A surface defect state evaluation method and system based on image analysis and a medium

Abstract

The present application relates to the technical field of defect analysis, and specifically provides a surface defect state evaluation method and system based on image analysis and a medium, the method comprising: acquiring an original image of a surface of a to-be-tested object collected by an image collection device; based on color configuration information, splitting the original image into a base color image, a paint color image and an etching color image; processing the original image or the split image, and processing the etching color image to obtain etching data; based on the etching color image and the base color image, obtaining peeling data; performing edge detection and contour extraction on the original image to obtain bubble data; performing edge detection and texture feature extraction on the original image to obtain crack data; and based on the defect data and an experience coefficient, obtaining an etching grade, a peeling grade, a bubble grade and a cracking grade of the surface of the to-be-tested object. Through image collection, splitting, processing and grade evaluation, the present application quantifies key defect data, and realizes objective and repeatable automatic evaluation of surface defects of the to-be-tested object.

Description

Technical Field

[0001] This invention belongs to the field of image analysis technology, and in particular relates to a method, system and medium for evaluating the state of surface defects based on image analysis. Background Technology

[0002] In the operation and maintenance of industrial equipment, material corrosion is one of the key factors affecting equipment lifespan, safety, and operating efficiency. To scientifically assess the corrosion status of equipment, existing technologies mainly employ three methods: gravimetric analysis, surface observation, and electrochemical testing. Gravimetric analysis characterizes the corrosion rate by measuring the mass change of the sample before and after corrosion (or after removing corrosion products). It is suitable for quantitative analysis in laboratory environments but is difficult to apply to rapid on-site testing of large numbers of devices. Surface observation relies on manual visual inspection or simple tools to qualitatively judge the corrosion morphology, color, and distribution. Although simple to operate, it is highly subjective, has poor repeatability, and cannot meet the needs of large-scale, high-frequency inspections. Electrochemical testing, while possessing high sensitivity and mechanistic research capabilities, typically requires contact probes, specific electrolytic environments, and specialized operators, making it unsuitable for rapid on-site assessment of surfaces covered with non-conductive coatings or with complex structures.

[0003] With the development of intelligent operation and maintenance in industry, higher requirements have been placed on the detection of corrosion status: non-contact, high-efficiency, and standardized corrosion degree identification is needed without damaging the equipment. However, traditional methods generally have limitations such as long detection cycles, reliance on human experience, and difficulty in large-scale application. Especially when dealing with large facilities (such as chemical pipelines, offshore platforms, and power equipment) with hundreds or thousands of detection points, existing methods are no longer sufficient to meet the actual operation and maintenance efficiency and accuracy requirements. Summary of the Invention

[0004] To address the problems existing in the prior art, the present invention provides a surface defect state assessment method based on image analysis, comprising the following steps: Step S1: Obtain the original image of the surface of the object under test acquired by the image acquisition device; Step S2: Based on the preset color configuration information, the original image is split into a background color image, a paint color image, and an erosion color image; Step S3: Process the original image or the split image to obtain defect data, which includes corrosion data, peeling data, bubble data, and crack data. Step S31: Process the corrosion color map to obtain corrosion data, the corrosion data including corrosion area percentage; Step S32: Based on the corrosion color map and the background color map, obtain the peeling data, which includes the peeling area percentage; Step S33: Perform edge detection and contour extraction on the original image to obtain bubble data, wherein the bubble data includes the bubble area percentage; Step S34: Perform edge detection and texture feature extraction on the original image to obtain crack data; Step S4: Based on the defect data and the experience coefficients based on the expert knowledge base, obtain the corrosion level, peeling level, bubble level and cracking level of the surface of the object to be tested.

[0005] Specifically, the corrosion data acquisition method in step S31 is as follows: Step S311: Convert the erosion color image into a grayscale image, and binarize the grayscale image to obtain a binary image; Step S312: Perform connected component analysis on the binary image and mark all eroded connected components; Step S313: Perform edge detection, extract the edge contour of the eroded area, and obtain the edge image; Step S314: Dilate and erode the edge image to obtain the eroded region; Step S315: Based on the corrosion area, calculate the total area of ​​the corrosion area, the maximum corrosion area, and the percentage of corrosion area.

[0006] Furthermore, the method for obtaining the peeling data in step S32 is as follows: Step S321: Based on the color configuration information, the corrosion color map is divided into a peeled portion and an unpeeled portion; Step S322: Convert the peeled-off portion and the background color image into grayscale images, and perform binarization processing on the grayscale images to obtain a binary image; Step S323: Perform connected component analysis on the binary image and mark all peeled connected components; Step S324: Perform edge detection, extract the edge contour of the peeled area, and obtain the peeled edge image; Step S325: Perform dilation and erosion processing on the peeled edge image to extract the peeled area; Step S326: Based on the peeling area, calculate the total area of ​​the peeling area, the maximum peeling area, and the percentage of the peeling area.

[0007] Furthermore, the method for obtaining bubble data in step S33 is as follows: Step S331: Perform median filtering on the original image, and remove the eroded and peeled areas from the filtered image to obtain the initial bubble image; Step S332: Perform edge detection on the initial bubble image to obtain a bubble edge image; Step S333: Perform contour detection on the bubble edge image and filter each contour information based on the bubble basic data; Step S334: Perform connected component analysis on the contour information to calculate the number of bubbles, bubble area, and bubble area percentage.

[0008] Specifically, the crack data acquisition method in step S34 is as follows: Step S341: Perform median filtering on the original image, and remove the eroded and peeling areas from the filtered image to obtain the initial crack image; Step S342: Perform edge detection on the initial crack image to obtain edge contour information; Step S343: Expand the open edge contour information to obtain the crack connected region; Step S344: Crack detection is performed on the crack-connected region to identify crack data.

[0009] Preferably, step S2 includes: Step S21: Based on the material and surface color of the object to be tested, preset color configuration information is provided, which includes at least material color, coating color and corrosion color. Step S22: Based on the color configuration information, the original image is split into a background color image, a paint color image, and an erosion color image.

[0010] Furthermore, step S2 also includes: Step S23: Compare the differences between the original image color information and the color configuration information, and obtain the average color difference value of the original image by judging the Lab spatial distance; Step S24: Based on the average color difference value, calculate the color change level and remaining years of the test object.

[0011] On the other hand, this application provides a surface defect status assessment system based on image analysis, the system comprising: an image acquisition module, a surface defect status assessment module, and a database; The image acquisition module is used to acquire raw images using an image acquisition device and send the raw images to the surface defect status assessment module; The surface defect status assessment module stores the original image into the database and implements the surface defect status assessment method based on image analysis as described above to obtain the surface defect status level, which includes corrosion level, peeling level, bubble level and cracking level. The database includes a standard library management module and a defect data module. The standard library management module is used to set color configuration information, and the defect data module stores standard samples and images to be tested.

[0012] Based on the above scheme, the image acquisition device includes a mirrorless camera, a macro lens and a macro flash, wherein the macro flash adopts a ring light source to provide constant illumination to the area being acquired.

[0013] The present invention also provides a computer-readable storage medium having a computer program that, when executed by a processor, implements the steps of the surface defect state assessment method based on image analysis as described above.

[0014] Compared with the prior art, the present invention has the following beneficial effects: 1. This invention achieves a comprehensive, objective, and repeatable automatic assessment of the surface defect status of the object under test by simultaneously acquiring and quantifying four key defect data: corrosion, peeling, bubbles, and cracks through a unified technical process of image acquisition, intelligent segmentation, classification processing, and grade evaluation. 2. By using a color matching algorithm, the original image is split into pure metallic color, pure paint color, and pure corrosion color images, providing accurate data for subsequent analysis of different defects and avoiding interference; 3. The combination of computer image recognition and real-time image acquisition system enables real-time monitoring and early warning of defect levels, which helps to detect and handle defects early, reducing losses and maintenance costs; 4. The automatic evaluation of this invention can process a large amount of image data and achieve the assessment of the defect degree of the test object in a short time, which significantly improves work efficiency and evaluation accuracy. Attached Figure Description

[0015] Figure 1 This is a flowchart for the defect assessment of this application; Figure 2 This is a flowchart of the corrosion and spalling assessment process for this application; Figure 3 This is a schematic diagram of corrosion data extraction in this application; Figure 4 This is a flowchart of the coating bubble level assessment process for this application; Figure 5 This is a flowchart for assessing the coating cracking level in this application; Figure 6 This is a diagram of the overall system architecture of this application; Figure 7 This is a diagram of the database structure of this application. Detailed Implementation

[0016] The invention will be further described below with reference to specific embodiments.

[0017] like Figure 1 As shown, the present invention provides a surface defect state assessment method based on image analysis, comprising the following steps: Step S1: Obtain the original image of the surface of the object under test acquired by the image acquisition device; Specifically, step S1 includes: acquiring an original image of the surface of the object to be tested using an image acquisition device, and then obtaining the original image; wherein the resolution of the image acquisition device can capture information such as coating cracks and bubbles of the object to be tested.

[0018] Step S2: Based on the preset color configuration information, the original image is split into a background color image, a paint color image, and an erosion color image; In this embodiment, step S2 includes: Step S21: Based on the color and surface color of the object to be tested, preset color configuration information is provided, which includes at least material color, coating color, and corrosion color; median filtering is applied to the original image to eliminate noise interference.

[0019] The standard colors are configured based on the colors (base colors) of different types of test objects, the colors produced by rust on different types of test objects (corrosion colors), and the paint color on the surface of the test objects (paint colors).

[0020] In other implementations of this embodiment, the material of the object under test is also configured, and the color is configured by matching the background color with the material of the object under test. By pre-configuring the material, the corresponding color can be directly matched according to the actual information of the object under test, saving color lookup time and improving the efficiency of image processing.

[0021] Step S22: Based on the color configuration information, the original image is split into a background color image, a paint color image, and an erosion color image.

[0022] In this embodiment, step S22 includes: S221: Based on the color configuration information, determine a predefined standard color, which includes the base color, coating color (paint color), and corrosion color of the object to be tested; S222: Based on the original image of the object under test, extract the color information of the original image, and split the original image into a background color image, paint color image, and corrosion color image by matching it with standard colors.

[0023] The specific method for matching with standard colors is as follows: S2221: Obtain a large number of standard images from the database and record the color information corresponding to the degree of erosion of different standard images; S2222: The difference between the acquired standard image color information and the standard color is compared by a color matching algorithm, and the background color, paint color and corrosion color of the image are identified by the difference.

[0024] In other implementations of this embodiment, the remaining years can also be determined by the difference between the original image color and the standard color, specifically as follows: Step S23: Compare the difference between the original image color and the color configuration information, and obtain the average color difference value of the original image by judging the Lab spatial distance; Those skilled in the art should understand that the implementation steps of the Lab spatial distance determination method are existing technologies in this field and will not be described in detail here.

[0025] Step S24: Based on the average color difference value, calculate the color change level and remaining years of the test object.

[0026] In step S24, the larger the average color difference value, the higher the color change level of the test object and the fewer the remaining years. By predicting the lifespan of the test object through color difference, timely handling and repair can reduce the later maintenance costs and losses caused by unusability.

[0027] The original image of the test object is split based on the color configuration information in step S2 above. It supports flexible configuration of standard colors (such as different base colors of stainless steel, brass, etc., and different types of paint colors) according to the material type of the test object, so that the splitting logic can be adapted to a variety of easily corroded objects and expand the scope of application. At the same time, it provides an image data source for the independent evaluation of indicators such as corrosion, peeling, and rust levels.

[0028] Step S3: Process the original image or the split image to obtain defect data, which includes corrosion data, peeling data, bubble data, and crack data. Step S31: Process the corrosion color map to obtain corrosion data, which includes the total area of ​​the corrosion region and the proportion of the corrosion region, etc. The corrosion data acquisition method is as follows: Step S311: The erosion color image is converted to grayscale to obtain an 8-bit grayscale image, and the grayscale image is binarized to obtain a binary image; Step S312: Perform connected component analysis on the binary image and mark all eroded connected components; Step S313: Median filtering is then performed, followed by edge detection to extract the edge contours of the eroded area and obtain the edge image. In this embodiment, the Canny edge detection algorithm is used to detect the edges of the image. Canny edge detection has high accuracy in edge detection and can keep the edge detection result as a single edge line.

[0029] Step S314: Dilate and erode the edge image to obtain the eroded region; After expansion and corrosion treatment, the edge lines will be connected and divided into several regions. Then, the connected regions are filtered to obtain the corrosion regions. Step S315: Based on the corrosion area, calculate the total area of ​​the corrosion area, the maximum corrosion area, and the proportion of the corrosion area.

[0030] Step S32: Based on the corrosion color map and the background color map, obtain the peeling data, which includes the peeling area and the proportion of the peeling area, etc. like Figure 2 As shown, the method for obtaining the peeling data in step S32 is as follows: Step S321: Based on the color configuration information, the corrosion color map is divided into a peeled portion and an unpeeled portion; Step S322: Convert the peeled-off portion and the background color image into grayscale images, and perform binarization processing on the grayscale images to obtain a binary image; It should be noted that the background color image is the color of the material being tested, representing the extracted image where the material color remains even after the coating is peeled off.

[0031] Step S324: Perform connected component analysis on the binary image and mark all peeled connected components; Step S325: Perform edge detection, extract the edge contour of the peeled area, and obtain the peeled edge image; Step S326: Perform dilation and erosion processing on the peeled edge image to extract the peeled area; Step S327: Based on the peeling area, calculate the total area of ​​the peeling area, the maximum peeling area, and the proportion of the peeling area.

[0032] Step S33: Perform edge detection and contour extraction on the original image to obtain bubble data, wherein the bubble data includes the number of contours and the area of ​​the contours; The method for obtaining bubble data in step S33 is as follows: Step S331: Perform median filtering on the original image, and remove the eroded and peeled areas from the filtered image to obtain the initial bubble image; Step S332: Perform edge detection on the initial bubble image to obtain a bubble edge image; Step S333: Perform contour detection on the bubble edge image and filter each contour information based on the bubble basic data; When filtering contours, it is necessary to traverse each contour and filter out contours that do not meet the bubble conditions in terms of area or shape, so that the remaining contours are the bubbles.

[0033] Step S334: Perform connected component analysis on the contour information to calculate the number of bubbles and bubble area, etc.

[0034] Step S34: Perform edge detection and texture feature extraction on the original image to obtain crack data, including crack length, crack width, and crack area, etc. The method for obtaining crack data in step S34 is as follows: Step S341: Perform median filtering on the original image, and remove the eroded and peeling areas from the filtered image to obtain the initial crack image; Step S342: Perform edge detection on the initial crack image to obtain edge contour information; Step S343: Expand the open edge contour information to obtain the crack connected region; Step S344: Crack detection is performed on the crack-connected region to identify crack data; According to one implementation method, step S344 includes: S3441: Traverse each connected component to calculate the minimum rotating rectangle bounding box and fill rate, where fill rate = area of ​​connected component / area of ​​rotating rectangle; S3442: If any of the following conditions are met, it is determined to be a crack region: (1) The rectangle has a width of less than 5 mm and a width-to-height ratio of greater than 5; (2) The area of ​​the rectangle is greater than 25 mm², and the fill rate within the rectangle is less than 0.3. S3443: Traverse each crack region, find the largest inscribed circle, and obtain the crack data.

[0035] In this embodiment, in order to eliminate the effects of corrosion and peeling, the results of corrosion and peeling identification are removed from the image, and then edge detection and texture detection methods are used to identify the crack area.

[0036] In step S3, the image is processed and defect data is identified. The defect data is used to judge the object under test and is also used for subsequent grade evaluation.

[0037] Step S4: Based on the defect data and the experience coefficients based on the expert knowledge base, the corrosion level, peeling level, bubble level and cracking level of the surface of the object to be tested are obtained. In step S4, the experience coefficients are obtained based on the images evaluated by experts.

[0038] In this process, by constructing a standard sample library of test objects for expert rating, the defect data corresponding to images of different defect types and severity in the sample library are correlated with the expert rating levels to determine the empirical coefficient.

[0039] The specific defect level assessment in step S4 is as follows: Step S41: Based on the corrosion area ratio and empirical coefficient, the corrosion level of the test object is obtained; Step S42: Based on the proportion of peeling area and empirical coefficients, obtain the peeling level of the test object; Step S43: Based on the ratio of bubble area to total area and empirical coefficients, the bubble level of the test object is obtained; Step S44: Based on the maximum inscribed circle diameter of the cracked area and the empirical coefficient, the crack grade of the test object is obtained.

[0040] Step S4 combines quantitative data obtained from image analysis with expert knowledge by integrating an expert knowledge base, thereby avoiding the mechanical nature of data statistics and preventing judgment biases among different evaluators.

[0041] Based on the same technical concept, the present invention also provides a surface defect status assessment system based on image analysis, the system comprising: an image acquisition module, a surface defect status assessment module, and a database; The image acquisition module is used to acquire raw images using an image acquisition device and send the raw images to the surface defect status assessment module; The image acquisition device includes a mirrorless camera, a macro lens, and a macro flash. The macro flash uses a ring light source to provide constant illumination to the area being acquired.

[0042] In this embodiment, the mirrorless camera is a mirrorless camera, equipped with a 90 or 100mm macro lens and a macro flash; because the amount of light reaching the sensor is relatively small when using a macro lens, relatively strong supplemental lighting is provided for the object being photographed. High-brightness illumination is provided through the structure of the macro flash, specifically: The macro flash adopts the light source layout of a surgical shadowless lamp, using a ring light source, which is composed of multiple high-power white LED beads arranged in a ring.

[0043] The surface defect status assessment module stores the original image into the database and implements the surface defect status assessment method based on image analysis as described above to obtain the surface defect status level, which includes corrosion level, peeling level, bubble level and cracking level. The database includes a standard library management module and a defect data module. The standard library management module is used to set color configuration information, and the defect data module stores standard samples and images to be tested.

[0044] Specific embodiments of the surface defect state assessment system of the present invention can be referred to the surface defect state assessment method, and will not be repeated here.

[0045] Furthermore, the surface defect state assessment method according to the present invention can be recorded in a computer-readable recording medium. Specifically, according to the present invention, a computer-readable recording medium storing computer-executable instructions can be provided, which, when executed by a processor, cause the processor to perform the surface defect state assessment method as described above.

[0046] It should be noted that the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, program segment, or portion of code containing at least one executable instruction for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0047] In general, various exemplary embodiments of the present invention can be implemented in hardware or dedicated circuitry, software, firmware, logic, or any combination thereof. Some aspects can be implemented in hardware, while others can be implemented in firmware or software that can be executed by a controller, microprocessor, or other computing device. When aspects of embodiments of the present invention are illustrated or described as block diagrams, flowcharts, or represented using certain other images, it will be understood that the blocks, apparatuses, systems, techniques, or methods described herein can be implemented as non-limiting examples in hardware, software, firmware, dedicated circuitry or logic, general-purpose hardware or controllers or other computing devices, or certain combinations thereof.

[0048] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0049] While the specific embodiments of the present invention have been described above, they are not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art without creative effort based on the technical solutions of the present invention are still within the scope of protection of the present invention.

Claims

1. A surface defect state assessment method based on image analysis, characterized in that, Includes the following steps: Step S1: Obtain the original image of the surface of the object under test acquired by the image acquisition device; Step S2: Based on the preset color configuration information, the original image is split into a background color image, a paint color image, and an erosion color image; Step S2 includes: presetting color configuration information based on the color and surface color of the object to be tested, wherein the color configuration information includes at least material color, paint color and corrosion color; Based on the color configuration information, a predefined standard color is determined, which includes the background color, paint color, and corrosion color of the object to be tested; Based on the original image of the surface of the object under test, the color information of the original image is extracted. By matching it with the standard color, the original image is split into the background color image, paint color image, and corrosion color image. The specific method for matching with standard colors is as follows: Obtain a large number of standard images from the database and record the color information corresponding to the degree of erosion of different standard images; The difference between the acquired standard image color information and the standard color is compared by a color matching algorithm, and the background color, paint color and corrosion color of the image are identified by the difference. Step S3: Process the original image or the split image to obtain defect data, which includes corrosion data, peeling data, bubble data, and crack data. Step S31: Process the corrosion color map to obtain corrosion data, the corrosion data including corrosion area percentage; Step S32: Based on the corrosion color map and the background color map, obtain the peeling data, which includes the peeling area percentage; Step S33: Perform edge detection and contour extraction on the original image to obtain bubble data, wherein the bubble data includes the bubble area percentage; Step S34: Perform edge detection and texture feature extraction on the original image to obtain crack data; Step S4: Based on the defect data and the experience coefficients based on the expert knowledge base, obtain the corrosion level, peeling level, bubble level and cracking level of the surface of the object to be tested.

2. The surface defect state assessment method based on image analysis according to claim 1, characterized in that, The corrosion data acquisition method in step S31 is as follows: Step S311: Convert the erosion color image into a grayscale image, and binarize the grayscale image to obtain a binary image; Step S312: Perform connected component analysis on the binary image and mark all eroded connected components; Step S313: Perform median filtering and edge detection to extract the edge contours of the eroded area and obtain the edge image; Step S314: Dilate and erode the edge image to obtain the eroded region; Step S315: Based on the corrosion area, calculate the total area of ​​the corrosion area, the maximum corrosion area, and the percentage of corrosion area.

3. The surface defect state assessment method based on image analysis according to claim 2, characterized in that, The method for obtaining the peeling data in step S32 is as follows: Step S321: Based on the color configuration information, the corrosion color map is divided into a peeled portion and an unpeeled portion; Step S322: Convert the peeled-off portion and the background color image into grayscale images, and perform binarization processing on the grayscale images to obtain a binary image; Step S323: Perform connected component analysis on the binary image and mark all peeled connected components; Step S324: Perform median filtering and edge detection to extract the edge contour of the peeled area and obtain the peeled edge image; Step S325: Perform dilation and erosion processing on the peeling edge image to extract the peeling area; Step S326: Based on the peeling area, calculate the total area of ​​the peeling area, the maximum peeling area, and the percentage of the peeling area.

4. The surface defect state assessment method based on image analysis according to claim 3, characterized in that, The method for obtaining bubble data in step S33 is as follows: Step S331: Perform median filtering on the original image, and remove the eroded and peeled areas from the filtered image to obtain the initial bubble image; Step S332: Perform edge detection on the initial bubble image to obtain a bubble edge image; Step S333: Perform contour detection on the bubble edge image and filter each contour information based on the bubble basic data; Step S334: Perform connected component analysis on the contour information to calculate the number of bubbles, bubble area, and bubble area percentage.

5. The surface defect state assessment method based on image analysis according to claim 2, characterized in that, The method for obtaining crack data in step S34 is as follows: Step S341: Perform median filtering on the original image, and remove the eroded and peeling areas from the filtered image to obtain the initial crack image; Step S342: Perform edge detection on the initial crack image to obtain edge contour information; Step S343: Dilate the edge contour information to obtain the crack connected region; Step S344: Crack detection is performed on the crack-connected region to identify crack data.

6. The surface defect state assessment method based on image analysis according to claim 1, characterized in that, Step S2 further includes: By comparing the differences between the original image's color information and the color configuration information, the average color difference value of the original image is obtained through Lab spatial distance determination; Based on the average color difference value, the color change grade and remaining years of the test object are calculated.

7. A surface defect state assessment system based on image analysis, characterized in that, The system includes: an image acquisition module, a surface defect status assessment module, and a database; The image acquisition module is used to acquire raw images using an image acquisition device and send the raw images to the surface defect status assessment module; The surface defect status assessment module stores the original image into the database and implements the surface defect status assessment method based on image analysis as described in any one of claims 1-6 to obtain the surface defect status level, which includes corrosion level, peeling level, bubble level and cracking level. The database includes a standard library management module and a defect data module. The standard library management module is used to set color configuration information, and the defect data module stores standard samples and images to be tested.

8. The surface defect state assessment system based on image analysis according to claim 7, characterized in that, The image acquisition device includes a mirrorless camera, a macro lens, and a macro flash. The macro flash uses a ring light source to provide constant illumination to the area being acquired.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium has a computer program that, when executed by a processor, implements the surface defect state assessment method based on image analysis as described in any one of claims 1-6.

Images