Paint film adhesion judgment method, system and equipment based on image processing and medium

Abstract

The invention relates to the technical field of image processing, in particular to a paint film adhesion judgment method, system and equipment based on image processing and a medium. The method comprises the following steps: firstly, collecting a target image of a paint film adhesion judgment area, and preprocessing the image to improve the effect of subsequent feature recognition; then carrying out feature recognition on the preprocessed image, and accurately extracting the stripping area of a paint film on the surface of the test piece; calculating the proportion of the paint film stripping area according to the extracted paint film stripping area and the actual area of the judgment area; and finally, comparing the calculated paint film stripping area proportion with a preset adhesive force grade judgment standard so as to determine and output the adhesive force grade of the paint film, so that the judgment efficiency and the objectivity and consistency of the judgment result are improved.

Description

Technical Field

[0001] The present application relates to the technical field of image processing, and in particular to a method, system, device and medium for judging the adhesion of a paint film based on image processing. Background Art

[0002] Paint film adhesion is one of the important indicators for evaluating coating quality and is widely used in the fields of automobiles, home appliances, construction, etc. Traditionally, the test of paint film adhesion mainly relies on manual visual judgment, which has problems such as low efficiency and strong subjectivity of results. With the continuous development of industrial automation and intelligent manufacturing, it is urgent to develop a more efficient, objective and reliable automatic detection method for paint film adhesion. Summary of the invention

[0003] In order to solve the problem that the existing manual visual judgment of paint film adhesion is inefficient and the results are highly subjective, the present application provides a paint film adhesion judgment method, system, device and medium based on image processing, which adopts the following technical solutions: In a first aspect, the present application provides a method for determining the adhesion of a paint film based on image processing, comprising the following steps: Collecting a target image of a paint film adhesion judgment area and preprocessing the target image; Perform feature recognition on the preprocessed target image and extract the paint peeling area on the surface of the specimen; Calculate the paint film peeling area ratio according to the paint film peeling area on the surface of the test piece and the area of ​​the judgment area; The paint film peeling area ratio is compared with a preset adhesion grade judgment standard to determine the paint film adhesion grade.

[0004] By adopting the above-mentioned technical scheme, the present application first collects the target image of the paint film adhesion judgment area and preprocesses the image to improve the effect of subsequent feature recognition; then, feature recognition is performed on the preprocessed image to accurately extract the peeling area of ​​the paint film on the surface of the specimen; then, based on the extracted paint film peeling area and the actual area of ​​the judgment area, the proportion of the paint film peeling area is calculated; finally, the calculated paint film peeling area ratio is compared with the pre-set adhesion grade judgment standard to determine and output the adhesion grade of the paint film, thereby improving the judgment efficiency as well as the objectivity and consistency of the judgment results.

[0005] Optionally, the collecting of the target image of the paint film adhesion judgment area and preprocessing of the target image specifically include the following steps: Collect target images of the paint film adhesion judgment area; Performing image enhancement and noise removal on the target image to obtain an optimized target image; The target judgment area is detected and cropped out in the optimized target image to obtain the preprocessed target image.

[0006] By adopting the above-mentioned technical scheme, the present application first collects the original target image of the paint film adhesion judgment area; then performs optimization processing such as image enhancement and noise removal on the collected original image to obtain an optimized target image with enhanced quality; then, the target area that needs to be judged is detected and accurately cropped out in the optimized target image to obtain the final target image after preprocessing, which can accurately separate the area that needs to be judged, eliminate background interference, and improve the accuracy of subsequent feature recognition and area calculation.

[0007] Optionally, the step of performing feature recognition on the preprocessed target image to extract the paint film peeling area on the surface of the specimen specifically includes the following steps: Binarization is performed on the preprocessed target image to determine target pixels and background pixels, wherein the target pixels are pixels of the peeling area; According to the target pixels and background pixels, the connected regions of the binarized target image are marked to identify independent peeling regions; Calculate the area of ​​each independent peeling region, add up the areas of all independent peeling regions, and obtain the peeling area of ​​the paint film on the specimen surface.

[0008] By adopting the above-mentioned technical scheme, since there is a certain grayscale or color difference between the paint film peeling area and the background in the preprocessed target image, the present application first divides the image pixels into two categories, target pixels and background pixels, through binarization processing; then, based on the binarization result, the connected areas of the image are marked, and the connected target pixels are classified as an independent peeling area; then, the area of ​​each independent peeling area is calculated separately, and the areas of all areas are accumulated to obtain the overall paint film peeling area, which can accurately quantify various irregular shaped peeling areas and improve the accuracy of judgment.

[0009] Optionally, after comparing the paint film peeling area ratio on the surface of the test piece with a preset adhesion grade judgment standard and determining the paint film adhesion grade, the method further comprises the following steps: The effective test area image, target image and paint film adhesion grade are displayed on the user interface and printed out as original records; Saving the original record in a database; The manual determination and review results of the user in the user interface are received, and the paint film adhesion level is corrected according to the manual determination and review results.

[0010] By adopting the above-mentioned technical scheme, the present application first displays the effective test area image and the original target image on the user interface, and simultaneously displays and prints out the paint film adhesion grade results obtained by automatic judgment as the original records; then, the original records are saved in the database for subsequent query and traceability; then, the operator's manual judgment and review opinions on the judgment results are received on the user interface; finally, according to the operator's manual judgment and review results, the previous automatic judgment results are corrected accordingly to obtain the corrected final paint film adhesion grade, which improves the transparency and traceability of the judgment process, and at the same time improves the reliability of the results by setting up manual judgment and review links.

[0011] Optionally, before receiving the manual determination and review result of the user on the user interface, the method further includes the following steps: Analyze the preprocessed target image to obtain the paint film surface texture characteristics, illumination distribution characteristics, and paint film color and background color contrast characteristics; Based on the paint film surface texture characteristics, light distribution characteristics, and paint film color and background color contrast characteristics, a confidence score for automatic determination of the paint film peeling area is calculated; The credibility score is compared with a preset credibility threshold, and when the credibility score is higher than the credibility threshold, the currently automatically determined paint film peeling area result and the paint film adhesion level are displayed on the user interface; When the credibility score is lower than the credibility threshold, a manual determination request is sent to require manual review and determination.

[0012] By adopting the above technical scheme, in the process of judgment based on image processing, the surface texture, lighting conditions, color contrast, etc. of the paint film will affect the accuracy of the judgment. The present application first analyzes the preprocessed target image to extract the features of the paint film surface texture, lighting distribution, color contrast, etc.; then, based on these extracted features, with the help of a pre-trained evaluation model, the credibility score of the current automatic judgment result of the paint film peeling area is calculated; then, the calculated credibility score is compared with the preset credibility threshold. When the credibility score is higher than the threshold, the automatic judgment result is directly displayed on the user interface and is regarded as a reliable result; when the credibility score is lower than the threshold, a manual judgment request is sent, requiring the operator to manually review and judge, and the automatic judgment result is not directly adopted; by setting the credibility threshold, when the credibility is high, the automatic judgment result can be directly adopted, avoiding excessive reliance on manual judgment and improving the judgment efficiency; when the credibility is low, manual review is automatically requested to ensure the accuracy of the result.

[0013] Optionally, before collecting the target image of the paint film adhesion judgment area, the method further includes the following steps: On the test piece with the paint film, the area to be tested is cut out in a preset manner; The area to be tested is covered with standard adhesive tape, and after the covering adhesive tape is torn off, a paint film adhesion judgment area is obtained.

[0014] By adopting the above technical solution, the present application can simulate the paint film peeling situation in the actual use environment by pre-manufacturing a standard paint film peeling area on the surface of the test piece; and the standard tape is used to ensure the consistency and repeatability of the peeling process.

[0015] Optionally, after calculating the area of ​​each independent peeling region and accumulating the areas of all independent peeling regions to obtain the peeling area of ​​the paint film on the surface of the test piece, the method further comprises the following steps: Capturing the image of the torn adhesive tape to obtain an adhesive tape image; Calculating a reference area of ​​the peeling paint film based on the tape image, and calculating a difference between the peeling area of ​​the paint film on the surface of the test piece and the reference area of ​​the peeling paint film; If the difference is less than a preset threshold, the paint film peeling area on the surface of the test piece is determined to be the final paint film peeling area; Otherwise, a manual decision request is sent.

[0016] By adopting the above technical scheme, since the paint film peeling area calculated based on image processing may have a certain deviation from the actual peeling area, for example, improper angle and force of tearing the tape may cause incomplete paint film peeling or attached tape residue, the present application firstly collects images of the torn tape paper used to make the peeling area to obtain the tape paper image; then, based on the tape paper image, calculates the reference area of ​​the peeling paint film as the standard value; then, calculates the difference between the paint film peeling area previously obtained based on the specimen image and the above reference area; if the difference is less than a preset threshold, the peeling area calculated previously is confirmed to be the final valid result; otherwise, if the difference is too large and exceeds the acceptable range, a manual judgment request is sent, requiring manual verification and confirmation of the area result, and combining the area measurement based on the specimen image with the reference area measurement based on the tape paper image, thereby improving the accuracy of the judgment.

[0017] In a second aspect, the present application provides a paint film adhesion judgment system based on image processing, comprising: An image preprocessing module is used to collect a target image of a paint film adhesion judgment area and preprocess the target image; The area extraction module is used to perform feature recognition on the preprocessed target image and extract the paint film peeling area on the surface of the test piece; An area ratio calculation module, used to calculate the paint film peeling area ratio according to the paint film peeling area on the surface of the test piece and the area of ​​the judgment area; The adhesion level determination module is used to compare the paint film peeling area ratio with a preset adhesion level judgment standard to determine the paint film adhesion level.

[0018] In a third aspect, the present application provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned method for determining the adhesion of a paint film based on image processing when executing the computer program.

[0019] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-mentioned method for determining the adhesion of a paint film based on image processing.

[0020] In summary, the present application includes at least one of the following beneficial technical effects: 1. The present application first collects the target image of the paint film adhesion judgment area and preprocesses the image to improve the effect of subsequent feature recognition; then, feature recognition is performed on the preprocessed image to accurately extract the peeling area of ​​the paint film on the surface of the test piece; then, the proportion of the paint film peeling area is calculated based on the extracted paint film peeling area and the actual area of ​​the judgment area; finally, the calculated paint film peeling area ratio is compared with the pre-set adhesion grade judgment standard to determine and output the adhesion grade of the paint film, thereby improving the judgment efficiency and the objectivity and consistency of the judgment result; 2. The present application first divides the image pixels into two categories, target pixels and background pixels, through binarization processing; then, based on the binarization result, the image is marked for connected regions, and the connected target pixels are classified as an independent peeling region; then, the area of ​​each independent peeling region is calculated respectively, and the areas of all regions are accumulated to obtain the overall paint film peeling area, which can accurately quantify various irregular shaped peeling regions and improve the accuracy of judgment; 3. This application first analyzes the preprocessed target image and extracts features such as paint film surface texture, light distribution, color contrast, etc.; then, based on these extracted features, with the help of a pre-trained evaluation model, the credibility score of the current automatic judgment result of the paint film peeling area is calculated; then, the calculated credibility score is compared with the preset credibility threshold. When the credibility score is higher than the threshold, the automatic judgment result is directly displayed on the user interface and is regarded as a reliable result; when the credibility score is lower than the threshold, a manual judgment request is sent, requiring the operator to manually review and judge, and the automatic judgment result is not directly adopted; by setting a credibility threshold, when the credibility is high, the automatic judgment result can be directly adopted to avoid excessive reliance on manual judgment and improve judgment efficiency; when the credibility is low, manual review is automatically requested to ensure the accuracy of the result. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a flow chart of a method for judging the adhesion of a paint film based on image processing according to an embodiment of the present application; Figure 2 It is a schematic diagram of a flow chart of displaying and recording adhesion level in a method for judging adhesion of a paint film based on image processing in an embodiment of the present application; Figure 3 It is a schematic diagram of a process of credibility scoring in a paint film adhesion judgment method based on image processing in an embodiment of the present application; Figure 4 It is a schematic diagram of a process of obtaining a reference area in a method for judging the adhesion of a paint film based on image processing in an embodiment of the present application; Figure 5 This is a module schematic diagram of a paint film adhesion judgment system based on image processing in an embodiment of the present application; Figure 6 It is a diagram of the internal structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0022] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification and appended claims of the present application, the singular expressions "one", "a kind of", "said", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations comprising one or more listed items.

[0023] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0024] The embodiments of the present application are further described in detail below in conjunction with the drawings in the specification.

[0025] In the first aspect, the present application provides a method for judging the adhesion of a paint film based on image processing, referring to Figure 1 , including the following steps: S110, collecting a target image of the paint film adhesion judgment area, and preprocessing the target image.

[0026] In this embodiment, the target image refers to the surface image of the paint film that needs to be judged for adhesion. The target image can be acquired by taking a picture of the judgment area using a camera device such as a digital camera, an industrial camera or a smart phone.

[0027] Specifically, a target image of a paint film adhesion judgment area is first acquired; then image enhancement and noise removal are performed on the target image to obtain an optimized target image; and the target judgment area is detected and cropped out in the optimized target image to obtain a preprocessed target image.

[0028] S120, performing feature recognition on the preprocessed target image to extract the paint film peeling area on the surface of the test piece.

[0029] Among them, feature recognition refers to analyzing the image through the image processing algorithm to identify the range and area of ​​the paint film peeling area. In this embodiment, the pre-processed image is first binarized, the pixels are divided into target pixels (peeling area) and background pixels, and then the connected target pixel points are identified as independent peeling areas through the connected area labeling algorithm. Finally, the area of ​​each independent area is calculated and accumulated to obtain the paint film peeling area on the surface of the test piece.

[0030] Specifically, during the binarization process, the global threshold method, local threshold method or Otsu algorithm can be used to determine the appropriate grayscale threshold, and the image pixels can be binarized into 0 and 1. The connected region marking algorithm can use 4-connected or 8-connected algorithms to mark each independent peeling area. The area calculation can be performed by counting the number of target pixels in each independent area and converting the number of pixels into the actual area value.

[0031] S130. Calculate the paint film peeling area ratio according to the paint film peeling area on the surface of the test piece and the area of ​​the judgment area.

[0032] In this embodiment, the area of ​​the judgment area refers to the actual area size of the area to be tested, which can be determined by a known cutting size or calculated based on image analysis. The paint film peeling area is the result extracted in the previous step. By dividing the peeling area by the area of ​​the region, the percentage of the paint film peeling area in the region can be obtained.

[0033] Specifically, assuming that the area of ​​the judgment area is A square centimeters, and the extracted paint film peeling area is B square centimeters, then the proportion of the paint film peeling area is B / A×100%.

[0034] S140, comparing the paint film peeling area ratio with a preset adhesion grade judgment standard to determine the paint film adhesion grade.

[0035] In this embodiment, the adhesion grade judgment standard is a set of pre-established grade division rules corresponding to the area ratio, which is usually composed of multiple interval thresholds. The calculated paint film peeling area ratio value is compared with each interval threshold to determine which interval the value falls within, and the adhesion grade of the paint film can be determined accordingly.

[0036] In one embodiment, referring to Figure 2 In step S140, the paint film peeling area ratio of the test piece surface is compared with the preset adhesion grade judgment standard. After the paint film adhesion grade is determined, the method further includes the following steps: S210, displaying the effective test area image, the target image and the paint film adhesion grade on the user interface and printing them out as original records.

[0037] In this embodiment, the effective test area image refers to the image data containing only the target judgment area after preprocessing. The target image refers to the complete image originally collected. The paint film adhesion grade is the judgment result obtained based on image analysis.

[0038] Specifically, the operation interface displays the pre-processed effective test area image, the original collected complete target image, and the paint film adhesion grade result calculated based on the area ratio. At the same time, this information can be output and saved in the form of files or printouts as original evidence records for subsequent judgments.

[0039] S220, saving the original record in the database.

[0040] S230, receiving the manual determination and review results of the user in the user interface, and correcting the paint film adhesion level according to the manual determination and review results.

[0041] In this embodiment, manual judgment and review refers to manually inspecting the images and data in the original records to review and make necessary corrections to the results of the automatic judgment.

[0042] Specifically, a manual review entry is provided on the user interface, and the operator checks the image and grade result displayed in S210. If the judgment result is found to be biased, the grade result can be manually corrected on the interface. The corrected grade result will overwrite the automatic judgment result as the final judgment conclusion. At the same time, the manual review information is recorded and saved in the database.

[0043] In one embodiment, referring to Figure 3 Before receiving the manual determination and review result of the user in the user interface, the method further includes the following steps: S310, analyzing the preprocessed target image to obtain the paint film surface texture features, illumination distribution features, and paint film color and background color contrast features.

[0044] In this embodiment, the surface texture feature refers to the roughness and particle distribution of the paint film surface; the illumination distribution feature refers to the uniformity of illumination and the light-dark contrast in the image; and the color contrast feature refers to the degree of difference between the paint film color and the background color.

[0045] Specifically, the grayscale co-occurrence matrix of the preprocessed target image is calculated, and the contrast eigenvalue is extracted from it to reflect the roughness of the paint film surface. The preprocessed target image is decomposed by wavelet transform, and the energy value and entropy characteristics are extracted from the statistical characteristics of the wavelet coefficients of each scale to reflect the particle distribution on the paint film surface. The grayscale histogram of the preprocessed target image is analyzed, and the mean and standard deviation of the histogram are calculated to determine the uniformity of the illumination; then the gradient field of the preprocessed target image is calculated, and the mean and standard deviation of the gradient value reflect the light and dark contrast of the image. The preprocessed target image is clustered, and the pixels are divided into paint film color class and background color class. The centroid distance between the two color classes in the preset color space is calculated as the eigenvalue of the contrast between the paint film color and the background color.

[0046] S320, based on the paint film surface texture characteristics, the illumination distribution characteristics, and the paint film color and background color contrast characteristics, calculate the credibility score of the automatic determination of the paint film peeling area.

[0047] In this embodiment, the credibility score reflects the reliability of the automatic determination result under the current image feature conditions. When the texture feature is poor, the lighting is uneven, and the color contrast is low, the credibility score will be reduced.

[0048] Specifically, each extracted feature is quantified into a score, and the scores of these features are comprehensively calculated through a preset weighted algorithm to obtain a total score as the final credibility score.

[0049] S330: Compare the credibility score with a preset credibility threshold. When the credibility score is higher than the credibility threshold, display the currently automatically determined paint film peeling area result and paint film adhesion level on the user interface.

[0050] In this embodiment, the credibility threshold is a preset lower limit of the score. Only when the score is higher than the threshold, the automatic determination result is considered to be sufficiently reliable and can be directly displayed on the interface.

[0051] Specifically, the calculated credibility score is compared with the threshold. If the score is higher than the threshold, the previously obtained paint film peeling area result and the adhesion grade calculated therefrom are directly displayed in the result area of ​​the operation interface as the final judgment conclusion for the user to view and use.

[0052] S340: When the credibility score is lower than the credibility threshold, a manual determination request is sent to require manual review and determination.

[0053] In this embodiment, a credibility score lower than the preset threshold means that the reliability of the current automatic determination result is insufficient and there is a certain risk of deviation, and manual intervention is required for review and judgment.

[0054] Specifically, if the credibility score is lower than the threshold, the system will automatically issue a manual judgment request to the operator in the form of a pop-up prompt window, a message notification, etc., to prompt timely human intervention, use the human eye's ability to recognize and judge to analyze the paint peeling area, and give a final accurate judgment conclusion.

[0055] In one embodiment, referring to Figure 4 Before collecting the target image of the paint film adhesion judgment area, it is necessary to cut out the test area on the test piece with the paint film in a preset way; then cover the test area with standard tape, and after tearing off the covering tape, the paint film adhesion judgment area is obtained, wherein the preset methods include standard circling method, grid method, etc.

[0056] In this embodiment, after calculating the area of ​​each independent peeling region and accumulating the areas of all independent peeling regions to obtain the peeling area of ​​the paint film on the surface of the test piece, the method further includes the following steps: S410: Capture an image of the torn adhesive tape to obtain an adhesive tape image.

[0057] In this embodiment, paint film particles peeled off from the surface of the test piece adhere to the torn tape paper, and the peeling condition of the paint film on the surface of the test piece can be evaluated by analyzing the tape paper image.

[0058] Specifically, a high-resolution digital camera or an industrial camera may be used to take photos of the torn adhesive tape to obtain image data.

[0059] S420, calculating the reference area of ​​the peeling paint film based on the tape image, and calculating the difference between the peeling area of ​​the paint film on the surface of the test piece and the reference area of ​​the peeling paint film.

[0060] In this embodiment, the peeling paint film will cover the tape. It can be understood that if all the peeling paint films are adhered to the tape, and there is no falling, overlapping, or warping of the paint films on the tape and the surface of the specimen, then the reference area of ​​the peeling paint film calculated on the tape should be equal to the peeling area of ​​the paint film on the surface of the specimen.

[0061] Specifically, the tape image can be preprocessed by binarization and denoising through image processing algorithms, and then the total area of ​​the paint film particles in the image can be segmented and extracted using methods such as connected domain analysis as a reference value for the peeling paint film area. The reference value is then compared with the actual peeling area of ​​the specimen surface measured previously to calculate the difference between the two.

[0062] S430: If the difference is less than a preset threshold, the paint film peeling area on the surface of the test piece is determined to be the final paint film peeling area.

[0063] In this embodiment, the preset threshold is a reasonable difference range set according to the actual process level. As long as the difference is within this range, the two measurement results are considered to be basically consistent, and the peeling area measured on the specimen surface can be directly used as the final result.

[0064] Specifically, a percentage threshold of area difference is set. If the difference between the peeling area of ​​the specimen surface and the reference area is within the percentage threshold, the two measurement data are determined to be consistent, and the peeling area value measured on the specimen surface can be confirmed as the final result, and the corresponding paint film adhesion grade can be evaluated accordingly.

[0065] S440: Otherwise, send a manual determination request.

[0066] In this embodiment, if the difference is greater than or equal to the preset threshold, the system will automatically prompt the operator to manually review and judge the original image data. The manual judgment can choose whether to use the peeling area result measured on the surface of the test piece or the reference value of the tape according to the actual situation, or it can be combined with human eye observation to re-measure a more accurate peeling area data, and the manual judgment conclusion will be output as the final result.

[0067] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0068] In the second aspect, the present application provides a paint film adhesion judgment system based on image processing. The paint film adhesion judgment system based on image processing of the present application is described below in combination with the above-mentioned paint film adhesion judgment method based on image processing.

[0069] Reference Figure 5 , a paint film adhesion judgment system based on image processing, comprising: An image preprocessing module is used to collect a target image of a paint film adhesion judgment area and preprocess the target image; The area extraction module is used to perform feature recognition on the preprocessed target image and extract the paint film peeling area on the surface of the test piece; The area ratio calculation module is used to calculate the paint film peeling area ratio according to the paint film peeling area on the surface of the test piece and the area of ​​the judgment area; The adhesion level determination module is used to compare the paint film peeling area ratio with the preset adhesion level judgment standard to determine the paint film adhesion level.

[0070] In one embodiment, the present application provides an electronic device, which may be a server, and its internal structure diagram may be as follows: Figure 6 As shown. The electronic device includes a processor, a memory and a network interface connected through a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the electronic device is used to store data. The network interface of the electronic device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for judging the adhesion of a paint film based on image processing is implemented.

[0071] Those skilled in the art will understand that Figure 6 The structure shown in the figure is merely a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the electronic device to which the scheme of the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0072] In one embodiment, an electronic device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0073] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the above-mentioned computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0074] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, any equivalent changes made according to the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A paint film adhesion judgment method based on image processing, It is characterized in that The steps include: Collecting a target image of a paint film adhesion judgment area and preprocessing the target image; Perform feature recognition on the preprocessed target image and extract the paint peeling area on the surface of the specimen; Calculate the paint film peeling area ratio according to the paint film peeling area on the surface of the test piece and the area of ​​the judgment area; The paint film peeling area ratio is compared with a preset adhesion grade judgment standard to determine the paint film adhesion grade.

2. The method for judging the adhesion of a paint film based on image processing according to claim 1, It is characterized in that The step of collecting a target image of the paint film adhesion judgment area and preprocessing the target image specifically includes the following steps: Collect target images of the paint film adhesion judgment area; Performing image enhancement and noise removal on the target image to obtain an optimized target image; The target judgment area is detected and cropped out in the optimized target image to obtain the preprocessed target image.

3. The method for judging the adhesion of a paint film based on image processing according to claim 1, It is characterized in that The feature recognition of the pre-processed target image and the extraction of the paint film peeling area on the surface of the test piece specifically include the following steps: Binarization is performed on the preprocessed target image to determine target pixels and background pixels, wherein the target pixels are pixels of the peeling area; According to the target pixels and background pixels, the connected regions of the binarized target image are marked to identify independent peeling regions; Calculate the area of ​​each independent peeling region, add up the areas of all independent peeling regions, and obtain the peeling area of ​​the paint film on the specimen surface.

4. The method for judging the adhesion of a paint film based on image processing according to claim 1, It is characterized in that After comparing the paint film peeling area ratio on the surface of the test piece with a preset adhesion grade judgment standard and determining the paint film adhesion grade, the method further comprises the following steps: The effective test area image, target image and paint film adhesion grade are displayed on the user interface and printed out as original records; Saving the original record in a database; The manual determination and review results of the user in the user interface are received, and the paint film adhesion level is corrected according to the manual determination and review results.

5. The method for judging the adhesion of a paint film based on image processing according to claim 4, It is characterized in that Before receiving the manual determination and review result of the user on the user interface, the method further comprises the following steps: Analyze the preprocessed target image to obtain the paint film surface texture characteristics, illumination distribution characteristics, and paint film color and background color contrast characteristics; Based on the paint film surface texture characteristics, light distribution characteristics, and paint film color and background color contrast characteristics, a confidence score for automatic determination of the paint film peeling area is calculated; The credibility score is compared with a preset credibility threshold, and when the credibility score is higher than the credibility threshold, the currently automatically determined paint film peeling area result and the paint film adhesion level are displayed on the user interface; When the credibility score is lower than the credibility threshold, a manual determination request is sent to require manual review and determination.

6. The method for judging the adhesion of a paint film based on image processing according to claim 3, It is characterized in that Before collecting the target image of the paint film adhesion judgment area, the method further includes the following steps: On the test piece with the paint film, the area to be tested is cut out in a preset manner; The area to be tested is covered with standard adhesive tape, and after the covering adhesive tape is torn off, a paint film adhesion judgment area is obtained.

7. The method for judging the adhesion of a paint film based on image processing according to claim 6, It is characterized in that After calculating the area of ​​each independent peeling region and adding up the areas of all independent peeling regions to obtain the peeling area of ​​the paint film on the surface of the test piece, the method further comprises the following steps: Capturing the image of the torn adhesive tape to obtain an adhesive tape image; Calculating a reference area of ​​the peeling paint film based on the tape image, and calculating a difference between the peeling area of ​​the paint film on the surface of the test piece and the reference area of ​​the peeling paint film; If the difference is less than a preset threshold, the paint film peeling area on the surface of the test piece is determined to be the final paint film peeling area; Otherwise, a manual decision request is sent.

8. A paint film adhesion judgment system based on image processing, It is characterized in that include: An image preprocessing module is used to collect a target image of a paint film adhesion judgment area and preprocess the target image; The area extraction module is used to perform feature recognition on the preprocessed target image and extract the paint film peeling area on the surface of the test piece; An area ratio calculation module, used to calculate the paint film peeling area ratio according to the paint film peeling area on the surface of the test piece and the area of ​​the judgment area; The adhesion level determination module is used to compare the paint film peeling area ratio with a preset adhesion level judgment standard to determine the paint film adhesion level.

9. An electronic device, It is characterized in that The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the method for determining the adhesion of a paint film based on image processing described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of the paint film adhesion judgment method based on image processing described in any one of claims 1 to 7 are implemented.

Images