

[0056] With this configuration, it is possible to reduce the number of steps required to inspect the contents of defects occurring in the appearance of the object to be inspected from images containing defects that can be obtained by a simple method. In addition, since the judgment criteria are clearer than the vague manual confirmation used until now, it is also possible to reduce unnecessary repairs for defects occurring in the appearance.

[0057] The marked defect image is an image captured with a marker attached near the defect, and the visual inspection device 80 may include a defect area extraction unit (e.g., defect area extraction unit 24) that extracts an image including the marker and within a predetermined range from the marked defect image as an image including a defect portion. Then, the defect type determination unit 25 may determine the type of the defect included in the extracted image. Such a configuration can improve the accuracy of determining the type of the defect.

[0058] Furthermore, the appearance inspection device 80 (for example, the appearance inspection device 30) may include a rule master storage unit (for example, the storage unit 31) that stores a rule master that specifies the response content for the defect type and the defect size, and a response determination unit (for example, the response determination unit 32) that determines the response content according to the output defect type and defect size based on the rule master. Such a configuration makes it possible to automate decision-making regarding defects.

[0059] Furthermore, the defect content output section 84 (for example, the output section 33) may output the process in which the defect occurred based on the type of the defect.

[0060] More specifically, the marker may be formed using two or more colors so that a part or the whole of a square or circle can be specified with each of at least two colors.

[0061] In addition, the appearance inspection apparatus 80 may be provided with an input section (e.g., input section 22) that accepts input of a marked defect image from an imaging device (e.g., imaging device 10) that captures a marked defect image including a marker and a non-inspected object in response to user operation.

[0062] Although the present invention has been described above with reference to the embodiments and examples, the present invention is not limited to the above-mentioned embodiments and examples. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention.

[0063] This application claims priority based on Japanese Patent Application No. 2019-192625, filed on October 23, 2019, the disclosure of which is incorporated herein in its entirety. [Explanation of symbols]

[0064] 10. Imaging device 11 Imaging unit 12 Transmitter 20,30 Visual inspection equipment 21,31 Storage section 22 Input section 23 Conversion formula calculation section 24 Defective area extraction section 25 Defect type determination section 26 Defect Measurement Department 27,33 Output section 32 Response determination unit

Claims

1. a conversion equation calculation means for calculating a conversion equation from the size of a marked defect image to an actual size based on an image of a marked defect in an object to be inspected and a marker of a predetermined size that is affixed to a position on the object to be inspected that does not overlap the defect and is within a predetermined distance from the defect; a defect type determining means for determining a type of a defect included in the marked defect image by using a model for detecting a defect of an object to be inspected from the image and determining a type of the defect; a defect measuring means for measuring a size of a defect included in the marked defect image by using the conversion formula; a defect content output means for outputting the determined defect type and the measured defect size, The defect content output means outputs a defect occurrence process including a transportation process and a manufacturing process, the defect occurrence process corresponding to the determined defect type being specified based on a defect occurrence master in which the defect occurrence process is associated with each defect type. A visual inspection apparatus comprising:

2. a defect area extracting means for extracting an image including the marker and within a predetermined range from the marked defect image as an image including a defect portion, The defect type determining means determines the type of the defect contained in the extracted image.

2. The visual inspection apparatus according to claim 1.

3. a rule master storage means for storing a rule master that specifies the type and size of a defect and indicates the manufacturer's warranty against the defect; and a response determination means for determining a response depending on the output defect type and defect size based on the rule master.

3. The visual inspection apparatus according to claim 1 or 2.

4. The marker is formed as a figure including a part or a whole of a circle that can be recognized regardless of the color of the appearance of the object to be inspected. The visual inspection apparatus according to any one of claims 1 to 3.

5. The marker is formed so that two or more colors are used and a part or the whole of a square or a circle can be identified with each of at least two colors. The visual inspection apparatus according to any one of claims 1 to 4.

6. The apparatus further includes an input unit for receiving an input of a defect image with a marker from an imaging device that captures a defect image with a marker including the marker and the object to be inspected in response to a user's operation. The visual inspection apparatus according to any one of claims 1 to 5.

7. calculating a conversion formula from the size of the marked defect image to an actual size based on an image of the marked defect, the image including a marker and a marker of a predetermined size that is attached to the object at a position that does not overlap the defect and is within a predetermined distance from the defect; determining a type of a defect included in the marked defect image using a model for detecting a defect in an object to be inspected from an image and determining a type of the defect; Using the conversion formula, a size of a defect included in the marked defect image is measured; The type of the determined defect and the measured size of the defect, which are specified based on a defect occurrence master in which each type of defect is associated with a corresponding occurrence process, and the occurrence process of the defect corresponding to the determined type of defect, the occurrence process including a transportation process and a manufacturing process are output. A visual inspection method comprising:

8. extracting an image including the marker and within a predetermined range from the marked defect image as an image including a defective portion; Identifying the type of defect contained in the extracted image The appearance inspection method according to claim 7.

9. On the computer, a conversion equation calculation process for calculating a conversion equation from the size of the marked defect image to the actual size based on an image of the marked defect, the image showing a defect on the object to be inspected and a marker of a predetermined size attached to the object to be inspected at a position that does not overlap the defect and is within a predetermined distance from the defect; a defect type determination process for determining the type of a defect contained in the marked defect image by using a model for detecting a defect of an object to be inspected from the image and determining the type of the defect; a defect measurement process for measuring a size of a defect included in the marked defect image by using the conversion formula; and Executing a defect content output process for outputting the determined defect type and the measured defect size; In the defect content output process, a defect occurrence process corresponding to the determined defect type is output, the defect occurrence process being specified based on a defect occurrence master in which the defect occurrence process is associated with each defect type, the defect occurrence process including a transportation process and a manufacturing process. Visual inspection program for

10. On the computer, executing a defect area extraction process for extracting an image including the marker and within a predetermined range from the marked defect image as an image including a defective portion; In the defect type determination process, the type of defect contained in the extracted image is determined. The visual inspection program according to claim 9.

Images