Image inspection apparatus

Abstract

To provide an image inspection device capable of preventing a defect reflected in a different scale from being overlooked and improving the extraction accuracy of the defect.SOLUTION: An image inspection device includes an image acquisition unit that acquires a captured image obtained by imaging an inspection region with a camera, a camera distance information storage unit that holds camera distance information between the camera and the inspection region, a drawing information storage unit that holds drawing information including dimension information of a roughened surface of the inspection region, a plane development processing unit that converts the captured image of the roughened surface of the inspection region into a plane developed captured image using the camera distance information and the drawing information, an image scale correction unit that calculates an image scale correction value for each roughened surface of the inspection region using the camera distance information and the drawing information and generates a scale corrected image of the plane developed captured image, and a defect extraction processing unit that extracts a defect from the scale corrected image.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an image inspection device. [Background technology]

[0002] Patent Document 1 discloses an inner circumference inspection device for cylindrical containers that includes an illumination unit, an imaging unit, and an image processing unit, and that takes images of the inside of the cylindrical container while rotating the cylindrical container. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2012-26858 Summary of the Invention [Problem to be solved by the invention]

[0004] In Patent Document 1, since the scale of the captured image differs between the front side and the back side of the cylinder in the direction of the cylinder, there is a risk that defects of a specific size cannot be extracted. An object of the present invention is to provide an image inspection apparatus that can prevent defects that appear at different scales from being overlooked and improve the accuracy of defect extraction. [Means for solving the problem]

[0005] An image inspection device in one embodiment of the present invention comprises an image acquisition unit that acquires an image of an inspection area captured by a camera, a camera distance information storage unit that holds camera distance information between the camera and the inspection area, a drawing information storage unit that holds drawing information having dimensional information of the unevenly processed surface of the inspection area, a planar development processing unit that uses the camera distance information and the drawing information to convert the image of the unevenly processed surface of the inspection area into a planar developed image, an image scale correction unit that uses the camera distance information and the drawing information to calculate an image scale correction value for each unevenly processed surface of the inspection area and generate a scale-corrected image of the planar developed image, and a defect extraction processing unit that extracts defects from the scale-corrected image. [Effects of the Invention]

[0006] Therefore, in the present invention, it is possible to prevent defects that appear at different scales from being overlooked, and to improve the accuracy of defect extraction. [Brief explanation of the drawings]

[0007] [Figure 1] 1 is a schematic diagram illustrating an entire image inspection device 1 according to a first embodiment. [Figure 2] 1 is a main flowchart showing the flow of image inspection in the first embodiment. [Figure 3] 3 is a cross-sectional view of a cylindrical hole portion in the first embodiment. FIG. [Figure 4] 4 is a time chart showing the flow of operations of a planar development processing unit and an image scale correction unit in the first embodiment. [Figure 5] 4 is a time chart showing the flow of generating a virtual boundary line image in the first embodiment. [Figure 6] 10 is a time chart showing the flow of acquiring boundary lines of a planarly developed captured image of a captured image that has been rectangularly developed in the circumferential direction in the first embodiment. [Figure 7] 10(a) and 10(b) are diagrams illustrating a method for determining whether an occlusion has occurred in a captured image in the first embodiment. [Figure 8] 10 is a flowchart showing the flow of determining whether occlusion has occurred and calculating an image scale value in the first embodiment. [Figure 9] FIG. 10 is a schematic view of the entire image inspection device of the second embodiment. [Figure 10] 10 is a main flowchart showing the flow of image inspection in the second embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0008] [Embodiment 1] FIG. 1 is a schematic diagram of the entire image inspection device 1 of the first embodiment.

[0009] The image inspection device 1 of the first embodiment includes a hole-lens camera (camera) 2 and a computer 3 . The hole lens camera 2 captures an image of the inside of a cylindrical hole (inspection area) 17a having an uneven surface of a VTC cover 17, which is an object to be inspected. The computer 3 is, for example, a personal computer, and includes a CPU 4 and a memory 5 . The CPU 4 includes a camera communication unit 6, a captured image acquisition unit 7, a plane development processing unit 8, an image scale correction unit 9, and a defect extraction processing unit 10. The camera communication unit 6 controls the image capturing by the hole lens camera 2 to obtain one captured image captured in one shot of the unevenly processed surface inside the cylindrical hole 17a, and the captured image acquisition unit 7 acquires the captured image. In this way, it is sufficient to take a single image of the entire unevenly processed surface inside cylindrical hole 17a in one shot, so that the imaging time can be reduced. The details of the processing by the plane development processing unit 8, the image scale correction unit 9, and the defect extraction processing unit 10 will be described later. The memory 5 includes a captured image storage unit 11 , a camera information storage unit 12 , a drawing information storage unit 13 , an image scale correction value storage unit 14 , a scale-corrected image storage unit 15 , and a defect extraction result storage unit 16 . The captured image memory unit 11 stores the captured image of the inside of the cylindrical hole portion 17a acquired by the captured image acquisition unit 7, the camera information memory unit 12 stores the distance between the hole lens camera 2 and the cylindrical hole portion 17a, the resolution of the hole lens camera 2, etc., the drawing information memory unit 13 stores drawing information having dimensional information (design dimensions, shape data, etc.) of each unevenly processed surface within the cylindrical hole portion 17a, the image scale correction value memory unit 14 stores the image scale correction value, the scale corrected image memory unit 15 stores the scale corrected image generated by the image scale correction unit 9, and the defect extraction result memory unit 16 stores the defect extraction results of the defect extraction processing unit 10.

[0010] FIG. 2 is a main flowchart showing the flow of image inspection in the first embodiment.

[0011] In step S1, the unevenly machined surface inside the cylindrical hole portion 17a is converted into a planar developed captured image using the camera distance information stored in the camera information memory unit 12, the drawing information stored in the drawing information memory unit 13, and the captured image of the unevenly machined surface inside the cylindrical hole portion 17a stored in the captured image memory unit 11, which is captured in one shot. In step S2, since the image is a single image of the entire unevenly machined surface inside cylindrical hole portion 17a captured in one shot, the scale is uneven between the front and back sides of cylindrical hole portion 17a in the cylindrical direction (the further back, the smaller the image appears), so an image scale correction value is calculated for each unevenly machined surface inside cylindrical hole portion 17a from the camera distance information, drawing information, and the planar developed image of the unevenly machined surface inside cylindrical hole portion 17a, and a scale-corrected image of the planar developed image of the unevenly machined surface inside cylindrical hole portion 17a with a uniform scale is generated. In step S3, defects are extracted from the scale-corrected image.

[0012] FIG. 3 is a cross-sectional view of the cylindrical hole portion in the first embodiment.

[0013] The uneven surface of cylindrical hole portion 17a is composed of upper and lower chamfered surfaces 17a1, an upper cylindrical surface 17a2, a grooved surface 17a3, upper and lower grooved side surfaces 17a4, and a lower cylindrical surface 17a5.

[0014] FIG. 4 is a time chart showing the flow of processing by the planar development processing unit and image scale correction unit in the first embodiment.

[0015] In the first block P1, the planar development processing unit 8 obtains a captured image captured in one shot and stored in the captured image storage unit 11. The grid pattern K (calibration image) of the captured image is projected using a laser or the like. In the second block P2, the planar development processing unit 8 converts the acquired captured image into a rectangular image in the circumferential direction to convert it into a planar developed captured image, and corrects the brightness value for each uneven surface within the cylindrical hole portion 17a of the planar developed captured image to process it into an image with uniform brightness. Although the circumferential lengths of the respective unevenly processed surfaces are different, the differences are small, so the planar developed images are used in which the lengths are approximately the same. In the third block P3, an excerpt of the planar developed captured image is shown for the purpose of explanation. In the fourth block P4, the image scale correction unit 9 divides a portion of the planarly developed captured image into cylindrical sections for each unevenly processed surface, and calculates an image scale correction value for each unevenly processed surface from the dimensional information of each unevenly processed surface, the resolution (pixels) of the hole lens camera 2, and the grid pattern K (calibration image) of the captured image so that the captured images of each unevenly processed surface are of a uniform scale. For example, the image scale correction values ​​for each unevenly machined surface are: chamfered surface 17a1: 0.8, upper cylindrical machined surface 17a2: 1.0, grooved surface 17a3: 1.2, grooved side surface 17a4: 0.8, and lower cylindrical machined surface 17a5: 1.4. In the fifth block P5, the image scale correction unit 9 generates divided scale-corrected images for each machining surface at a uniform scale using the image scale correction value for each machining surface. In the sixth block P6, the image scale corrector 9 combines the divided scale-corrected images for each machining surface to generate a scale-corrected image. This makes it possible to prevent defects that appear at different scales from being overlooked, and improve the accuracy of defect extraction. Furthermore, since captured images with a uniform scale can be obtained, it is possible to extract defects taking into account their size. Furthermore, since a captured image with uniform brightness can be obtained, it is possible to prevent overlooking defects due to overexposure or darkness, thereby improving the accuracy of defect extraction.

[0016] FIG. 5 is a time chart showing the flow of generating a virtual boundary line captured image in embodiment 1, and FIG. 6 is a time chart showing the flow of obtaining the boundary line of a planar developed captured image of a captured image that has been rectangularly developed in the circumferential direction in embodiment 1.

[0017] In the first block Q1, a cylindrical hole and a camera coordinate system identical to those in the real environment are placed in a virtual space such as 3D CAD or CG software. The relative positional relationship between the cylindrical hole and the camera coordinate system in the actual environment is measured using a calibration method using a chessboard or the like. In the second block Q2, a virtual captured image is generated in which a virtual machining surface boundary is added to a virtual captured image of the target cylindrical hole portion as seen from the camera coordinate system based on the internal camera parameters of the hole lens camera (focal length, lens distortion, image pixel discretization value, etc.). That is, in 3D space, for example, by displaying only the lines representing the virtual machining surface boundary and projecting them onto the virtual captured image, it is possible to generate a virtual captured image in which the extracted virtual machining surface boundary is added to the virtual captured image. This makes it possible to geometrically extract the boundary line positions between the unevenly processed surfaces in the virtual captured image. In the third block Q3, the virtual captured image to which the virtual machining surface boundary has been added is expanded into a rectangle in the circumferential direction. In the fourth block Q4, each machining surface boundary line candidate is estimated using an edge extraction method for the planar developed captured image developed into a rectangle in the circumferential direction. This makes it possible to estimate the boundary lines between the unevenly processed surfaces in the planar developed captured image. In the fifth block Q5, a candidate line 1 is identified as the machining surface boundary line of the planar developed captured image corresponding to the virtual machining surface boundary to be detected in the virtual captured image, based on the minimum distance between the boundary lines, etc. In the sixth block Q6, the processing of the fifth block Q5 is repeated to identify and acquire all the processed surface boundary lines of the corresponding planar developed captured image. This makes it possible to identify the boundary lines between the textured surfaces in all the planar developed captured images.

[0018] 7(a) and (b) are diagrams illustrating a method for determining whether an occlusion has occurred in a captured image in the first embodiment. That is, it is determined that an occluded portion that is not captured in the captured image has occurred.

[0019] (a) shows a method for determining whether occlusion has occurred on each machining surface of the captured image by calculating the intersection of a virtual image using the optical axis vector of each machining surface and the camera, and it can be determined that the occluded portion is part of the groove machining surface 17a3 and the groove machining side surface 17a4. (b) shows a method for determining whether an occluded portion has occurred in each machining surface of the captured image when the boundary line of the captured image corresponding to the boundary line of the virtual machining surface to be detected in the virtual image is acquired. In the fifth block Q5, a candidate line is identified as the machining surface boundary line of the planar developed captured image corresponding to the boundary line of the virtual machining surface to be detected from the minimum distance between the boundaries in Figure 6, and if there is no machining surface boundary line of the planar developed captured image corresponding to the boundary line of the virtual machining surface to be detected within a predetermined threshold distance, it is determined that the machining surface is hidden due to occlusion and the machining surface boundary line is not visible. This allows for the acquisition of images with a uniform scale even in cases where a planar image contains areas that are partially obscured due to occlusion, making it possible to extract defects taking into account their size.

[0020] FIG. 8 is a flowchart showing the flow of determining whether occlusion has occurred and calculating an image scale value in the first embodiment.

[0021] In step S11, a setting value (for example, 1 mm = 5 pixels) is set to indicate how many pixels wide the actual size (actual dimensions) of the inside of the cylindrical hole should be in the captured image, based on the dimensional information in the drawing information and the resolution of the camera. In step S12, it is determined whether or not there is no occlusion on each processed surface of the captured image and whether or not the entire surface is captured in the captured image. If there is no occlusion on each processing surface of the captured image, the process proceeds to step S13, and if there is an occlusion on each processing surface of the captured image, the process proceeds to step S16. In step S13, the pixel width in the image is calculated from the actual size and set value of the cylindrical width of each processed surface. In step S14, the pixel width in the captured image is measured. In step S15, the image scale correction value for each processed surface is calculated. (For example, if the actual cylindrical width of the machining surface is 2 mm and is displayed in 5 pixels, you would like to enlarge the 2 mm to 10 pixels, so the image scale correction value is 2.0.) In step S16, the grid width in the cylindrical direction of each processed surface is measured in pixels from a grid pattern (calibration image) projected by a laser or the like in the captured image. In step S17, an image scale correction value is calculated from the actual grid size of each processed surface of the captured image and the set value / pixel width. (For example, if a 1mm wide grid in the cylindrical direction is displayed with 2 pixels, we want to correct it to 1mm = 5 pixels, so the image scale correction value is 5 / 2 = 2.5.) This makes it possible to obtain an image with a uniform scale even when the image contains areas that are partially obscured due to occlusion, and by using a grid pattern K (calibration image) projected using a laser or the like, it becomes possible to calculate the scale correction value for areas that are partially obscured due to occlusion, and since an image with a uniform scale is obtained, it becomes possible to extract defects taking into account the defect size.

[0022] Next, the effects of the first embodiment will be described.

[0023] (1) Image inspection device 1 includes an image acquisition unit 7 that acquires an image captured by hole lens camera 2 of the inside of cylindrical hole 17a, a camera information storage unit 12 that stores camera distance information between hole lens camera 2 and cylindrical hole 17a, a drawing information storage unit 13 that stores drawing information having dimensional information of the unevenly machined surfaces (17a1-17a5) inside cylindrical hole 17a, a planar development processing unit 8 that converts the image of the unevenly machined surfaces (17a1-17a5) inside cylindrical hole 17a into a planar development image using the camera distance information and drawing information, an image scale correction unit 9 that calculates an image scale correction value for each of the unevenly machined surfaces (17a1-17a5) inside cylindrical hole 17a using the camera distance information and drawing information and generates a scale-corrected image of the planar development image, and a defect extraction processing unit 10 that extracts defects from the scale-corrected image. Therefore, it is possible to prevent defects that appear at different scales from being overlooked, and improve the accuracy of defect extraction.

[0024] (2) The image scale corrector 9 generates a scale-corrected image in which the unevenly machined surface (17a1-17a5) in the cylindrical hole 17a is displayed at a uniform scale. Therefore, since captured images with a uniform scale can be obtained, it becomes possible to extract defects taking into account the defect size.

[0025] (3) The image was taken in one shot of the unevenly machined surface inside the cylindrical hole 17a. Therefore, the imaging time can be reduced.

[0026] (4) Based on the camera distance information and drawing information, the image scale correction unit 9 determines that occlusion has occurred in the captured image of the unevenly machined surfaces (17a1-17a5) within the cylindrical hole portion 17a, and generates a scale-corrected image displayed at a uniform scale for each of the unevenly machined surfaces (17a1-17a5) within the cylindrical hole portion 17a, taking the occlusion into consideration. Therefore, even if a captured image contains areas that are partially obscured due to occlusion, the captured image has a uniform scale, making it possible to extract defects taking into account the defect size.

[0027] (5) The image scale correction unit 9 calculates an image scale correction value for each unevenly processed surface (17a1-17a5) within the cylindrical hole portion 17a based on the camera distance information, drawing information, and a grid pattern K (calibration image) projected by a laser or the like, and generates a scale-corrected image of the planar expansion captured image. Therefore, it becomes possible to calculate the scale correction value for the region that is partially hidden due to occlusion, and an image with a uniform scale can be obtained, which makes it possible to extract defects taking into account the defect size.

[0028] (6) The plane development processing unit 8 extracts the positions of the virtual machining surface boundary lines between the uneven machining surfaces (17a1-17a5) in the virtual captured image of the cylindrical hole portion 17a, which is geometrically determined based on the camera distance information and drawing information. Therefore, it is possible to geometrically extract the boundary line positions between the unevenly processed surfaces (17a1-17a5) in the virtual captured image.

[0029] (7) The plane development processing unit 8 uses edge extraction processing on the captured image of the uneven processed surface (17a1-17a5) within the cylindrical hole portion 17a to estimate candidate boundary lines between the uneven processed surfaces (17a1-17a5) within the cylindrical hole portion 17a in the captured image. Therefore, it is possible to estimate the boundary lines between the unevenly processed surfaces (17a1-17a5) in the captured image.

[0030] (8) Based on the camera distance information and drawing information, the plane expansion processing unit 8 calculates the distance between the extracted virtual machining surface boundary line between the geometrically determined uneven machining surfaces (17a1-17a5) and the multiple boundary lines between the uneven machining surfaces (17a1-17a5) estimated from the captured image, based on the positions of the group of boundary lines between the uneven machining surfaces (17a1-17a5) in the virtual captured image of the cylindrical hole portion 17a determined geometrically and the positions of the group of boundary lines between the uneven machining surfaces (17a1-17a5) in the cylindrical hole portion 17a estimated from the captured image, and identifies which of the multiple boundary lines between the uneven machining surfaces (17a1-17a5) estimated from the captured image the extracted virtual machining surface boundary line between the geometrically determined uneven machining surfaces (17a1-17a5) corresponds to. Therefore, it is possible to identify the boundary lines between the unevenly processed surfaces (17a1-17a5) in all the captured images.

[0031] (9) The image scale correction unit 9 divides the planar developed captured image into each of the unevenly processed surfaces (17a1-17a5) within the cylindrical hole portion 17a, generates scale-corrected images of the planar developed captured image divided by the image scale correction value into each of the unevenly processed surfaces (17a1-17a5) within the cylindrical hole portion 17a, and then combines the scale-corrected images of the divided planar developed captured image. This prevents defects on the boundary line of the unevenly machined surface (17a1-17a5) in the cylindrical hole portion 17a from being overlooked due to defects of a size smaller than the standard defect size being displayed as small defects on the image, thereby improving the accuracy of defect extraction.

[0032] (10) The plane development processing unit 8 converts the captured image of the unevenly processed surface (17a1-17a5) in the cylindrical hole 17a into a plane development captured image by developing it into a rectangle. Therefore, since it is possible to correct the distortion of the captured image that is curved in the circumferential direction of the cylindrical hole portion 17a, it is possible to obtain a captured image with a uniform scale in the circumferential direction of the cylindrical hole portion 17a, thereby improving the accuracy of defect extraction.

[0033] (11) The image scale correction unit 9 corrects the brightness value for each unevenly processed surface (17a1-17a5) within the cylindrical hole portion 17a of the planar developed captured image, processes it into a captured image with uniform brightness, and calculates an image scale correction value for each unevenly processed surface (17a1-17a5) within the cylindrical hole portion 17a based on the camera distance information and drawing information, thereby generating a scale-corrected image of the planar developed captured image. Therefore, a captured image with uniform brightness can be obtained, preventing overlooking defects due to overexposure or darkness, and improving the accuracy of defect extraction.

[0034] [Embodiment 2] FIG. 9 is a schematic diagram of the entire image inspection device according to the second embodiment, and FIG. 10 is a main flowchart showing the flow of image inspection according to the second embodiment.

[0035] In the first embodiment, the image scale correction unit 9 calculates an image scale correction value for each processed surface and generates a scale-corrected image, and the defect extraction processing unit 10 extracts defects from the scale-corrected image. In the second embodiment, however, the image scale correction unit 9 calculates an image scale correction value for each processed surface (step S2a in FIG. 10), and the defect extraction processing unit 10 extracts defects from the captured image based on the image scale correction value (step S3a in FIG. 10).

[0036] The other configurations are the same as those in the first embodiment, so the same components are given the same reference numerals and the description thereof will be omitted. Therefore, the second embodiment has the same effects as the first embodiment.

[0037] Other Embodiments The above describes an embodiment for carrying out the present invention, but the specific configuration of the present invention is not limited to the configuration of the embodiment, and design changes and the like that do not deviate from the gist of the invention are also included in the present invention. The object to be inspected is not limited to a VTC cover, and may be anything that has a narrow cylindrical or polygonal hole as an inspection area and that can be image inspected within this hole. [Explanation of symbols]

[0038] 1 Image inspection device, 2 Hole lens camera (camera), 3 Computer, 4 CPU, 5 Memory, 7 Captured image acquisition unit, 8 Plane development processing unit, 9 Image scale correction unit, 10 Defect extraction processing unit, 12 Camera information storage unit, 13 Drawing information storage unit, 17 VTC cover (inspected object), 17a Cylindrical hole portion (inspection area)

Claims

1. An image inspection apparatus for inspecting an inspection area of ​​an object to be inspected for defects, comprising: a captured image acquisition unit that acquires a captured image of the inspection area by a camera; a camera information storage unit that stores camera distance information between the camera and the inspection area; a drawing information storage unit that stores drawing information having dimensional information of the uneven processed surface of the inspection area; a plane development processing unit that converts the captured image of the uneven processed surface of the inspection area into a plane development captured image using the camera distance information and the drawing information; an image scale correction unit that calculates an image scale correction value for each uneven surface of the inspection area using the camera distance information and the drawing information, and generates a scale-corrected image of the planar development captured image; a defect extraction processing unit that extracts defects from the scale-corrected image; An image inspection device having the above structure.

2. 2. The image inspection device according to claim 1, The image scale correction unit generating a scale-corrected image in which the uneven surface of the inspection area is displayed at a uniform scale; An image inspection device characterized by:

3. 3. The image inspection device according to claim 2, The image scale correction unit determining whether occlusion has occurred in the captured image of the unevenly processed surface of the inspection area based on the camera distance information and the drawing information, and generating scale-corrected images displayed at a uniform scale for each unevenly processed surface of the inspection area, taking the occlusion into consideration; An image inspection device characterized by:

4. 4. The image inspection device according to claim 3, The image scale correction unit Calculating an image scale correction value for each uneven surface of the inspection area based on the camera distance information, drawing information, and calibration image, and generating a scale-corrected image of the planar development captured image. An image inspection device characterized by:

5. 2. The image inspection device according to claim 1, The planar development processing unit extracting positions of a group of virtual processed surface boundary lines between concave and convex processed surfaces in the geometrically determined virtual captured image of the inspection object based on the camera distance information and the drawing information; An image inspection device characterized by:

6. 6. The image inspection device according to claim 5, The planar development processing unit an edge extraction process is performed on the captured image of the unevenly processed surface of the inspection area, and a group of candidate boundary lines between the unevenly processed surfaces of the inspection object in the captured image is estimated; An image inspection device characterized by:

7. 7. The image inspection device according to claim 6, The planar development processing unit calculating distances between the extracted virtual processed surface boundary lines between the concave-convex processed surfaces geometrically determined in the virtual captured image of the inspection object based on the camera distance information and the drawing information, and between the extracted virtual processed surface boundary lines between the concave-convex processed surfaces geometrically determined and the plurality of boundary lines between the concave-convex processed surfaces estimated in the captured image, based on the positions of the group of boundary lines between the concave-convex processed surfaces of the inspection object geometrically determined in the virtual captured image of the inspection object based on the camera distance information and the drawing information; Identifying which of the multiple boundaries between the uneven processed surfaces estimated from the captured image corresponds to the extracted virtual processed surface boundary line between the uneven processed surfaces obtained geometrically; An image inspection device characterized by:

8. 2. The image inspection device according to claim 1, The image scale correction unit Dividing the planar developed captured image into sections for each unevenly processed surface of the inspection area, generating scale-corrected images of the divided planar developed captured images using image scale correction values ​​for each unevenly processed surface of the inspection area, and then combining the scale-corrected images of the divided planar developed captured images. An image inspection device characterized by:

9. 2. The image inspection device according to claim 1, The planar development processing unit converting the captured image of the unevenly processed surface of the inspection area into a planar developed captured image by developing it into a rectangle; An image inspection device characterized by:

10. 2. The image inspection device according to claim 1, The image scale correction unit correcting the brightness value for each uneven surface of the planar developed captured image of the inspection object and processing it into a captured image with uniform brightness, and calculating an image scale correction value for each uneven surface of the inspection area based on camera distance information and drawing information, and generating a scale-corrected image of the planar developed captured image; An image inspection device characterized by:

11. An image inspection apparatus for inspecting an inspection area of ​​an object to be inspected for defects, comprising: a captured image acquisition unit that acquires a captured image of the inspection area by a camera; a camera information storage unit that stores camera distance information between the camera and the inspection area; a drawing information storage unit that stores drawing information having dimensional information of the uneven processed surface of the inspection area; a plane development processing unit that converts the captured image of the uneven processed surface of the inspection area into a plane development captured image using the camera distance information and the drawing information; an image scale correction unit that calculates an image scale correction value for each uneven surface of the inspection area using the camera distance information and the drawing information; a defect extraction processing unit that extracts defects from the captured image of the uneven processed surface of the inspection area based on an image scale correction value for each uneven processed surface of the inspection area; An image inspection device having the above structure.

Images