A display screen multi-parameter detection method and system

Abstract

The application relates to the technical field of display screen detection, and particularly discloses a display screen multi-parameter detection method and system, which comprises a display screen image acquisition module, a display screen image preprocessing module, a display screen image feature extraction module, a display screen performance parameter detection module, a display screen image anomaly detection module, a display screen image anomaly control module, a display screen detection quality analysis module and a display screen detection result display module; the application collects display screen images and pre-processes the images; image features are extracted, performance parameter evaluation coefficients and image anomaly feature coefficients are obtained through analysis, image anomaly data is controlled through a display screen image anomaly control coefficient, and finally, a quality evaluation index of a target display screen is obtained through analysis; through the introduction of a deep learning recognition algorithm and an image processing technology, the application not only improves detection precision and efficiency, but also realizes the automation and intelligentization of detection, and provides strong support for display screen production and management.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of display screen detection, and particularly relates to a display screen multi-parameter detection method and system. BACKGROUND

[0002] With the continuous development of display technology, the application of display is more and more extensive, from daily computer display, television screen to various mobile device display screens. The quality requirements of display screens are also increasing, and any screen defects may affect user experience, such as bright spots, dark spots, bad points, color deviation, uneven brightness and the like.

[0003] At present, the traditional display screen detection method has many defects: first, the traditional display screen detection relies on manual observation, and the detection personnel need to carefully check the screen one by one, which is slow and difficult to meet the efficient detection needs of large-scale display production. In the production peak season or when the order quantity is large, it is easy to cause production backlog; secondly, when the detection personnel detects manually, the vision condition, fatigue degree and personal experience difference of the detection personnel will affect the detection result, leading to unstable detection result, missing bad points, misjudging color deviation and the like, affecting product quality control; in addition, the traditional method is difficult to comprehensively and accurately detect the key performance parameters of the screen such as brightness uniformity, color gamut accuracy and response time, which cannot meet the market requirements for high-quality and diversified performance detection of display, and is not conducive to the improvement of product competitiveness in the market.

[0004] Therefore, there is an urgent need for an efficient, accurate and comprehensive display screen detection technology to solve the problems existing in the prior art. SUMMARY

[0005] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present application provide a display screen multi-parameter detection method and system to solve the problems proposed in the above background.

[0006] To achieve the above-mentioned purpose, the present application provides the following technical scheme: a display screen multi-parameter detection system, comprising: a display screen image acquisition module, a display screen image preprocessing module, a display screen image feature extraction module, a display screen performance parameter detection module, a display screen image anomaly detection module, a display screen image anomaly control module, a display screen detection quality analysis module and a display screen detection result display module.

[0007] The display screen image acquisition module: uses a high-resolution image acquisition device to acquire the image of the target display screen, and marks it as a display screen image to be processed;

[0008] The display screen image preprocessing module is configured to preprocess the display screen image to be processed by using an image enhancement and filtering algorithm, and mark the preprocessed image as a display screen image to be detected.

[0009] The display screen image feature extraction module is configured to extract image features from the display screen image to be detected, wherein the image features include image performance parameter features and image abnormal parameter features.

[0010] The display screen performance parameter detection module is configured to detect and analyze display screen performance parameters based on the image performance parameter features, and obtain a performance parameter evaluation coefficient of the target display screen.

[0011] The display screen image abnormality detection module is configured to detect and analyze display screen image abnormalities based on the image abnormal parameter features, and obtain an image abnormality feature coefficient of the target display screen.

[0012] The display screen image abnormality control module is configured to compare the image abnormality feature coefficient of the target display screen with a preset image abnormality feature coefficient, filter out image abnormality data, and control the image abnormality data by using a display screen image abnormality control coefficient.

[0013] The display screen detection quality analysis module is configured to analyze a quality evaluation index of the target display screen based on the performance parameter evaluation coefficient and the image abnormality feature coefficient of the target display screen.

[0014] The display screen detection result display module is configured to display the display screen detection result in the form of a report on a mobile device of a management personnel, and store the detection data in a database.

[0015] Preferably, the display screen image preprocessing module is executed in the following manner:

[0016] The preprocessed image is marked as a display screen image to be detected, and the display screen image to be detected includes n frames of images, which are sequentially numbered as 1, 2,..., i,..., n, wherein i is the number of each frame of the display screen image to be detected.

[0017] Preferably, the display screen image feature extraction module is executed in the following manner:

[0018] The display screen feature map is extracted from the display screen image to be detected by using an image feature recognition algorithm based on deep learning, and the performance parameter features and the image abnormal parameter features of the display screen feature map are obtained.

[0019] The image performance parameter features include brightness features, contrast features, and color gamut features of each frame of the display screen image to be detected.

[0020] The image abnormal parameter features include: bad point features, bright point features, and scratch features of each frame of the to-be-detected display screen image.

[0021] Preferably, the display screen performance parameter detection module is executed in the following manner:

[0022] The luminance value based on the luminance features of each frame of the to-be-detected display screen image Br i The luminance uniformity of each frame of the to-be-detected display screen image is analyzed, specifically: each frame of the to-be-detected display screen image is divided into Q regular sub-regions, Q is the total number of sub-regions, and the luminance uniformity of the i-th frame of the to-be-detected display screen image is calculated by the formula , wherein represents the average luminance of the k-th sub-region corresponding to the i-th frame of the to-be-detected display screen image, represents the average luminance of the i-th frame of the to-be-detected display screen image, i is the number of each frame of the to-be-detected display screen image, i = 1, 2,..., n, and k is the number of each sub-region, k = 1, 2,..., Q;

[0023] The average luminance of each frame of the to-be-detected display screen image is analyzed The contrast index of each frame of the to-be-detected display screen image is analyzed, specifically: each frame of the to-be-detected display screen image is subjected to gray scale processing to obtain each frame of the to-be-detected display screen gray scale image, and the standard deviation of the gray scale value of each frame of the to-be-detected display screen gray scale image is obtained by the formula CI i , represents the standard deviation of the gray scale value of the i-th frame of the to-be-detected display screen gray scale image;

[0024] Based on the color gamut features of each frame of the to-be-detected display screen image, the color gamut coverage rate of each frame of the to-be-detected display screen image is analyzed, specifically: the area of the display screen color gamut in the chromaticity diagram in each frame of the to-be-detected display screen image is obtained A i , and the area of the standard color gamut is obtained , to calculate the color gamut coverage rate of the i-th frame of the to-be-detected display screen image Cgc i , A i represents the area of the display screen color gamut in the chromaticity diagram in the i-th frame of the to-be-detected display screen image;

[0025] The luminance uniformity, contrast index, and color gamut coverage rate of each frame of the to-be-detected display screen image are read, the display screen performance parameters are analyzed, the performance parameter evaluation coefficient of the target display screen is obtained, and the calculation formula is specifically as follows: ​​​

[0026] wherein, PEC represents a performance parameter evaluation coefficient of the target display screen, represents a preset maximum value of the contrast index, Gcd i represents a color gamut coverage deviation of the i-th frame of the display screen image to be detected, , represents a preset standard color gamut coverage, represents an exponential function.

[0027] Preferably, the display screen image anomaly detection module is executed in the following specific manner:

[0028] Based on the bad point features of each frame of the display screen image to be detected, the bad point uniformity index of each frame of the display screen image to be detected is analyzed, specifically: a target detection model recognition algorithm based on deep learning is used to recognize each frame of the display screen image to be detected, and the bad point coordinates of each frame of the display screen image to be detected are obtained , the bad point uniformity index of the i-th frame of the display screen image to be detected is calculated by the formula UI i , represents the bad point horizontal coordinate variance of the i-th frame of the display screen image to be detected, represents the bad point vertical coordinate variance of the i-th frame of the display screen image to be detected, represents the width of the i-th frame of the display screen image to be detected, represents the height of the i-th frame of the display screen image to be detected;

[0029] Based on the scratch features of each frame of the display screen image to be detected, the scratch rate of each frame of the display screen image to be detected is analyzed, specifically: the edge detection algorithm is used to import the display screen image to be detected, and the scratch edge line in the display screen image to be detected is recognized, the threshold segmentation technology is used to convert the display screen image to be detected into a binary image, the scratch area is white and the background is black, and the number of pixels in the scratch area of each frame of the display screen image to be detected is obtained by counting Spc i and the number of pixels in the display screen area of each frame of the display screen image to be detected Dpc i is substituted into the formula , the scratch rate of the i-th frame of the display screen image to be detected is obtained Sr i ;

[0030] The bad point uniformity index and the scratch rate of each frame of the display screen image to be detected are read, and the image anomaly feature coefficient of the target display screen is calculated, and the calculation formula is specifically as follows:

[0031] ​ wherein, ACC represents the image abnormality feature coefficient of the target display screen, Db i represents the highlight density of the i-th frame of the display screen image to be detected.

[0032] Preferably, the highlight density of the i-th frame of the display screen image to be detected is obtained in the following manner:

[0033] Each frame of the display screen image to be detected is obtained, and the pixel value range of the image is wherein 255 represents the brightest pixel value;

[0034] Each frame of the display screen image to be detected is subjected to grayscale processing to obtain each frame of the display screen grayscale image to be detected, and all pixels of the grayscale image are traversed to count the number of pixels with a brightness value greater than or equal to a brightness threshold T in each frame of the display screen grayscale image to be detected. Nb i The highlight density of the i-th frame of the display screen image to be detected is calculated by the formula Db i , Nb i represents the number of highlight pixels of the i-th frame of the display screen image to be detected, represents the width of the i-th frame of the display screen image to be detected, represents the height of the i-th frame of the display screen image to be detected, wherein the brightness threshold T is set to 200.

[0035] Preferably, the display screen image abnormality control module is executed in the following manner:

[0036] The image abnormality feature coefficient of the target display screen is read ACC The data with the image abnormality feature coefficient greater than the preset image abnormality feature coefficient is screened out and marked as image abnormality data by comparing the image abnormality feature coefficient of the target display screen with the preset image abnormality feature coefficient, and the image abnormality data is controlled by the display screen image abnormality control coefficient;

[0037] wherein the calculation formula of the display screen image abnormality control coefficient is specifically: wherein, represents the display screen image abnormality control coefficient, represents the preset image abnormality feature coefficient.

[0038] Preferably, the display screen detection quality analysis module is executed in the following manner:

[0039] The performance parameter evaluation coefficient of the target display screen is obtained PEC and the image abnormality feature coefficient of the target display screen ACC ​The quality evaluation index of the target display screen is compared with a preset quality evaluation index threshold value, if the quality evaluation index of the target display screen is greater than or equal to the preset quality evaluation index threshold value, it is judged that the detection quality of the target display screen is normal, otherwise, it is judged that the detection quality of the target display screen is abnormal, and the results of the normal and abnormal detection quality are marked as the detection result of the target display screen. The calculation formula is: ;

[0040] The quality evaluation index of the target display screen is compared with a preset quality evaluation index threshold value, if the quality evaluation index of the target display screen is greater than or equal to the preset quality evaluation index threshold value, it is judged that the detection quality of the target display screen is normal, otherwise, it is judged that the detection quality of the target display screen is abnormal, and the results of the normal and abnormal detection quality are marked as the detection result of the target display screen.

[0041] To achieve the above object, the present application provides the following technical scheme: a display screen multi-parameter detection method, implementing the above-mentioned display screen multi-parameter detection system, comprising the following steps:

[0042] S1: collecting display screen images: using a high-resolution image acquisition device to collect images of a target display screen, and marking them as display screen images to be processed;

[0043] S2: display screen image preprocessing: preprocessing the display screen images to be processed through an image enhancement and filtering algorithm preprocessing method, and marking the preprocessed images as display screen images to be detected;

[0044] S3: display screen image feature extraction: performing image feature extraction on the display screen images to be detected, the image features including image performance parameter features and image abnormal parameter features;

[0045] S4: display screen performance parameter detection analysis: detecting and analyzing display screen performance parameters based on the image performance parameter features, to obtain a performance parameter evaluation coefficient of the target display screen;

[0046] S5: display screen image abnormality detection analysis: detecting and analyzing display screen image abnormalities based on the image abnormal parameter features, to obtain an image abnormality feature coefficient of the target display screen;

[0047] S6: display screen image abnormality control: comparing the image abnormality feature coefficient of the target display screen with a preset image abnormality feature coefficient, screening out image abnormality data, and controlling the image abnormality data through a display screen image abnormality control coefficient;

[0048] S7: display screen detection quality analysis: analyzing a quality evaluation index of the target display screen according to the performance parameter evaluation coefficient and the image abnormality feature coefficient of the target display screen;

[0049] S8: display screen detection result display: displaying the display screen detection result in the form of a report on a mobile device of a management personnel, and storing the detection data in a database.

[0050] The technical effects and advantages of the present application are as follows:

[0051] 1、The present application first collects the display screen image through high-resolution equipment, and enhances the image quality through preprocessing; then, the image features are extracted, the performance parameters and image abnormalities of the display screen are detected respectively, and the abnormal data are screened out for control; finally, the display screen quality is analyzed by comprehensively combining the performance parameters and abnormal feature coefficients, the detection results are displayed in the form of a report, and the data are stored, so as to facilitate the management personnel to monitor and evaluate the display screen state; by introducing the recognition algorithm of deep learning and the image processing technology, the present application not only improves the detection precision and efficiency, but also realizes the automation and intelligentization of detection, and provides strong support for display screen production and management.

[0052] 2、The present application realizes the comprehensive automation and intelligentization of display screen detection by integrating multiple modules such as high-resolution image acquisition, preprocessing, feature extraction, performance and abnormality detection, abnormality control and quality detection analysis; can accurately capture the details of the display screen image, efficiently extract the key features, and comprehensively evaluate the performance parameters and image abnormalities of the display screen, so as to provide a comprehensive and objective quality evaluation report; this innovation not only significantly improves the accuracy and efficiency of detection, reduces the manual error, but also provides strong data support for the subsequent maintenance, optimization and quality improvement of the display screen, greatly improves the user experience and satisfaction. BRIEF DESCRIPTION OF DRAWINGS

[0053] The present application will be further described by using the accompanying drawings, but the embodiments in the drawings do not constitute any limitation on the present application. For ordinary skilled persons in the art, other drawings can be obtained without creative labor on the basis of the following drawings.

[0054] Figure 1 It is a structural schematic diagram of a display screen multi-parameter detection system of the present application.

[0055] Figure 2 It is a flowchart of a display screen multi-parameter detection method of the present application. DETAILED DESCRIPTION

[0056] The technical solutions in the embodiments of the present application will be described clearly and completely by combining the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary skilled persons in the art without creative labor are within the scope of protection of the present application.

[0057] Embodiment 1

[0058] Please refer to Figure 1As shown, the present application provides a display screen multi-parameter detection system, comprising: a display screen image acquisition module, a display screen image preprocessing module, a display screen image feature extraction module, a display screen performance parameter detection module, a display screen image anomaly detection module, a display screen image anomaly control module, a display screen detection quality analysis module, and a display screen detection result display module.

[0059] The display screen image acquisition module: uses a high-resolution image acquisition device to acquire the image of the target display screen and marks it as a display screen image to be processed.

[0060] The display screen image preprocessing module: used for preprocessing the display screen image to be processed through image enhancement and filtering algorithm preprocessing, and marking the preprocessed image as a display screen image to be detected.

[0061] In this embodiment, it needs to be specifically explained that the execution mode of the display screen image preprocessing module is as follows:

[0062] The preprocessed image is marked as a display screen image to be detected, which includes n frames of images, and is sequentially numbered as 1, 2,..., i,..., n, wherein i is the number of each frame of display screen image to be detected.

[0063] It needs to be specifically explained that the display screen image preprocessing module is equipped with a high-performance computer as an image processing core to preprocess the image, and is equipped with a professional image acquisition card to ensure fast and stable image transmission.

[0064] The display screen image feature extraction module: used for image feature extraction of the display screen image to be detected, the image features include image performance parameter features and image anomaly parameter features.

[0065] In this embodiment, it needs to be specifically explained that the execution mode of the display screen image feature extraction module is as follows:

[0066] Using a deep learning-based image feature recognition algorithm to extract a display screen feature map from the display screen image to be detected, and obtaining performance parameter features and image anomaly parameter features of the display screen feature map.

[0067] The image performance parameter features include: brightness features, contrast features, and color gamut features of each frame of display screen image to be detected.

[0068] The image anomaly parameter features include: bad point features, bright point features, and scratch features of each frame of display screen image to be detected.

[0069] In this embodiment, it should be specifically noted that the image feature recognition algorithm based on deep learning can be found in the following references: Modern Machine Learning: Image Feature Extraction Based on Deep Learning, Feature Extraction Based on Deep Learning and Its Application in Image Retrieval, Research on Image Feature Extraction and Classification Algorithm Based on Deep Learning for the Great Wall, and A Review of the Application of Deep Learning in the Field of Image Processing.

[0070] Display screen performance parameter detection module: Detects and analyzes display screen performance parameters based on image performance parameter features to obtain the performance parameter evaluation coefficients of the target display screen;

[0071] In this embodiment, it should be specifically explained that the execution method of the display screen performance parameter detection module is as follows:

[0072] Brightness values ​​based on the brightness characteristics of each frame of the display screen image to be detected Br i The brightness uniformity of each frame of the display screen image to be tested is analyzed. Specifically, each frame of the display screen image to be tested is divided into Q regular sub-regions, where Q is the total number of sub-regions, using the formula... The brightness uniformity of the i-th frame of the display screen image to be detected is calculated. ,in, This represents the average brightness of the k-th sub-region corresponding to the i-th frame of the display screen image to be detected. The value represents the average brightness of the i-th frame of the display screen to be detected, where i is the number of each frame of the display screen to be detected, i=1,2,...n, and k is the number of each sub-region, k=1,2,...Q;

[0073] Based on the average brightness of each frame of the display screen image to be detected The contrast index of each frame of the display screen image to be tested is analyzed. Specifically, each frame of the display screen image to be tested is processed into grayscale to obtain grayscale images of each frame of the display screen to be tested. The standard deviation of the grayscale values ​​of each frame of the grayscale images of the display screen to be tested is obtained by formula. The contrast index of the i-th frame of the display screen to be detected is calculated. CI i , represents the standard deviation of the grayscale values ​​of the i-th frame of the grayscale image of the display screen to be detected;

[0074] Based on the color gamut characteristics of each frame of the display screen image to be detected, the color gamut coverage of each frame of the display screen image to be detected is analyzed. Specifically, the area of ​​the display screen color gamut in the chromaticity map of each frame of the display screen image to be detected is obtained. A i At the same time, obtain the area of ​​the standard color gamut. ,Depend on The color gamut coverage of the i-th frame of the display screen to be detected is calculated. Cgci A i represents the area of the color gamut of the display screen in the chromaticity diagram in the i-th frame of the display screen image to be detected;

[0075] It needs to be specifically pointed out that the chromaticity diagram is a two-dimensional chart for representing color characteristics, focusing on the hue and saturation of color by removing the brightness information.

[0076] The brightness uniformity, contrast index, and color gamut coverage of each frame of the display screen image to be detected are read, the performance parameter of the display screen is analyzed, the performance parameter evaluation coefficient of the target display screen is obtained, and the calculation formula is specifically as follows:

[0077] wherein, PEC represents the performance parameter evaluation coefficient of the target display screen, represents the preset maximum value of the contrast index, Gcd i represents the color gamut coverage deviation of the i-th frame of the display screen image to be detected, represents the preset standard color gamut coverage, represents the exponential function.

[0078] It needs to be specifically pointed out that in the formula, the greater the brightness uniformity, the greater the contrast index, and the smaller the color gamut coverage deviation of each frame of the display screen image to be detected, the greater the performance parameter evaluation coefficient of the target display screen, indicating that the performance of the target display screen is better; and the brightness uniformity, contrast index, and color gamut coverage deviation will not affect each other.

[0079] The display screen image abnormality detection module: based on the image abnormality parameter characteristics, the image abnormality of the display screen image is detected and analyzed, and the image abnormality characteristic coefficient of the target display screen is obtained;

[0080] In this embodiment, it needs to be specifically pointed out that the execution mode of the display screen image abnormality detection module is specifically as follows:

[0081] Based on the bad point characteristics of each frame of the display screen image to be detected, the bad point uniformity index of each frame of the display screen image to be detected is analyzed, which is specifically: based on the target detection model recognition algorithm of deep learning, each frame of the display screen image to be detected is recognized, and the bad point coordinates of each frame of the display screen image to be detected are obtained , the bad point uniformity index of the i-th frame of the display screen image to be detected is calculated UI i represents the bad point horizontal coordinate variance of the i-th frame of the display screen image to be detected, represents the bad point vertical coordinate variance of the i-th frame of the display screen image to be detected,​​​​ represents the width of the i-th frame of the display screen image to be detected, represents the height of the i-th frame of the display screen image to be detected.

[0082] It should be particularly pointed out that in the formula, the bad point uniformity index of each frame of the display screen image to be detected UI i , the value range is between 0 and 1, when UI i =1 indicates that the bad points are completely uniformly distributed, when UI i =0 indicates that the bad points are completely concentrated, wherein the larger the variance, the more dispersed the bad point distribution; the smaller the variance, the more concentrated the bad points.

[0083] In this embodiment, it should be particularly pointed out that the target detection model recognition algorithm based on deep learning can refer to the literature: Research on Image Target Detection Algorithm Based on YOLO Deep Learning Model, Smart Phone Panel Surface Defect Detection Method Based on YOLO V5 Model.

[0084] Based on the scratch features of each frame of the display screen image to be detected, the scratch rate of each frame of the display screen image to be detected is analyzed, specifically: the edge detection algorithm is introduced into each frame of the display screen image to be detected, and the scratch edge line in each frame of the display screen image to be detected is identified, the threshold segmentation technology is used to convert each frame of the display screen image to be detected into a binary image, the scratch area is white, and the background is black. Statistics are made, and the pixel number of the scratch area in each frame of the display screen image to be detected Spc i and the pixel number of the display screen area in each frame of the display screen image to be detected Dpc i is substituted into the formula , and the scratch rate of the i-th frame of the display screen image to be detected Sr i is obtained.

[0085] The bad point uniformity index and the scratch rate of each frame of the display screen image to be detected are read, and the image abnormal feature coefficient of the target display screen is calculated, and the calculation formula is specifically as follows:

[0086] , wherein, ACC represents the image abnormal feature coefficient of the target display screen, Db i represents the i-th frame of the display screen image to be detected.

[0087] It needs to be specifically pointed out that in the formula, the greater the bad point uniformity index of each frame of the to-be-detected display screen image, the smaller the scratch rate and the smaller the bright spot density, the smaller the image abnormal feature coefficient of the target display screen, indicating that the image quality of the target display screen is better; and the bad point uniformity index, the scratch rate and the bright spot density will not affect each other.

[0088] In this embodiment, it needs to be specifically pointed out that the acquisition method of the bright spot density of the i-th frame of the to-be-detected display screen image is specifically as follows:

[0089] Each frame of the to-be-detected display screen image is acquired, and the pixel value range of the image is , wherein 255 represents the brightest pixel value;

[0090] Each frame of the to-be-detected display screen image is subjected to gray scale processing to obtain each frame of the to-be-detected display screen gray scale image, all pixels of the gray scale image are traversed, and the number of pixels with a brightness value greater than or equal to a brightness threshold T in each frame of the to-be-detected display screen gray scale image is counted Nb i , the bright spot density of the i-th frame of the to-be-detected display screen image is calculated Db i , Nb i , wherein the number of bright spot pixels of the i-th frame of the to-be-detected display screen image is represented by , the width of the i-th frame of the to-be-detected display screen image is represented by , and the height of the i-th frame of the to-be-detected display screen image is represented by, wherein the brightness threshold T is set to 200.

[0091] The display screen image abnormality control module: based on the comparison between the image abnormal feature coefficient of the target display screen and the preset image abnormal feature coefficient, the image abnormal data is screened out, and the image abnormal data is controlled through the display screen image abnormality control coefficient;

[0092] In this embodiment, it needs to be specifically pointed out that the execution method of the display screen image abnormality control module is specifically as follows:

[0093] The image abnormal feature coefficient of the target display screen is read ACC , compared with the preset image abnormal feature coefficient, the data whose image abnormal feature coefficient is greater than the preset image abnormal feature coefficient is screened out, and is marked as image abnormal data, and the image abnormal data is controlled through the display screen image abnormality control coefficient;

[0094] , the calculation formula of the display screen image abnormality control coefficient is specifically: , wherein represents the display screen image abnormality control coefficient, represents the preset image abnormal feature coefficient.​

[0095] Need to be specific, in the formula, when , ; when the image abnormal feature coefficient of the target display screen and the difference between the preset image abnormal feature coefficient increases, The denominator increases, The value will decrease, indicating that the image abnormality degree exceeds the preset more, the control coefficient is smaller, and the control strength needs to be increased; when the image abnormal feature coefficient of the target display screen and the difference between the preset image abnormal feature coefficient decreases, The value will tend to 1, indicating that the control strength can be appropriately relaxed.

[0096] Display screen detection quality analysis module: used for analyzing the quality evaluation index of the target display screen according to the performance parameter evaluation coefficient and the image abnormal feature coefficient of the target display screen;

[0097] In this embodiment, it needs to be specifically explained that the execution mode of the display screen detection quality analysis module is as follows:

[0098] Obtain the performance parameter evaluation coefficient of the target display screen PEC And the image abnormal feature coefficient of the target display screen ACC , analyze the quality evaluation index of the target display screen , the calculation formula is: ;

[0099] Compare the quality evaluation index of the target display screen with the preset quality evaluation index threshold value, if the quality evaluation index of the target display screen is greater than or equal to the preset quality evaluation index threshold value, it is judged that the detection quality of the target display screen is normal, otherwise, it is judged that the detection quality of the target display screen is abnormal, and the results of normal and abnormal detection quality are marked as the detection result of the target display screen.

[0100] Need to be specific, in the formula, the performance parameter evaluation coefficient of the target display screen PEC The greater 、 The image abnormal feature coefficient ACC The greater, the quality evaluation index of the target display screen The better, the quality detection result of the target display screen is better;

[0101] In the formula, the performance parameter evaluation coefficient of the target display screen PEC, The image abnormal feature coefficient of the target display screen ACC Will not affect each other.

[0102] Display screen detection result display module: used for displaying the display screen detection result in the form of a report on the mobile device of the management personnel, and storing the detection data to the database.

[0103] Embodiment 2

[0104] Referring to Figure 2 As shown in the figure, the present application provides a display screen multi-parameter detection method, comprising the following steps: S1: collecting display screen images, S2: display screen image preprocessing, S3: display screen image feature extraction, S4: display screen performance parameter detection analysis, S5: display screen image anomaly detection analysis, S6: display screen image anomaly control, S7: display screen detection quality analysis, and S8: display screen detection result display.

[0105] S1: Collecting display screen images: using a high-resolution image acquisition device to collect the images of the target display screen, and marking them as display screen images to be processed;

[0106] S2: Display screen image preprocessing: preprocessing the display screen images to be processed through image enhancement and filtering algorithm preprocessing methods, and marking the preprocessed images as display screen images to be detected;

[0107] S3: Display screen image feature extraction: performing image feature extraction on the display screen images to be detected, wherein the image features include image performance parameter features and image anomaly parameter features;

[0108] S4: Display screen performance parameter detection analysis: detecting and analyzing the display screen performance parameters based on the image performance parameter features, to obtain the performance parameter evaluation coefficient of the target display screen;

[0109] S5: Display screen image anomaly detection analysis: detecting and analyzing the display screen image anomalies based on the image anomaly parameter features, to obtain the image anomaly feature coefficient of the target display screen;

[0110] S6: Display screen image anomaly control: comparing the image anomaly feature coefficient of the target display screen with the preset image anomaly feature coefficient, screening out image anomaly data, and controlling the image anomaly data through a display screen image anomaly control coefficient;

[0111] S7: Display screen detection quality analysis: analyzing the quality evaluation index of the target display screen according to the performance parameter evaluation coefficient and the image anomaly feature coefficient of the target display screen;

[0112] S8: Display screen detection result display: displaying the display screen detection results in the form of a report on the mobile device of the management personnel, and storing the detection data in the database.

[0113] Finally, the above-mentioned is only the preferred embodiment of the present application, and is not used to limit the present application, any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0114] The above description is only specific embodiments of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A multi-parameter detection system for a display screen, characterized in that, Comprise: Display screen image acquisition module: use high-resolution image acquisition equipment to collect the image of the target display screen, and mark it as a display screen image to be processed; Display screen image preprocessing module: used for preprocessing the display screen image to be processed through image enhancement and filtering algorithm, and marking the preprocessed image as a display screen image to be detected; Display screen image feature extraction module: used for image feature extraction of the display screen image to be detected, the image feature includes image performance parameter feature and image abnormal parameter feature; Display screen performance parameter detection module: based on the image performance parameter feature, the display screen performance parameter is detected and analyzed, and the performance parameter evaluation coefficient of the target display screen is obtained; The brightness value based on the brightness characteristic of each frame of the display screen image to be detected Br i The brightness uniformity of each frame of the display screen image to be detected is analyzed, specifically: each frame of the display screen image to be detected is divided into Q regular sub-regions, Q is the total number of sub-regions, and the brightness uniformity of the i-th frame of the display screen image to be detected is calculated by the formula Wherein, Y (i, k) represents the average brightness of the k-th sub-region corresponding to the i-th frame of the display screen image to be detected, Y (i, k) represents the average brightness of the k-th sub-region corresponding to the i-th frame of the display screen image to be detected, Y (i) represents the average brightness of the i-th frame of the display screen image to be detected, i is the number of each frame of the display screen image to be detected, i = 1, 2,..., n, k is the number of each sub-region, k = 1, 2,..., Q;​ Based on average brightness of each frame of display screen image to be detected , analyze the contrast index of each frame of display screen image to be detected, specifically: perform gray processing on each frame of display screen image to be detected to obtain each frame of display screen gray image to be detected, obtain the standard deviation of the gray value of each frame of display screen gray image to be detected, and the contrast index of the i-th frame of display screen image to be detected is calculated by the formula , analyze the contrast index of each frame of display screen image to be detected, specifically: perform gray processing on each frame of display screen image to be detected to obtain each frame of display screen gray image to be detected, obtain the standard deviation of the gray value of each frame of display screen gray image to be detected, and the contrast index of the i-th frame of display screen image to be detected is calculated by the formula CI i , , analyze the contrast index of each frame of display screen image to be detected, specifically: perform gray processing on each frame of display screen image to be detected to obtain each frame of display screen gray image to be detected, obtain the standard deviation of the gray value of each frame of display screen gray image to be detected, and the contrast index of the i-th frame of display screen image to be detected is calculated by the formula Based on the color gamut characteristics of each frame of the to-be-detected display screen image, the color gamut coverage of each frame of the to-be-detected display screen image is analyzed, specifically: the area of the display screen color gamut in the chromaticity diagram in each frame of the to-be-detected display screen image is obtained A i Meanwhile, the area of the standard color gamut is obtained The color gamut coverage of the i-th frame of the to-be-detected display screen image is calculated Cgc i , A i The area of the display screen color gamut in the chromaticity diagram in the i-th frame of the to-be-detected display screen image is represented​ Read the brightness uniformity, contrast index and color gamut coverage of each frame of display screen image to be detected, analyze the display screen performance parameter, and obtain the performance parameter evaluation coefficient of the target display screen, the calculation formula is as follows: wherein, PEC represents a performance parameter evaluation coefficient of the target display screen, represents a preset maximum value of the contrast index, Gcd i represents a color gamut coverage deviation of the i-th frame of the display screen image to be detected, , represents a preset standard color gamut coverage, represents an exponential function; Display screen image abnormality detection module: based on the image abnormal parameter feature, the display screen image abnormality is detected and analyzed, and the image abnormal feature coefficient of the target display screen is obtained; Based on the bad point features of each frame of the to-be-detected display screen image, the bad point uniformity index of each frame of the to-be-detected display screen image is analyzed, specifically: a target detection model recognition algorithm based on deep learning is used to recognize each frame of the to-be-detected display screen image, and the bad point coordinates of each frame of the to-be-detected display screen image are obtained The bad point uniformity index of the i-th frame of the to-be-detected display screen image is calculated by the formula UI i , The bad point horizontal coordinate variance of the i-th frame of the to-be-detected display screen image is represented by The bad point vertical coordinate variance of the i-th frame of the to-be-detected display screen image is represented by The width of the i-th frame of the to-be-detected display screen image is represented by The height of the i-th frame of the to-be-detected display screen image is represented by​ Based on the scratch characteristics of each frame of the to-be-detected display screen image, the scratch rate of each frame of the to-be-detected display screen image is analyzed, specifically: the edge detection algorithm is used to import each frame of the to-be-detected display screen image, and the scratch edge line in each frame of the to-be-detected display screen image is recognized; the threshold segmentation technology is used to convert each frame of the to-be-detected display screen image into a binary image, the scratch area is white, and the background is black; and the scratch area in each frame of the to-be-detected display screen image is counted to obtain the pixel number of the scratch area in each frame of the to-be-detected display screen image Spc i and the pixel number of the display screen area in each frame of the to-be-detected display screen image Dpc i , which is substituted into the formula to obtain the scratch rate of the i-th frame of the to-be-detected display screen image Sr i ; Read the bad point uniformity index and scratch rate of each frame of display screen image to be detected, calculate the image abnormal feature coefficient of the target display screen, and the calculation formula is as follows: wherein, ACC represents the image abnormality feature coefficient of the target display screen, Db i represents the highlight density of the i-th frame of the display screen image to be detected; Display screen image abnormality control module: based on the comparison between the image abnormal feature coefficient of the target display screen and the preset image abnormal feature coefficient, the image abnormal data is screened out, and the image abnormal data is controlled through the display screen image abnormality control coefficient; Reading image abnormal feature coefficient of target display screen ACC Comparing with the preset image abnormal feature coefficient, screening out the data of the image abnormal feature coefficient of the target display screen greater than the preset image abnormal feature coefficient, marking it as image abnormal data, and controlling the image abnormal data through the display screen image abnormal control coefficient. The calculation formula of the display screen image abnormality control coefficient is specifically as follows: wherein, represents the display screen image abnormality control coefficient, represents a preset image abnormality feature coefficient; Display screen detection quality analysis module: used for analyzing the quality evaluation index of the target display screen according to the performance parameter evaluation coefficient and the image abnormal feature coefficient of the target display screen; Display screen detection result display module: used for displaying the display screen detection result in the form of report on the mobile device of the management personnel, and storing the detection data to the database.

2. The multi-parameter detection system of claim 1, wherein: The execution mode of the display screen image preprocessing module is as follows: Mark the preprocessed image as a display screen image to be detected, which includes n frames of images, which are numbered in turn as 1, 2,..., i,..., n, wherein i is the number of each frame of display screen image to be detected.

3. The multi-parameter detection system of claim 1, wherein: The execution mode of the display screen image feature extraction module is as follows: Use deep learning based image feature recognition algorithm to extract display screen feature map from the display screen image to be detected, and obtain the performance parameter feature and image abnormal parameter feature of the display screen feature map; The image performance parameter feature includes: brightness feature, contrast feature and color gamut feature of each frame of display screen image to be detected; The image abnormal parameter feature includes: bad point feature, bright point feature and scratch feature of each frame of display screen image to be detected.

4. The multi-parameter detection system of claim 1, wherein: The acquisition mode of the bright point density of the i-th frame of display screen image to be detected is as follows: Acquire each frame of the image of the display screen to be detected, the pixel value range of the image is wherein 255 represents the brightest pixel value; The frames of the to-be-detected display screen images are subjected to grayscale processing to obtain frames of to-be-detected display screen grayscale images, all pixels of the grayscale images are traversed, and the number of pixels with a luminance value greater than or equal to a luminance threshold T in the frames of to-be-detected display screen grayscale images is counted Nb i The luminance threshold T is 200. The luminance threshold T is 200. Db i , Nb i The luminance threshold T is 200. The luminance threshold T is 200. The luminance threshold T is 200.

5. The multi-parameter detection system of claim 1, wherein: The execution mode of the display screen detection quality analysis module is as follows: Obtaining a performance parameter evaluation coefficient of a target display screen PEC and an image abnormality feature coefficient of the target display screen ACC , and analyzing to obtain a quality evaluation index of the target display screen , and the calculation formula is: ; The quality evaluation index of the target display screen is compared with a preset quality evaluation index threshold. If the quality evaluation index of the target display screen is greater than or equal to the preset quality evaluation index threshold, it is determined that the detection quality of the target display screen is normal, otherwise, it is determined that the detection quality of the target display screen is abnormal, and the results of the normal and abnormal detection quality are marked as the detection result of the target display screen.

6. A method for detecting multiple parameters of a display screen using a system for detecting multiple parameters of a display screen according to any one of claims 1-5, characterized in that, The method comprises the following steps: S1: Collecting a display screen image: using a high-resolution image collection device, collecting an image of a target display screen, and marking it as a display screen image to be processed; S2: Display screen image preprocessing: preprocessing the display screen image to be processed through an image enhancement and filtering algorithm preprocessing method, and marking the preprocessed image as a display screen image to be detected; S3: Display screen image feature extraction: performing image feature extraction on the display screen image to be detected, wherein the image features include image performance parameter features and image abnormal parameter features; S4: Display screen performance parameter detection analysis: detecting and analyzing the display screen performance parameters based on the image performance parameter features to obtain a performance parameter evaluation coefficient of the target display screen; The brightness value based on the brightness characteristic of each frame of the display screen image to be detected Br i The brightness uniformity of each frame of the display screen image to be detected is analyzed, specifically: each frame of the display screen image to be detected is divided into Q regular sub-regions, Q is the total number of sub-regions, and the brightness uniformity of the i-th frame of the display screen image to be detected is calculated by the formula Wherein, represents the average brightness of the i-th frame of the display screen image to be detected corresponding to the k-th sub-region, represents the average brightness of the i-th frame of the display screen image to be detected, i is the number of each frame of the display screen image to be detected, i=1, 2,..., n, k is the number of each sub-region, k=1, 2,..., Q.​ Based on average brightness of each frame of display screen image to be detected , a contrast index of each frame of display screen image to be detected is analyzed, specifically: each frame of display screen image to be detected is subjected to gray scale processing to obtain each frame of display screen gray scale image, a standard deviation of gray scale values of each frame of display screen gray scale image is obtained, and the contrast index of the i-th frame of display screen image to be detected is calculated according to the formula , wherein, σi represents the standard deviation of the gray scale values of the i-th frame of display screen gray scale image. CI i , ​ Based on the color gamut characteristics of each frame of the to-be-detected display screen image, the color gamut coverage of each frame of the to-be-detected display screen image is analyzed, specifically: the area of the display screen color gamut in the chromaticity diagram in each frame of the to-be-detected display screen image is obtained A i Meanwhile, the area of the standard color gamut is obtained , The color gamut coverage of the i-th frame of the to-be-detected display screen image is calculated Cgc i , A i The area of the display screen color gamut in the chromaticity diagram in the i-th frame of the to-be-detected display screen image is represented Read the brightness uniformity, contrast index, and color gamut coverage of each frame of the display screen image to be detected, analyze the display screen performance parameters, and obtain the performance parameter evaluation coefficient of the target display screen. The calculation formula is as follows: wherein, PEC represents a performance parameter evaluation coefficient of the target display screen, represents a preset maximum value of the contrast index, Gcd i represents a color gamut coverage deviation of the i-th frame of the display screen image to be detected, , represents a preset standard color gamut coverage, represents an exponential function; S5: Display screen image abnormality detection analysis: detecting and analyzing the display screen image abnormalities based on the image abnormal parameter features to obtain an image abnormality feature coefficient of the target display screen; Based on the bad point features of each frame of the to-be-detected display screen image, the bad point uniformity index of each frame of the to-be-detected display screen image is analyzed, specifically: a target detection model recognition algorithm based on deep learning is used to recognize each frame of the to-be-detected display screen image, and the bad point coordinates of each frame of the to-be-detected display screen image are obtained The bad point uniformity index of the i-th frame of the to-be-detected display screen image is calculated by the formula UI i , The bad point horizontal coordinate variance of the i-th frame of the to-be-detected display screen image is represented by The bad point vertical coordinate variance of the i-th frame of the to-be-detected display screen image is represented by The width of the i-th frame of the to-be-detected display screen image is represented by The height of the i-th frame of the to-be-detected display screen image is represented by​ Based on the scratch characteristics of each frame of the to-be-detected display screen image, the scratch rate of each frame of the to-be-detected display screen image is analyzed, specifically: the edge detection algorithm is used to import each frame of the to-be-detected display screen image, and the scratch edge line in each frame of the to-be-detected display screen image is recognized; the threshold segmentation technology is used to convert each frame of the to-be-detected display screen image into a binary image, the scratch area is white, and the background is black; and the scratch area in each frame of the to-be-detected display screen image is counted to obtain the pixel number of the scratch area in each frame of the to-be-detected display screen image Spc i and the pixel number of the display screen area in each frame of the to-be-detected display screen image Dpc i , which is substituted into the formula to obtain the scratch rate of the i-th frame of the to-be-detected display screen image Sr i ; Read the bad point uniformity index and scratch rate of each frame of the display screen image to be detected, and calculate the image abnormality feature coefficient of the target display screen. The calculation formula is as follows: wherein, ACC represents the image abnormality feature coefficient of the target display screen, Db i represents the highlight density of the i-th frame of the display screen image to be detected; S6: Display screen image abnormality control: comparing the image abnormality feature coefficient of the target display screen with a preset image abnormality feature coefficient, screening out image abnormality data, and controlling the image abnormality data through a display screen image abnormality control coefficient; Reading image abnormal feature coefficient of target display screen ACC Comparing with the preset image abnormal feature coefficient, screening out the data of the image abnormal feature coefficient of the target display screen greater than the preset image abnormal feature coefficient, marking it as image abnormal data, and controlling the image abnormal data through the display screen image abnormal control coefficient. The calculation formula of the display screen image abnormality control coefficient is specifically as follows: wherein, represents the display screen image abnormality control coefficient, represents a preset image abnormality feature coefficient; S7: Display screen detection quality analysis: analyzing the quality evaluation index of the target display screen based on the performance parameter evaluation coefficient and the image abnormality feature coefficient; S8: Display screen detection result display: displaying the display screen detection result in the form of a report on the mobile device of the management personnel, and storing the detection data in the database.

Images