A method, device, and storage medium for detecting repeated defects in a display screen

Abstract

The present application discloses a method, device and storage medium for detecting repeated defects of a display screen, which is used to improve the detection efficiency of display screen defects. Perform consistency preprocessing on the collected display screen image; perform dot-line-block mura defect extraction processing on the display screen image, and perform defect area segmentation and extraction processing to generate dot-line-block defect areas; perform blob analysis on the dot-line-block defect areas to generate defect feature information; perform area merging on the dot-line-block defect areas according to the aspect ratio AR value and defect position information of the defect feature information; for several display screen images of the same ID, calculate the geometric position adjacency matching degree according to the adjacency matching degree and Euclidean distance between two dot-line-block defect areas on every two display screen images; perform over-inspection analysis processing on the display screen according to the geometric position adjacency matching degree.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of display screen detection, and in particular, to a method, device, and storage medium for detecting repeated defects of a display screen. Background Art

[0002] With the rapid development of industrial and Internet technologies, the industry's requirements for the quality of industrial products are becoming more and more refined and standardized. In the display panel industry, the quality of products directly affects their competitiveness. Among them, the accuracy of the product form and size specifications is the most basic process index of product quality. As one of the display components of a device, display screens are used in various high-end devices, such as mobile phones, TVs, and tablet computers. With the continuous improvement of people's requirements for screen display, display screens have gradually become products with high-precision technology.

[0003] Defect detection of display screens is a necessary process for adjustment. According to whether the display screen needs to be lit for detection, display screen defects can be divided into display defects and screen body defects. Display defects refer to inharmonious areas that appear during the display process of the display screen. In the prior art, display defects usually require inputting a specific image on the display screen to be tested, then collecting images through a camera, and then analyzing them through image detection. Screen body defects refer to damaged areas (such as corner breaks, foreign objects, etc.) on the surface or inside of the display screen itself. For such defects, no image needs to be input, and the images are collected through a camera, and then the images are detected through an automatic optical detection module for analysis. Some of these defects appear repeatedly in different grayscale images or even in images of different products, resulting in a large number of over-inspection phenomena. To reduce over-inspection phenomena, a defect area position matching algorithm is usually used for the defect areas of the display screen images to determine the same defect areas on the display screen images with the same ID.

[0004] However, there are some line-like scratch defects in the existing display screen defects. In the shooting angle of the side view, the scratches will be discontinuous, that is, there are break point defects that belong to the same defect on the display screen image, which increases the over-inspection situation of the display screen. Secondly, in order to protect the display screen from being scratched by the robotic arm during displacement, a protective film is usually attached to the surface of the display screen, which makes the scratch defects appear on the protective film. Although the protective film is set as thin as possible, it still has a certain thickness, and the generated scratches are deeper than those on the display screen, resulting in more easily generated break point defects. Moreover, there may also be interlayer dirt defects between the protective film and the display screen, increasing the possibility of over-inspection and reducing the detection efficiency of display screen defects. Summary of the Invention

[0005] The present application discloses a method, device, and storage medium for detecting repeated defects of a display screen, which are used to improve the detection efficiency of display screen defects.

[0006] The first aspect of this application discloses a method for detecting repeated defects of a display screen, including:

[0007] Perform consistency preprocessing on the collected display screen images;

[0008] Perform dot-line-block mura defect extraction processing on the display screen images, and perform defect area segmentation extraction processing to generate dot-line-block defect areas;

[0009] Perform blob analysis on the dot-line-block defect areas to generate defect feature information;

[0010] Perform area merging on the dot-line-block defect areas according to the aspect ratio AR value and defect position information of the defect feature information;

[0011] For several display screen images of the same ID, calculate the geometric position adjacency matching degree according to the adjacency matching degree and Euclidean distance between two dot-line-block defect areas on each two display screen images;

[0012] Perform display screen pass inspection analysis processing according to the geometric position adjacency matching degree.

[0013] Optionally, after performing display screen pass inspection analysis processing according to the geometric position adjacency matching degree, the method further includes:

[0014] For several display screen images of different IDs, calculate the geometric position relationship information and defect feature relationship information between two dot-line-block defect areas on each two display screen images;

[0015] Perform display screen batch anomaly detection according to the geometric position relationship information and defect feature relationship information.

[0016] Optionally, the geometric position relationship information is Euclidean distance information;

[0017] For several display screen images of different IDs, calculating the geometric position relationship information and defect feature relationship information between two dot-line-block defect areas on each two display screen images includes:

[0018] For several display screen images of different IDs, calculate the Euclidean distance information between two dot-line-block defect areas on each two display screen images;

[0019] Calculate the defect feature relationship information according to the roundness calculation value, contrast calculation value, and texture feature calculation value of two dot-line-block defect areas on each two display screen images.

[0020] Optionally, performing area merging on the dot-line-block defect areas according to the aspect ratio AR value and defect position information of the defect feature information includes:

[0021] Determine the line - type defect area and non - line - type defect area in the dot - line block defect area according to the aspect ratio AR value in the defect feature information;

[0022] When the line - type defect area is within the minimum circumscribed rectangle area of the non - line - type defect area, calculate the Euclidean distance between the line - type defect area and the non - line - type defect area;

[0023] When the line - type defect area is not within the minimum circumscribed rectangle area of the non - line - type defect area, determine the orientation information of the line - type defect area and the non - line - type defect area;

[0024] Calculate the Euclidean distance at the position of the adjacent corner point of the minimum circumscribed rectangle of the line - type defect area in the non - line - type defect area according to the orientation information;

[0025] Conduct a merging analysis through the Euclidean distance;

[0026] Merge and split the dot - line block defect area according to the analysis result, obtain the display screen image with connected domain labels, and generate the Blob information and feature information at the corresponding positions after merging.

[0027] Optionally, perform consistency pre - processing on the collected display screen image, including:

[0028] Perform color channel merging or splitting processing on the collected display screen image;

[0029] Perform geometric correction processing on the display screen image;

[0030] Perform pre - processing filtering on the display screen image to remove noise and background interference;

[0031] Perform enhancement processing on the pre - processed image. The enhancement processing includes shadow correction and light - dark enhancement.

[0032] Optionally, for several display screen images of the same ID, calculate the geometric position adjacency matching degree according to the adjacency matching degree and Euclidean distance of two dot - line block defect areas on every two display screen images, including:

[0033] For several display screen images of the same ID, determine the independent area, intersection area, and the area of the minimum circumscribed rectangle of the defect area jointly formed by two defect areas on every two display screen images;

[0034] Calculate the defect area adjacency matching degree according to the independent area, intersection area, and the area of the minimum circumscribed rectangle;

[0035] Calculate the defect area Euclidean distance according to the coordinate information of two defect areas on every two display screen images;

[0036] Calculate the geometric position adjacency matching degree based on the defect area adjacency matching degree and the Euclidean distance of the defect area.

[0037] The second aspect of the present application discloses a device for detecting repeated defects of a display screen, including:

[0038] A processing unit for performing consistency preprocessing on the acquired display screen image;

[0039] A first generating unit for performing dot-line-block mura defect extraction processing on the display screen image, and performing defect area segmentation extraction processing to generate dot-line-block defect areas;

[0040] A second generating unit for performing blob analysis on the dot-line-block defect areas to generate defect feature information;

[0041] A defect merging unit for performing area merging on the dot-line-block defect areas according to the aspect ratio AR value of the defect feature information and the defect position information;

[0042] A first calculation unit for calculating the geometric position adjacency matching degree according to the adjacency matching degree and the Euclidean distance between two dot-line-block defect areas on several display screen images of the same ID;

[0043] An analysis unit for performing over-inspection analysis processing of the display screen according to the geometric position adjacency matching degree.

[0044] Optionally, after the calculation unit, the device further includes:

[0045] A second calculation unit for calculating the geometric position relationship information and the defect feature relationship information between two dot-line-block defect areas on several display screen images of different IDs;

[0046] A detection unit for performing batch anomaly detection of the display screen according to the geometric position relationship information and the defect feature relationship information.

[0047] Optionally, the geometric position relationship information is Euclidean distance information;

[0048] The second calculation unit includes:

[0049] For several display screen images of different IDs, calculate the Euclidean distance information between two dot-line-block defect areas on each two display screen images;

[0050] Calculate the defect feature relationship information according to the roundness calculation value, the contrast calculation value and the texture feature calculation value of two dot-line-block defect areas on each two display screen images.

[0051] Optionally, the defect merging unit includes:

[0052] Determine the line - type defect area and non - line - type defect area in the dot - line block defect area according to the aspect ratio AR value in the defect feature information;

[0053] When the line - type defect area is within the minimum circumscribed rectangle area of the non - line - type defect area, calculate the Euclidean distance between the line - type defect area and the non - line - type defect area;

[0054] When the line - type defect area is not within the minimum circumscribed rectangle area of the non - line - type defect area, determine the orientation information of the line - type defect area and the non - line - type defect area;

[0055] Calculate the Euclidean distance of the line - type defect area at the position of the similar corner point of the minimum circumscribed rectangle of the non - line - type defect area according to the orientation information;

[0056] Conduct a merging analysis through the Euclidean distance;

[0057] Merge and split the dot - line block defect area according to the analysis result, obtain the display screen image with connected domain labels, and generate the Blob information and feature information at the corresponding positions after merging.

[0058] Optionally, the processing unit includes:

[0059] Perform color channel merging or splitting processing on the collected display screen image;

[0060] Perform geometric correction processing on the display screen image;

[0061] Perform pre - processing filtering on the display screen image to remove noise and background interference;

[0062] Perform enhancement processing on the pre - processed image, and the enhancement processing includes shadow correction and light - and - shade enhancement.

[0063] Optionally, the first calculation unit includes:

[0064] For several display screen images with the same ID, determine the independent region area, intersection region area, and the area of the minimum circumscribed rectangle of the defect region jointly formed by two defect regions on each two display screen images;

[0065] Calculate the defect region adjacency matching degree according to the independent region area, intersection region area, and minimum circumscribed rectangle area;

[0066] Calculate the Euclidean distance of the defect region according to the coordinate information of two defect regions on each two display screen images;

[0067] Calculate the geometric position adjacency matching degree according to the defect region adjacency matching degree and the Euclidean distance of the defect region.

[0068] A third aspect of the present application provides a device for detecting repeated defects of a display screen, comprising:

[0069] Processor, memory, input-output unit, and bus;

[0070] The processor is connected to the memory, the input and output unit, and the bus;

[0071] The memory stores a program, and the processor calls the program to execute the first aspect and any optional method of the first aspect.

[0072] A fourth aspect of the present application provides a computer-readable storage medium, on which a program is stored. When the program is executed on a computer, the program executes the first aspect and any optional method of the first aspect.

[0073] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0074] In this application, the collected display screen images are firstly preprocessed for consistency, so that each image can avoid large display deviations and relative position deviations as much as possible. Each display screen image is subjected to point line block mura defect extraction processing, and defect area segmentation and extraction processing is performed to generate point line block defect areas, that is, defects of different forms are extracted and located. Next, the point line block defect area is subjected to blob analysis to generate defect feature information of each point line block defect area. The aspect ratio AR value is determined according to the defect feature information, and the point line block defect areas that meet the conditions are merged according to the aspect ratio AR value and the defect position information to reduce the breakpoint defects on the display screen or protective film on the same display screen image. For several display screen images with the same ID, the geometric position adjacency matching degree is calculated based on the adjacency matching degree and Euclidean distance of the two point line block defect areas on each two display screen images. The display screen is then inspected and analyzed based on the geometric position adjacency matching degree. Through the two parameters of adjacency matching and Euclidean distance, the geometric position adjacency matching of the defect area is analyzed in terms of positional relationship and morphological relationship, making the image repeated defect detection more accurate and improving the detection efficiency of display screen defects. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0076] Figure 1 A schematic diagram of an embodiment of a method for repeated defect detection of a display screen of the present application;

[0077] Figure 2 Schematic diagram of an embodiment of the method for batch anomaly detection of the display screen in this application;

[0078] Figure 3 Schematic diagram of an embodiment of the method for calculating the relationship information between geometric position and defect characteristics in this application;

[0079] Figure 4 Schematic diagram of an embodiment of the method for region merging in this application;

[0080] Figure 5 Schematic diagram of an embodiment of the method for consistency preprocessing in this application;

[0081] Figure 6 Schematic diagram of an embodiment of the method for calculating the adjacency matching degree of geometric positions in this application;

[0082] Figure 7 Schematic diagram of an embodiment of the device for detecting repeated defects of the display screen in this application;

[0083] Figure 8 Schematic diagram of another embodiment of the device for detecting repeated defects of the display screen in this application. Detailed implementation manners

[0084] In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of this application. However, those skilled in the art should clearly understand that this application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of this application.

[0085] It should be understood that when used in the specification of this application and the appended claims, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0086] It should also be understood that the term "and / or" as used in the specification of this application and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0087] As used in the specification of this application and the appended claims, the term "if" may be construed, depending on the context, as "when", "once", "in response to determining", or "in response to detecting". Similarly, the phrase "if determined" or "if [the described condition or event] is detected" may be construed, depending on the context, to mean "once determined", "in response to determining", "once [the described condition or event] is detected", or "in response to detecting [the described condition or event]".

[0088] In addition, in the description of the specification of this application and the appended claims, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and cannot be construed as indicating or implying relative importance.

[0089] Reference to "one embodiment" or "some embodiments" or the like described in the specification of this application means that a specific feature, structure, or characteristic described in connection with that embodiment is included in one or more embodiments of this application. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification do not necessarily all refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in another way. The terms "comprising", "including", "having", and their variants all mean "including but not limited to", unless otherwise specifically emphasized in another way.

[0090] In the prior art, there are some line - like scratch defects in the display screen defects. In the shooting angle of the side view, the scratches are discontinuous, that is, there are breakpoint defects that originally belong to the same defect in the display screen image, which increases the situation of the display screen passing the inspection. Secondly, in order to protect the display screen from being scratched by the robotic arm during displacement, a protective film is usually attached to the surface of the display screen. This makes the scratch defects appear on the protective film. Although the protective film is set as thin as possible, it still has a certain thickness, and the scratches generated are deeper than those on the display screen, resulting in more easily generated breakpoint defects. And there may also be interlayer dirt defects between the protective film and the display screen, increasing the possibility of passing the inspection and reducing the detection efficiency of the display screen defects.

[0091] Based on this, the present application discloses a method, device, and storage medium for detecting repeated defects of a display screen to improve the detection efficiency of display screen defects.

[0092] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts belong to the scope of protection of the present application.

[0093] The method of the present application can be applied to a server, a device, a terminal, or other devices with logical processing capabilities. In this regard, the present application makes no limitation. For the convenience of description, the following takes the execution entity as a terminal as an example for description.

[0094] Please refer to Figure 1 , an embodiment of a method for detecting repeated defects of a display screen provided by the present application includes:

[0095] 101. Perform consistency preprocessing on the collected display screen images;

[0096] The terminal first obtains a batch of display screens of the same type. For each display screen with an ID, multiple images of different grayscale levels are taken. The captured images of different grayscale levels of the same display screen and the captured images of different grayscale levels of different display screens are all subjected to consistency preprocessing, so that there will be no images that cannot be compared with each other, and the position of the display screen can be calibrated, making the position of the defective area relatively accurate.

[0097] 102. Perform point-line-block mura defect extraction processing on the display screen images, and perform defective area segmentation extraction processing to generate point-line-block defective areas;

[0098] The terminal performs point, line, and block mura defect extraction on the display screen images after consistency preprocessing. Through defect extraction from small to large in sequence, the defects can be accurately divided. The point-line convolution filtering window is used for defective area segmentation extraction to generate point-line-block defective areas.

[0099] 103. Perform blob analysis on the point-line-block defective areas to generate defect feature information;

[0100] First, the terminal performs blob analysis on the extracted point-line-block defective areas to extract defect feature information. Among them, the defect feature information includes the centroid coordinates, upper-left and lower-right coordinates, corner coordinates, area, minimum circumscribed rectangle boundary coordinates, aspect ratio, foreground (background) average concentration, contrast, and shape texture features of the corresponding defective area.

[0101] 104. Perform area merging on the point-line-block defective areas according to the aspect ratio AR value of the defect feature information and the defect position information;

[0102] In this embodiment, the terminal merges the dot-line block defect regions based on the aspect ratio AR value of the defect feature information and the defect position information, so as to reduce the break point defects on the display screen or the protective film on the same display screen image.

[0103] 105. For several display screen images of the same ID, calculate the geometric position adjacency matching degree according to the adjacency matching degree and the Euclidean distance of two dot-line block defect regions on every two display screen images;

[0104] The terminal calculates the geometric position adjacency matching degree for several display screen images of the same ID according to the adjacency matching degree and the Euclidean distance of two dot-line block defect regions on every two display screen images. The geometric position adjacency matching degree of the defect region can be analyzed in terms of the position relationship and the morphological relationship through the two parameters of the adjacency matching degree and the Euclidean distance, so that the detection of image duplicate defects is more accurate and the detection efficiency of display screen defects is improved.

[0105] 106. Perform over-inspection analysis and processing on the display screen according to the geometric position adjacency matching degree.

[0106] Finally, the terminal determines multiple regions belonging to the same defect in the display screen images of the same ID according to the geometric position adjacency matching degree, and performs over-inspection analysis and processing on the display screen to reduce the occurrence of repeated confirmation of defect regions.

[0107] When duplicate defects are detected for the same ID of defects, according to the set duplicate defect threshold parameter, when quality-related abnormal defects are encountered in on-site applications, the defects at the current position can be set as one defect, without repeating the alarm control, to prevent repeated alarms and increase redundant information. The on-site user only needs to observe the final defect information.

[0108] In this embodiment, the collected display screen images are firstly subjected to consistency preprocessing so that each image can avoid large display deviations and relative position deviations as much as possible. Each display screen image is subjected to point line block mura defect extraction processing, and defect area segmentation and extraction processing is performed to generate point line block defect areas, that is, defects of different forms are extracted and located. Next, the point line block defect area is subjected to blob analysis to generate defect feature information of each point line block defect area. The aspect ratio AR value is determined according to the defect feature information, and the point line block defect areas that meet the conditions are merged according to the aspect ratio AR value and the defect position information to reduce the breakpoint defects on the display screen or protective film on the same display screen image. For several display screen images with the same ID, the geometric position adjacency matching degree is calculated based on the adjacency matching degree and Euclidean distance of the two point line block defect areas on each two display screen images. Then, the display screen is inspected and analyzed according to the geometric position adjacency matching degree. Through the two parameters of adjacency matching and Euclidean distance, the geometric position adjacency matching of the defect area is analyzed in terms of positional relationship and morphological relationship, making the image repeated defect detection more accurate and improving the detection efficiency of display screen defects.

[0109] See also Figure 2 The present application provides an embodiment of a method for batch abnormality detection of display screens, comprising:

[0110] 201. For a plurality of display screen images with different IDs, calculate geometric position relationship information and defect feature relationship information of two point-line block defect areas on every two display screen images;

[0111] 202. Perform batch anomaly detection on display screens based on geometric position relationship information and defect feature relationship information.

[0112] In this embodiment, the terminal first calculates the geometric position relationship information and defect feature relationship information of two point-line block defect areas on each two display screen images for several display screen images with different IDs. The collective position relationship refers to the relative position of the two defect areas, and the defect feature relationship information refers to the similarity and correlation between the morphological feature data on the defect areas.

[0113] The terminal performs batch anomaly detection on the display screen based on the geometric position relationship information and the defect feature relationship information. Specifically, during the production and detection process of display screens with different IDs, each industrial control computer on-site in real-time detects whether there are repeated defects. If there are detections and the number of repetitions exceeds the empirical number set by the user, at this time, the process alarms to prompt and timely remind to prevent batch defects from occurring on the current machine. In addition, since the repeated defect data information generated each time is stored in a given format as parameters, the database file has less information, occupies less space, and has a fast upload and download parsing speed and is concise and clear. Therefore, this type of data can be uploaded to the workshop shared directory for sharing by all machines. Third-party software such as CIM can achieve timely data sharing and timely early warning decision-making by monitoring the data generated by repeated defects in real-time.

[0114] After the detection is completed, defect integration is carried out, and the steps are as follows:

[0115] 1) When running for the first time, a repeated defect data set is generated and stored in the database. In addition to the coordinate information of the current defect and the defect information features (position coordinates, area, shape, texture, contrast value, etc.) of the previous step in the data set content, there are also two pieces of information: the continuous repetition count m and the repetition count nm among the given n data.

[0116] 2) When subsequent products are run, if the geometric positions and features of the detected defects in two times can be matched, it is regarded as the repeated defect position, and the repeated defect information at this time is recorded, the repetition count m is incremented by 1, and the nm count is also incremented by 1. If no repeated defect is found, the current data set m is set to 0, and the nm count remains unchanged.

[0117] 3) According to the software settings, it can be divided into continuous counting method and interval counting method.

[0118] a. If the continuous counting method is set, each time it is judged that there are repeated defects, the current defect data information is stored in the database in the specified format, and the repetition count m is incremented by 1. If it is not a repeated defect, m is set to 0. This is the case for each product detection process.

[0119] b. If the interval counting method is set, first set the maximum storage entries, such as 100 entries (when the production data is less than 100, the extra entries are set to null or default values). Each entry contains the defect information detected for a piece of product:

[0120] When the data is less than 100, the defect information of each input data is stored in the entry in order. Each time it is judged that it is a repeated defect, the corresponding nm flag is incremented by 1, otherwise it remains unchanged.

[0121] When the production data exceeds 100, the latest entry in the data set replaces the first entry.

[0122] Please refer toFigure 3 , an embodiment of a method for calculating the relationship information between geometric position and defect characteristics provided by this application includes:

[0123] 301. For several display screen images with different IDs, calculate the Euclidean distance information between two point-line-block defect regions on each pair of display screen images;

[0124] 302. Calculate the defect characteristic relationship information according to the roundness calculation value, contrast calculation value, and texture feature calculation value of the two point-line-block defect regions on each pair of display screen images.

[0125] The terminal calculates the Euclidean distance information between two point-line-block defect regions on each pair of display screen images with different IDs. Calculate the defect characteristic relationship information according to the roundness calculation value, contrast calculation value, and texture feature calculation value of the two point-line-block defect regions on each pair of display screen images. Specifically, for different types of product IDs, the terminal will first record the defect information of the display screen during two runs, including defect type (bright point, dark point, or others), area, centroid coordinates, upper-left, lower-right corner coordinates of the minimum circumscribed rectangle, texture feature, contrast, shape feature information, etc.

[0126] After the subsequent display screen runs, compare the current defect data information with the data of the previous display screen, and consider whether it is a repeated defect from two dimensions: one is the geometric position relationship, and the other is the eigenvalue matching degree: If the geometric positions and characteristics of the defects detected twice can match, it is regarded as the position of the repeated defect, and record the repeated defect information at this time. Geometrically, through the distance between the center coordinates of their respective defects, the eigenvalues are matched from the aspects of contrast, texture, and shape features:

[0127] The geometric relationship characteristics are as follows:

[0128]

[0129] is the Euclidean distance between defect p region and defect q region, is the abscissa of the center coordinate of defect p region, is the ordinate of the center coordinate of defect p region, is the abscissa of the center coordinate of defect q region, is the ordinate of the center coordinate of defect q region.

[0130] The expression of the eigenvalue (defect characteristic relationship information) in simplified form is:

[0131]

[0132] where represents the roundness calculation value, is the contrast calculation value, is the texture feature calculation value. The roundness calculation value refers to the roundness morphological feature of the defect area. Even if there is a protective film, the corresponding roundness calculation value is still generated according to the image information.

[0133] First, obtain the , and of the P defect area, and obtain the , and of the Q defect area. The specific formulas are as follows:

[0134] First, calculate the weights of the roundness calculation value, the contrast calculation value, and the texture feature calculation value. The calculation methods are as follows:

[0135]

[0136]

[0137]

[0138]

[0139] In the above formulas, the characteristic quantities of the three defect areas of the roundness calculation value, the contrast calculation value, and the texture feature calculation value are used to integrate them to form the weight parameters between the defect areas, and then the defect feature relationship information is calculated, which can better compare the morphological correlation between the defect areas.

[0140] Please refer to Figure 4 , this application provides an embodiment of a method for region merging, including:

[0141] 401. Determine the line-type defect area and the non-line-type defect area in the point-line block defect area according to the aspect ratio AR value in the defect feature information;

[0142] 402. When the line-type defect area is within the minimum circumscribed rectangle area of the non-line-type defect area, calculate the Euclidean distance between the line-type defect area and the non-line-type defect area;

[0143] 403. When the line-type defect area is not within the minimum circumscribed rectangle area of the non-line-type defect area, determine the orientation information of the line-type defect area and the non-line-type defect area;

[0144] 404. Calculate the Euclidean distance at the corner point position close to the minimum circumscribed rectangle of the non-line-type defect area by the line-type defect area according to the orientation information;

[0145] 405. Perform merging analysis through the Euclidean distance;

[0146] 406. Merge and split the defective areas of the dot-line block according to the analysis results, obtain the display screen image with connected domain labels, and generate the Blob information and feature information at the corresponding positions after merging.

[0147] In this embodiment, the terminal determines the line-type defective area and non-line-type defective area in the dot-line block defective area according to the aspect ratio AR value in the defective feature information. When the line-type defective area is within the minimum circumscribed rectangle area of the non-line-type defective area, calculate the Euclidean distance between the line-type defective area and the non-line-type defective area. When the line-type defective area is not within the minimum circumscribed rectangle area of the non-line-type defective area, determine the orientation information of the line-type defective area and the non-line-type defective area. Calculate the Euclidean distance of the line-type defective area at the position of the corner point close to the minimum circumscribed rectangle of the non-line-type defective area according to the orientation information. The terminal performs merge analysis through the Euclidean distance. The terminal merges and splits the dot-line block defective area according to the analysis results, obtains the display screen image with connected domain labels, and generates the Blob information and feature information at the corresponding positions after merging.

[0148] Specifically, the terminal merges the defective areas of the segmented regions and integrates the regions according to the blob region information, aiming to reduce the misdetection of the blob regions after the small defective segmented regions. Ideally, a single defective target should be connected after segmentation. However, due to the setting of the defective segmentation algorithm threshold, uneven display screen brightness, and other reasons, the same defective area may be segmented into multiple small sub-defects, which will cause the characteristic quantity of the defect to be distorted during subsequent repeated foreign object judgment, resulting in misjudgment of repeated defects. Therefore, this embodiment proposes an algorithm for overall analysis and merging of the defective extraction regions to ensure the accuracy of subsequent repeated foreign object extraction:

[0149] When the terminal performs blob analysis on the extracted dot-line block defective area and extracts the defective feature information, it obtains the centroid coordinates, upper-left and lower-right coordinates, corner point coordinates, area, minimum circumscribed rectangle boundary coordinates, aspect ratio, foreground (background) average concentration, contrast, and shape texture features of the corresponding defective area.

[0150] Next, the terminal calculates the regions geometrically close to the current defective area, and the steps are as follows:

[0151] a. Suppose k defects are detected, and the current defect serial number is i (0 < i <= k). Determine whether the current defective area p is a line-type defect. Identify the defect with an aspect ratio AR value greater than the given parameter as a line-type abnormality, otherwise it is a non-line-type defect;

[0152] b. The merging strategy for line defects and non-line defects is as follows. For the defective area p of line defects, first determine whether the defective area p is within the minimum circumscribed rectangle area of other non-line defects i. If it is within the area, only calculate the Euclidean distance from the defective area p to the defective area i. If it is not within the minimum circumscribed rectangle area, continue the following determination;

[0153] c. Determine which position (upper left, lower left, upper right, lower right) the defective area p is in the defective area i, and then calculate the Euclidean distance between the defective area p and the similar corner point position of the minimum circumscribed rectangle of the defective area i;

[0154] d. Then, the terminal first classifies the defective areas that can be merged into one category according to the calculated Euclidean distance, and then sets a label number for each category of areas;

[0155] On the basis of the previous step, the terminal further merges and splits the areas through feature quantities such as texture, shape, and contrast. Finally, a label map with connected domain labels is obtained, and the corresponding Blob information and feature information at the merged positions are calculated. Then, the defective feature information of the segmented area is obtained, including features such as area, coordinate position, shape features (horizontal and vertical lengths), and contrast.

[0156] Please refer to Figure 5 , an embodiment of a method for consistency preprocessing provided by this application includes:

[0157] 501. Perform color channel merging or splitting processing on the collected display screen image;

[0158] 502. Perform geometric correction processing on the display screen image;

[0159] 503. Perform preprocessing filtering on the display screen image to remove noise and background interference;

[0160] 504. Perform enhancement processing on the preprocessed image. The enhancement processing includes shadow correction and brightness enhancement.

[0161] In this embodiment, the terminal performs color channel merging or splitting on the collected display screen image, and then performs geometric correction on the display screen image. The terminal performs preprocessing filtering on the display screen image to remove noise and background interference, and finally performs enhancement processing on the preprocessed image. The enhancement processing includes shadow correction and brightness enhancement. Specifically, the terminal performs color channel merging or splitting on the display screen image to generate a grayscale image or a single-channel image. Then, the terminal performs geometric correction on the above image. The purpose is to be able to calculate relative coordinates with respect to the origin of the corner points of the screen resolution when calculating coordinates later. For different products, due to the change in the incoming material placement position, it is very important to calculate the relative coordinates of the same standard. Next, the terminal performs preprocessing filtering on the geometrically corrected display screen image to remove interference such as noise and background. Finally, the terminal performs further enhancement processing on the preprocessed display screen image, including shadow correction, brightness enhancement, etc.

[0162] Please refer to Figure 6 , an embodiment of a method for calculating the adjacency matching degree of geometric positions provided by this application includes:

[0163] 601. For several display screen images of the same ID, determine the area of the independent region, the area of the intersecting region, and the area of the minimum circumscribed rectangle of the defect region jointly formed by two defect regions on each two display screen images;

[0164] 602. Calculate the adjacency matching degree of the defect region according to the area of the independent region, the area of the intersecting region, and the area of the minimum circumscribed rectangle;

[0165] 603. Calculate the Euclidean distance of the defect region according to the coordinate information of the two defect regions on each two display screen images;

[0166] 604. Calculate the adjacency matching degree of the geometric position according to the adjacency matching degree of the defect region and the Euclidean distance of the defect region.

[0167] In this embodiment, for several display screen images of the same ID, the terminal first determines the area of the independent region of the two defect regions on each two display screen images and , the area of the intersecting region and the area of the minimum circumscribed rectangle of the defect region jointly formed, . Next, the terminal calculates the adjacency matching degree of the defect region according to the area of the independent region, the area of the intersecting region, and the area of the minimum circumscribed rectangle. Calculate the Euclidean distance of the defect region according to the coordinate information of the two defect regions on each two display screen images. Calculate the adjacency matching degree of the geometric position according to the adjacency matching degree of the defect region and the Euclidean distance of the defect region.

[0168] Specifically, for the same product ID, the location of the defective area generally remains roughly unchanged. However, due to changes in the hardware of the detection screen, exposure, gain, etc., as well as differences in software detection parameters, there will be some differences in the detected areas. After region extraction and merging, the similarity matching degree of the detected defective areas in the front and back comparison screens is calculated.

[0169] After obtaining the merged defective areas for both display screen images, calculate the adjacent defect region matching degree ATR of the two regions r and t between the front and back display screen images:

[0170]

[0171] Then, calculate the Euclidean distance of the defective areas based on the coordinate information of the two defective areas on each pair of display screen images. The formula is as follows:

[0172]

[0173] is the Euclidean distance between the defective area r and the defective area t, is the abscissa of the center coordinate of the defective area r, is the ordinate of the center coordinate of the defective area r, is the abscissa of the center coordinate of the defective area t, is the ordinate of the center coordinate of the defective area t.

[0174] The geometric position adjacent matching degree, denoted as IR, has the following simple formula:

[0175]

[0176]

[0177]

[0178] Among them and represent the areas of regions r and t respectively, represents the intersection of the two regions, represents the adjacent defect region matching degree between the two defective areas, generally using the Dice matching coefficient; represents the Euclidean distance between the center coordinates of r and t, represents the area of the minimum circumscribed rectangle calculated for the region jointly composed of regions r and t. The meaning of the above expression is that when r and t simultaneously satisfy and the threshold parameters (a, b, c, and d are preset threshold parameters), they are considered candidate regions of a repeated defect.

[0179] Calculate whether the defect feature information of r and t can be matched. If they are close and the calculation result of the previous step is within the given parameter range, it is finally determined that they belong to repeated defects.

[0180] Output the feature information of repeated defects, and determine the subsequent process according to whether its features meet the preset threshold parameters.

[0181] Please refer to Figure 7 , an embodiment of a device for detecting repeated defects of a display screen provided by the present application includes:

[0182] A processing unit 701 for performing consistency preprocessing on the collected display screen image;

[0183] Optionally, the processing unit 701 includes:

[0184] Perform color channel merging or splitting processing on the collected display screen image;

[0185] Perform geometric correction processing on the display screen image;

[0186] Perform preprocessing filtering on the display screen image to remove noise and background interference;

[0187] Perform enhancement processing on the preprocessed image. The enhancement processing includes shadow correction and brightness enhancement.

[0188] A first generation unit 702 for performing dot-line-block mura defect extraction processing on the display screen image and performing defect area segmentation extraction processing to generate dot-line-block defect areas;

[0189] A second generation unit 703 for performing blob analysis on the dot-line-block defect areas to generate defect feature information;

[0190] A defect merging unit 704 for performing region merging on the dot-line-block defect areas according to the aspect ratio AR value and defect position information of the defect feature information;

[0191] Optionally, the defect merging unit 704 includes:

[0192] Determine the line-type defect area and non-line-type defect area in the dot-line-block defect area according to the aspect ratio AR value in the defect feature information;

[0193] When the line-type defect area is within the minimum circumscribed rectangle area of the non-line-type defect area, calculate the Euclidean distance between the line-type defect area and the non-line-type defect area;

[0194] When the line-type defect area is not within the minimum circumscribed rectangle area of the non-line-type defect area, determine the orientation information of the line-type defect area and the non-line-type defect area;

[0195] Calculate the Euclidean distance of the approximate corner points of the minimum circumscribed rectangle of the line defect area in the non-line defect area according to the orientation information;

[0196] Perform combined analysis through the Euclidean distance;

[0197] Merge and split the point-line block defect area according to the analysis result, obtain the display screen image with connected domain labels, and generate the Blob information and feature information at the corresponding position after merging.

[0198] The first calculation unit 705 is used to calculate the geometric position adjacency matching degree according to the adjacency matching degree and Euclidean distance of two point-line block defect areas on every two display screen images for several display screen images of the same ID;

[0199] Optionally, the first calculation unit 705 includes:

[0200] For several display screen images of the same ID, determine the area of the independent area, the area of the intersecting area, and the area of the minimum circumscribed rectangle of the defect area jointly composed of two defect areas on every two display screen images;

[0201] Calculate the defect area adjacency matching degree according to the area of the independent area, the area of the intersecting area, and the area of the minimum circumscribed rectangle;

[0202] Calculate the defect area Euclidean distance according to the coordinate information of two defect areas on every two display screen images;

[0203] Calculate the geometric position adjacency matching degree according to the defect area adjacency matching degree and the defect area Euclidean distance.

[0204] The analysis unit 706 is used to perform over-inspection analysis and processing of the display screen according to the geometric position adjacency matching degree;

[0205] The second calculation unit 707 is used to calculate the geometric position relationship information and defect feature relationship information of two point-line block defect areas on every two display screen images for several display screen images of different IDs;

[0206] The second calculation unit 707 includes:

[0207] For several display screen images of different IDs, calculate the Euclidean distance information of two point-line block defect areas on every two display screen images;

[0208] Calculate the defect feature relationship information according to the roundness calculation value, contrast calculation value, and texture feature calculation value of two point-line block defect areas on every two display screen images.

[0209] The detection unit 708 is used to perform batch anomaly detection of the display screen according to the geometric position relationship information and defect feature relationship information.

[0210] Please refer to Figure 8 , this application provides a device for detecting repeated defects of a display screen, including:

[0211] A processor 801, a memory 802, an input / output unit 803, and a bus 804.

[0212] The processor 801 is connected to the memory 802, the input / output unit 803, and the bus 804.

[0213] The memory 802 stores a program, and the processor 801 calls the program to execute the methods such as Figure 1 , Figure 2 and Figure 3 , Figure 4 , Figure 5 and Figure 6 in it.

[0214] This application provides a computer-readable storage medium with a program stored thereon. When the program is executed on a computer, it executes the methods such as Figure 1 , Figure 2 and Figure 3 , Figure 4 , Figure 5 and Figure 6 in it.

[0215] Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0216] In several embodiments provided by this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0217] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or they can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0218] In addition, each functional unit in various embodiments of the present application may be integrated into one processing unit, may exist separately as individual physical units, or two or more units may be integrated into one unit. The above-mentioned integrated units may be implemented in the form of hardware or in the form of software functional units.

[0219] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, may be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, read-only memory), random access memories (RAM, random access memory), magnetic disks, or optical discs that can store program codes.

Claims

1. A method for detecting repeated defects in a display screen, characterized in that: include: Perform consistency preprocessing on the collected display screen images; Performing point-line-block mura defect extraction processing on the display screen image, and performing defect area segmentation extraction processing to generate point-line-block defect areas; Performing blob analysis on the defective area of ​​the dotted line block to generate defect feature information; Merging the defect areas of the point-line blocks according to the aspect ratio AR value of the defect feature information and the defect position information; For several display screen images with the same ID, the geometric position adjacency matching degree is calculated based on the adjacency matching degree and Euclidean distance of the defect areas of two point-line blocks on each two display screen images; Performing display screen over-inspection analysis and processing according to the geometric position adjacency matching degree; For a number of display screen images with different IDs, calculate the geometric position relationship information and defect feature relationship information of two point-line block defect areas on every two display screen images, wherein the geometric position relationship information is Euclidean distance information; For a number of display screen images with different IDs, the geometric position relationship information and defect feature relationship information of two dot-line block defect areas on every two display screen images are calculated, including: for a number of display screen images with different IDs, the Euclidean distance information of two dot-line block defect areas on every two display screen images is calculated; the defect feature relationship information is calculated according to the roundness calculation value, contrast calculation value and texture feature calculation value of the two dot-line block defect areas on every two display screen images; Batch abnormality detection of display screens is performed based on the geometric position relationship information and the defect feature relationship information.

2. The method according to claim 1, characterized in that Merging the point-line block defect areas according to the aspect ratio AR value of the defect feature information and the defect position information includes: Determine the linear defect region and the non-linear defect region in the point-line block defect region according to the aspect ratio AR value in the defect feature information; When the linear defect region is within the minimum circumscribed rectangular region of the non-linear defect region, calculating the Euclidean distance between the linear defect region and the non-linear defect region; When the linear defect region is not located within the minimum circumscribed rectangular region of the non-linear defect region, determining the orientation information of the linear defect region and the non-linear defect region; Calculate the Euclidean distance between the positions of the nearest corner points of the minimum circumscribed rectangles of the linear defect region and the non-linear defect region according to the orientation information; Merge analysis was performed using Euclidean distance; The point, line, and block defect areas are merged and split according to the analysis results, a display screen image with a connected domain label is obtained, and Blob information and feature information of the corresponding position after the merger are generated.

3. The method according to claim 1, characterized in that Perform consistency preprocessing on the collected display screen images, including: Perform color channel merging or splitting processing on the collected display screen images; Performing geometric correction processing on the display screen image; Pre-processing and filtering the display screen image to remove noise and background interference; The preprocessed image is enhanced, and the enhancement process includes shadow correction and brightness enhancement.

4. The method according to claim 1, characterized in that: For several display screen images with the same ID, the geometric position adjacency matching degree is calculated based on the adjacency matching degree and Euclidean distance of the two point-line block defect areas on each two display screen images, including: For several display screen images with the same ID, determine the independent area area, the intersecting area area and the minimum circumscribed rectangular area of ​​the two defect areas on every two display screen images; Calculate the adjacency matching degree of the defective area according to the area of ​​the independent area, the area of ​​the intersecting area and the area of ​​the minimum circumscribed rectangle; Calculate the Euclidean distance of the defective area according to the coordinate information of the two defective areas on each two display screen images; The geometric position adjacency matching degree is calculated according to the defect area adjacency matching degree and the Euclidean distance of the defect area.

5. A device for detecting repeated defects of a display screen, characterized in that: include: A processing unit, used for performing consistency preprocessing on the collected display screen images; A first generating unit is used to perform a point line block mura defect extraction process on the display screen image, and perform a defect area segmentation extraction process to generate a point line block defect area; A second generating unit is used to perform blob analysis on the point line block defect area to generate defect feature information; A defect merging unit is configured to merge the defect areas of the point-line block according to the aspect ratio AR value and the defect position information of the defect feature information; The first calculation unit is used to calculate the geometric position adjacency matching degree according to the adjacency matching degree and the Euclidean distance of the defect areas of two point-line blocks on each two display screen images for a plurality of display screen images with the same ID; An analysis unit, configured to perform display screen over-inspection analysis processing according to the geometric position adjacency matching degree; The second calculation unit is used to calculate the geometric position relationship information and defect feature relationship information of two point-line block defect areas on every two display screen images for a plurality of display screen images with different IDs; The geometric position relationship information is Euclidean distance information; The second calculation unit includes: for a plurality of display screen images with different IDs, calculating the Euclidean distance information of two dot-line block defect areas on every two display screen images; calculating the defect feature relationship information according to the roundness calculation value, contrast calculation value and texture feature calculation value of the two dot-line block defect areas on every two display screen images; A detection unit is used to perform batch abnormality detection of display screens based on the geometric position relationship information and the defect feature relationship information.

6. A device for detecting repeated defects in a display screen, characterized in that: include: Processor, memory, input-output unit, and bus; The processor is connected to the memory, the input and output unit, and the bus; The memory stores a program, and the processor calls the program to execute the method according to any one of claims 1 to 4.

7. A computer-readable storage medium having a program stored thereon, wherein the program, when executed on a computer, performs the method according to any one of claims 1 to 4.

Images