Display screen multi-parameter detection method and system

Abstract

The invention relates to the technical field of display screen detection, and particularly discloses a display screen multi-parameter detection method and 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. According to the method, display screen images are collected and preprocessed; the method comprises the following steps: extracting image features, analyzing to obtain a performance parameter evaluation coefficient and an image anomaly feature coefficient, controlling image anomaly data through a display screen image anomaly control coefficient, and finally analyzing to obtain a quality evaluation index of a target display screen. According to the invention, the detection precision and efficiency are improved, automation and intelligence of detection are realized, and powerful support is provided for display screen production and management.

Description

Technical Field

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

[0002] With the continuous development of display technologies, displays are increasingly widely used, from daily computer monitors, TV screens to the display screens of various mobile devices. The quality requirements for display screens are also increasing day by day. Any screen defect may affect the user experience, such as bright dots, dark dots, dead pixels, color deviation, uneven brightness, etc.

[0003] Currently, there are many deficiencies in traditional display screen detection methods: First, traditional display screen detection relies on manual observation. Detection personnel need to carefully check each screen one by one, which is slow and difficult to meet the high-efficiency detection requirements of large-scale display production. During peak production seasons or when the order volume is large, it is easy to cause production backlogs. Second, during manual detection, the visual acuity of detection personnel, fatigue during work, and individual experience differences will all affect the detection results, resulting in unstable detection results, such as missed detection of dead pixels and misjudgment of color deviation, affecting product quality control. In addition, traditional methods are difficult to comprehensively and accurately detect key performance parameters of the screen, such as brightness uniformity, color gamut accuracy, response time, etc., and cannot meet the requirements of the market for high-quality and diversified performance detection of displays, which is not conducive to enhancing the competitiveness of products 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 of the Invention

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

[0006] To achieve the above object, the present invention provides the following technical solution: A multi-parameter detection system for a display screen, 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 abnormality detection module, a display screen image abnormality 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 an image of the target display screen and marks it as an image of the display screen to be processed; The display screen image preprocessing module: is used to preprocess the image of the display screen to be processed through preprocessing methods of image enhancement and filtering algorithms, and marks the preprocessed image as an image of the display screen to be detected; Display screen image feature extraction module: used to extract image features from the display screen image to be detected, and the image features include image performance parameter features and image anomaly parameter features; Display screen performance parameter detection module: based on the image performance parameter features, detect and analyze the display screen performance parameters to obtain the performance parameter evaluation coefficient of the target display screen; Display screen image anomaly detection module: based on the image anomaly parameter features, detect and analyze the display screen image anomalies to obtain the image anomaly feature coefficient of the target display screen; Display screen image anomaly control module: based on the comparison between the image anomaly feature coefficient of the target display screen and the preset image anomaly feature coefficient, screen out the image anomaly data, and control the image anomaly data through the display screen image anomaly control coefficient; Display screen detection quality analysis module: used to analyze and obtain 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; Display screen detection result display module: used to display the display screen detection results in the form of a report on the mobile device of the management personnel, and store the detection data in the database.

[0008] Preferably, the execution method of the display screen image preprocessing module is specifically as follows: Mark the preprocessed image as the display screen image to be detected. The display screen image to be detected includes n frames of images, which are sequentially numbered 1, 2,... i,... n, where i is the number of each frame of the display screen image to be detected.

[0009] Preferably, the execution method of the display screen image feature extraction module is specifically as follows: Use an image feature recognition algorithm based on deep learning to extract the display screen feature map from the display screen image to be detected, and obtain the performance parameter features and image anomaly parameter features of the display screen feature map; The image performance parameter features include: the brightness feature, contrast feature, and color gamut feature of each frame of the display screen image to be detected; The image anomaly parameter features include: the dead pixel feature, bright spot feature, and scratch feature of each frame of the display screen image to be detected.

[0010] Preferably, the execution method of the display screen performance parameter detection module is specifically as follows: Based on the brightness value of the brightness feature of each frame of the display screen image to be detected Br i , analyze the brightness uniformity of each frame of the display screen image to be detected. Specifically: divide each frame of the display screen image to be detected into Q regular sub-regions, where Q is the total number of sub-regions. From the formula , calculate the brightness uniformity of the i-th frame of the display screen image to be detected , where represents the average brightness of the k-th sub-region corresponding to the i-th frame of the display screen image to be detected, 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, and k is the number of each sub-region, k = 1, 2,... Q; Based on the average brightness of each frame of the display screen image to be detected , analyze the contrast index of each frame of the display screen image to be detected. Specifically: perform gray-scale processing on each frame of the display screen image to be detected to obtain each frame of the gray-scale image of the display screen to be detected, and obtain the standard deviation of the gray-scale values of each frame of the gray-scale image of the display screen to be detected. From the formula , calculate the contrast index of the i-th frame of the display screen image to be detected CI i , represents the standard deviation of the gray-scale values of the i-th frame of the gray-scale image of the display screen to be detected; Based on the gamut characteristics of each frame of the display screen image to be detected, analyze the gamut coverage rate of each frame of the display screen image to be detected. Specifically: obtain the area of the display screen gamut in the chromaticity diagram of each frame of the display screen image to be detected A i , and at the same time obtain the area of the standard gamut , from , calculate the gamut coverage rate of the i-th frame of the display screen image to be detected Cgc i , A i represents the area of the display screen gamut in the chromaticity diagram of the i-th frame of the display screen image to be detected; Read the brightness uniformity, contrast index, and gamut coverage rate 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 specific calculation formula is as follows: , where PEC represents the performance parameter evaluation coefficient of the target display screen, represents the maximum value of the preset contrast index, Gcd i represents the gamut coverage rate deviation of the i-th frame of the display screen image to be detected, , represents the preset standard gamut coverage rate, represents the exponential function.

[0011] Preferably, the execution method of the display screen image abnormality detection module is specifically as follows: Based on the bad pixel features of each frame of the display screen image to be detected, analyze the bad pixel uniformity index of each frame of the display screen image to be detected. Specifically: Use the object detection model recognition algorithm based on deep learning to identify each frame of the display screen image to be detected, and obtain the bad pixel coordinates of each frame of the display screen image to be detected , and use the formula to calculate the bad pixel uniformity index of the i-th frame of the display screen image to be detected UI i , where represents the variance of the abscissa of the bad pixels in the i-th frame of the display screen image to be detected, represents the variance of the ordinate of the bad pixels in 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; Based on the scratch features of each frame of the display screen image to be detected, analyze the scratch rate of each frame of the display screen image to be detected. Specifically: Import each frame of the display screen image to be detected into the edge detection algorithm to identify the scratch edge lines in each frame of the display screen image to be detected. Use the threshold segmentation technology to convert each frame of the display screen image to be detected into a binary image, where the scratch area is white and the background is black, and perform statistics on it to obtain the number of pixels in the scratch area of each frame of the display screen image to be detected 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 , and substitute them into the formula to obtain the scratch rate of the i-th frame of the display screen image to be detected Sr i ; Read the bad pixel uniformity index and scratch rate of each frame of the display screen image to be detected, and calculate the image anomaly feature coefficient of the target display screen. The specific calculation formula is as follows: , where, ACC ACC represents the image anomaly feature coefficient of the target display screen, Db i Db represents the highlight density of the i-th frame of the display screen image to be detected.

[0012] Preferably, the method for obtaining the highlight density of the i-th frame of the display screen image to be detected is specifically as follows: Obtain each frame of the display screen image to be detected, and the pixel value range of the image is , where 255 represents the brightest pixel value; Perform gray-scale processing on each frame of the display screen image to be detected to obtain each frame of the display screen gray-scale image. Traverse all pixels of the gray-scale image and count the number of pixels in each frame of the display screen gray-scale image whose brightness value is greater than or equal to the brightness threshold TNb i , calculated from the formula to obtain the highlight density of the i-th frame of the display screen image to be detected Db i , Nb i represents the number of highlight pixels in 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, where the set brightness threshold T is 200.

[0013] Preferably, the execution mode of the display screen image abnormality control module is specifically as follows: Read the image abnormality feature coefficient of the target display screen ACC , compare it with the preset image abnormality feature coefficient, screen out the data where the image abnormality feature coefficient of the target display screen is greater than the preset image abnormality feature coefficient, and mark it as image abnormality data, and control the image abnormality data through the display screen image abnormality control coefficient; Among them, the calculation formula of the display screen image abnormality control coefficient is specifically: , where represents the display screen image abnormality control coefficient, represents the preset image abnormality feature coefficient.

[0014] Preferably, the execution mode of the display screen detection quality analysis module is specifically as follows: Obtain the performance parameter evaluation coefficient of the target display screen PEC and the image abnormality feature coefficient of the target display screen ACC , analyze to obtain the quality evaluation index of the target display screen , and the calculation formula is: ; Compare the quality evaluation index of the target display screen with the 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 detection results of normal and abnormal detection quality are respectively marked as the detection results of the target display screen.

[0015] To achieve the above object, the present invention provides the following technical solutions: A display screen multi-parameter detection method, implementing the above-mentioned display screen multi-parameter detection system, includes the following steps: S1: Collect the display screen image: Use a high-resolution image acquisition device to collect the image of the target display screen and mark it as the display screen image to be processed; S2: Preprocessing of display screen images: Preprocess the to-be-processed display screen images through preprocessing methods such as image enhancement and filtering algorithms, and mark the preprocessed images as to-be-detected display screen images; S3: Feature extraction of display screen images: Extract image features from the to-be-detected display screen images, where the image features include image performance parameter features and image anomaly parameter features; S4: Detection and analysis of display screen performance parameters: Detect and analyze the display screen performance parameters based on the image performance parameter features to obtain the performance parameter evaluation coefficient of the target display screen; S5: Detection and analysis of display screen image anomalies: Detect and analyze the display screen image anomalies based on the image anomaly parameter features to obtain the image anomaly feature coefficient of the target display screen; S6: Control of display screen image anomalies: Compare the image anomaly feature coefficient of the target display screen with the preset image anomaly feature coefficient, screen out the image anomaly data, and control the image anomaly data through the display screen image anomaly control coefficient; S7: Analysis of display screen detection quality: Analyze and obtain 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; S8: Display of display screen detection results: Display the display screen detection results in the form of a report on the mobile devices of the management personnel, and store the detection data in the database.

[0016] Technical effects and advantages of the present invention: 1. The present invention first collects display screen images through high-resolution devices and enhances the image quality through preprocessing; subsequently, extracts image features, detects the performance parameters and image anomalies of the display screen respectively, and screens out and controls the anomaly data accordingly; finally, analyzes the quality of the display screen by integrating the performance parameters and the anomaly feature coefficient, displays the detection results in the form of a report and stores the data, which is convenient for the management personnel to monitor and evaluate the status of the display screen; by introducing the recognition algorithm and image processing technology of deep learning, the present invention not only improves the detection accuracy and efficiency, but also realizes the automation and intelligence of detection, providing strong support for the production and management of display screens; 2. The present invention realizes the full automation and intelligence of display screen detection by integrating multiple modules such as high-resolution image acquisition, preprocessing, feature extraction, performance and anomaly detection, anomaly control, and quality detection and analysis; it can accurately capture the details of display screen images, efficiently extract key features, and comprehensively evaluate the performance parameters and image anomalies of the display screen, so as to provide a comprehensive and objective quality evaluation report; this innovation not only significantly improves the detection accuracy and efficiency, reduces human errors, but also provides strong data support for the subsequent maintenance, optimization, and quality improvement of the display screen, greatly enhancing the user experience and satisfaction. Description of the Drawings

[0017] The present invention will be further described with reference to the accompanying drawings. However, the embodiments in the drawings do not constitute any limitation to the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to the following drawings.

[0018] Figure 1 It is a schematic structural diagram of a multi-parameter detection system for a display screen according to the present invention.

[0019] Figure 2 It is a schematic flow diagram of a multi-parameter detection method for a display screen according to the present invention. Specific embodiments

[0020] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0021] Embodiment 1 Please refer to Figure 1 As shown, the present invention provides a multi-parameter detection system for a display screen, including: 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 abnormality detection module, a display screen image abnormality control module, a display screen detection quality analysis module, and a display screen detection result display module; The display screen image acquisition module: uses a high-resolution image acquisition device to acquire an image of the target display screen and marks it as an image of the display screen to be processed; The display screen image preprocessing module: is used to preprocess the image of the display screen to be processed through preprocessing methods such as image enhancement and filtering algorithms, and marks the preprocessed image as an image of the display screen to be detected; In this embodiment, it should be specifically noted that the execution manner of the display screen image preprocessing module is as follows: Mark the preprocessed image as an image of the display screen to be detected. The image of the display screen to be detected includes n frames of images, which are sequentially numbered 1, 2,... i,... n, where i is the number of each frame of the image of the display screen to be detected.

[0022] It should be specifically noted that the display screen image preprocessing module is equipped with a high-performance computer as the core for image processing to preprocess the image, and is equipped with a professional image acquisition card to ensure fast and stable transmission of the image.

[0023] Display screen image feature extraction module: used to extract image features from the display screen image to be detected, where the image features include image performance parameter features and image anomaly parameter features; In this embodiment, it should be specifically noted that the execution method of the display screen image feature extraction module is as follows: Use an image feature recognition algorithm based on deep learning to extract the display screen feature map from the display screen image to be detected, and obtain the performance parameter features and image anomaly parameter features of the display screen feature map; 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; The image anomaly parameter features include: dead pixel features, bright spot features, and scratch features of each frame of the display screen image to be detected.

[0024] In this embodiment, it should be specifically noted that the image feature recognition algorithm based on deep learning can refer to the following literature: Modern Machine Learning, Image Feature Extraction Based on Deep Learning, Feature Extraction Based on Deep Learning and Its Application in Image Retrieval, Research on the Feature Extraction and Classification Algorithm of the Great Wall Image Based on Deep Learning, and Review of the Application of Deep Learning in the Field of Image Processing.

[0025] Display screen performance parameter detection module: detect and analyze the display screen performance parameters based on the image performance parameter features to obtain the performance parameter evaluation coefficient of the target display screen; In this embodiment, it should be specifically noted that the execution method of the display screen performance parameter detection module is as follows: Based on the brightness value of the brightness feature of each frame of the display screen image to be detected Br i , analyze the brightness uniformity of each frame of the display screen image to be detected. Specifically: divide each frame of the display screen image to be detected into Q regular sub-regions, where Q is the total number of sub-regions. According to the formula , calculate the brightness uniformity of the i-th frame of the display screen image to be detected , where represents the average brightness of the k-th sub-region corresponding to the i-th frame of the display screen image to be detected, 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, and k is the number of each sub-region, k = 1, 2,... Q; Based on the average brightness of each frame of the display screen image to be detected , analyze the contrast index of each frame of the display screen image to be detected. Specifically: perform gray-scale processing on each frame of the display screen image to be detected to obtain the gray-scale image of each frame of the display screen image to be detected, and obtain the standard deviation of the gray-scale values of the gray-scale image of each frame of the display screen image to be detected. According to the formula , the contrast index of the i-th frame of the display screen image to be detected is calculated CI i , represents the standard deviation of the gray level values of the i-th frame of the display screen gray image to be detected; Based on the color gamut characteristics of each frame of the display screen image to be detected, analyze the color gamut coverage rate of each frame of the display screen image to be detected. Specifically: Obtain the area of the display screen color gamut in the chromaticity diagram of each frame of the display screen image to be detected A i , and at the same time obtain the area of the standard color gamut , from , the color gamut coverage rate of the i-th frame of the display screen image to be detected is calculated Cgc i , A i represents the area of the display screen color gamut in the chromaticity diagram of the i-th frame of the display screen image to be detected; It should be specifically noted that the chromaticity diagram is a two-dimensional chart used to represent color characteristics, which focuses on the hue and saturation of colors by removing brightness information.

[0026] Read the brightness uniformity, contrast index, and color gamut coverage rate 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 specific calculation formula is as follows: , where PEC represents the performance parameter evaluation coefficient of the target display screen, represents the maximum value of the preset contrast index, Gcd i represents the color gamut coverage rate deviation of the i-th frame of the display screen image to be detected, , represents the preset standard color gamut coverage rate, represents the exponential function.

[0027] It should be specifically noted that in the formula, the larger the brightness uniformity, the larger the contrast index, and the smaller the color gamut coverage rate deviation of each frame of the display screen image to be detected, the larger 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 rate deviation do not affect each other.

[0028] Display screen image anomaly detection module: Detect and analyze the anomalies of the display screen image based on the image anomaly parameter characteristics to obtain the image anomaly feature coefficient of the target display screen; In this embodiment, it should be specifically noted that the execution method of the display screen image anomaly detection module is specifically as follows: Based on the defect characteristics of each frame of the display screen image to be detected, analyze the defect uniformity index of each frame of the display screen image to be detected. Specifically: Use the object detection model recognition algorithm based on deep learning to identify each frame of the display screen image to be detected, and obtain the defect coordinates of each frame of the display screen image to be detected , and use the formula to calculate the defect uniformity index of the i-th frame of the display screen image to be detected UI i , represents the variance of the abscissa of the defects in the i-th frame of the display screen image to be detected, represents the variance of the ordinate of the defects in 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; It should be specifically noted that in the formula, the defect 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, it means that the defects are completely evenly distributed. When UI i = 0, it means that the defects are completely concentrated. Among them, the larger the variance, the more dispersed the defect distribution; the smaller the variance, the more concentrated the defects.

[0029] In this embodiment, it should be specifically noted that the object detection model recognition algorithm based on deep learning can refer to the literature: Research on Image Object Detection Algorithm Based on YOLO Deep Learning Model, Detection Method of Smartphone Panel Surface Defects Based on YOLO V5 Model.

[0030] Based on the scratch characteristics of each frame of the display screen image to be detected, analyze the scratch rate of each frame of the display screen image to be detected. Specifically: Import each frame of the display screen image to be detected into the edge detection algorithm to identify the scratch edge lines in each frame of the display screen image to be detected. Use the threshold segmentation technology to convert each frame of the display screen image into a binary image, where the scratch area is white and the background is black, and perform statistics on it to obtain the number of pixels in the scratch area of each frame of the display screen image to be detected 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 , substitute them into the formula , and obtain the scratch rate of the i-th frame of the display screen image to be detected Sr i ; Read the defect 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 specific calculation formula is as follows: , where ACC represents the image anomaly characteristic coefficient of the target display screen, Db i represents the bright point density of the i-th frame of the display screen image to be detected.

[0031] Specifically, in the formula, the larger the bad pixel uniformity index, the smaller the scratch rate, and the smaller the bright point density of each frame of the display screen image to be detected, the smaller the image anomaly characteristic coefficient of the target display screen, indicating that the image quality of the target display screen is better; and the bad pixel uniformity index, scratch rate, and bright point density do not affect each other.

[0032] In this embodiment, specifically, the method for obtaining the bright point density of the i-th frame of the display screen image to be detected is as follows: Obtain each frame of the display screen image to be detected, and the pixel value range of the image is , where 255 represents the brightest pixel value; Perform gray-scale processing on each frame of the display screen image to be detected to obtain each frame of the display screen gray-scale image. Traverse all the pixels of the gray-scale image, and count the number of pixels in each frame of the display screen gray-scale image whose brightness value is greater than or equal to the brightness threshold T Nb i , from the formula , calculate the bright point density of the i-th frame of the display screen image to be detected Db i , Nb i represents the number of bright point pixels in 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, where the set brightness threshold T is 200.

[0033] Display screen image anomaly control module: Based on the comparison between the image anomaly characteristic coefficient of the target display screen and the preset image anomaly characteristic coefficient, screen out the image anomaly data, and control the image anomaly data through the display screen image anomaly control coefficient; In this embodiment, specifically, the execution method of the display screen image anomaly control module is as follows: Read the image anomaly characteristic coefficient of the target display screen ACC , compare it with the preset image anomaly characteristic coefficient, screen out the data whose image anomaly characteristic coefficient of the target display screen is greater than the preset image anomaly characteristic coefficient, and mark it as image anomaly data, and control the image anomaly data through the display screen image anomaly control coefficient; Among them, the calculation formula of the display screen image anomaly control coefficient is specifically: , where represents the abnormal image control coefficient of the display screen, and

[0034] when ; when the difference between the abnormal image feature coefficient of the target display screen and the preset abnormal image feature coefficient increases, will increase, the denominator will increase, the value of will decrease, indicating that the more the abnormal image degree exceeds the preset value, the smaller the control coefficient, and the greater the control force needs to be increased; when the difference between the abnormal image feature coefficient of the target display screen and the preset abnormal image feature coefficient decreases,

[0035] The display screen detection quality analysis module: is used to analyze and obtain the quality evaluation index of the target display screen according to the performance parameter evaluation coefficient and the abnormal image feature coefficient of the target display screen; In this embodiment, it should be specifically noted that the execution method of the display screen detection quality analysis module is as follows: Obtain the performance parameter evaluation coefficient of the target display screen PEC and the abnormal image feature coefficient of the target display screen ACC , and analyze and obtain the quality evaluation index of the target display screen , and the calculation formula is: ; Compare the quality evaluation index of the target display screen with the 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 normal and abnormal detection quality are respectively marked as the detection results of the target display screen.

[0036] It should be specifically noted that in the formula, the larger the performance parameter evaluation coefficient PEC of the target display screen 、 and the smaller the abnormal image feature coefficient ACC , the larger the quality evaluation index of the target display screen, and the better the quality detection result of the target display screen; In the formula, the performance parameter evaluation coefficient PEC, of the target display screen ACC and the abnormal image feature coefficient

[0037] Display screen detection result display module: used to display the display screen detection results on the mobile devices of management personnel in the form of a report, and store the detection data in the database.

[0038] Embodiment 2 Please refer to Figure 2 As shown, the present invention provides a multi-parameter detection method for a display screen, including the following steps: S1: Collecting the display screen image, S2: Preprocessing the display screen image, S3: Extracting the display screen image features, S4: Detecting and analyzing the display screen performance parameters, S5: Detecting and analyzing the display screen image anomalies, S6: Controlling the display screen image anomalies, S7: Analyzing the display screen detection quality, and S8: Displaying the display screen detection results; S1: Collecting the display screen image: Using a high-resolution image acquisition device, collect the image of the target display screen, and mark it as the display screen image to be processed; S2: Preprocessing the display screen image: Preprocess the display screen image to be processed through preprocessing methods of image enhancement and filtering algorithms, and mark the preprocessed image as the display screen image to be detected; S3: Extracting the display screen image features: Extract the image features of the display screen image to be detected, and the image features include image performance parameter features and image anomaly parameter features; S4: Detecting and analyzing the display screen performance parameters: Based on the image performance parameter features, detect and analyze the display screen performance parameters to obtain the performance parameter evaluation coefficient of the target display screen; S5: Detecting and analyzing the display screen image anomalies: Based on the image anomaly parameter features, detect and analyze the display screen image anomalies to obtain the image anomaly feature coefficient of the target display screen; S6: Controlling the display screen image anomalies: Based on the comparison between the image anomaly feature coefficient of the target display screen and the preset image anomaly feature coefficient, screen out the image anomaly data, and control the image anomaly data through the display screen image anomaly control coefficient; S7: Analyzing the display screen detection quality: According to the performance parameter evaluation coefficient and the image anomaly feature coefficient of the target display screen, analyze and obtain the quality evaluation index of the target display screen; S8: Displaying the display screen detection results: Display the display screen detection results on the mobile devices of management personnel in the form of a report, and store the detection data in the database.

[0039] Finally: The above are only the preferred embodiments of the present invention and are not used to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0040] As described above, it is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claimed rights.

Claims

1. A multi-parameter detection system for a display screen, characterized in that Including: Display screen image acquisition module: Using a high-resolution image acquisition device, it acquires the image of the target display screen and marks it as the to-be-processed display screen image; Display screen image preprocessing module: It is used to preprocess the to-be-processed display screen image through preprocessing methods such as image enhancement and filtering algorithms, and marks the preprocessed image as the to-be-detected display screen image; Display screen image feature extraction module: It is used to extract image features from the to-be-detected display screen image, and the image features include image performance parameter features and image anomaly parameter features; Display screen performance parameter detection module: Based on the image performance parameter features, it detects and analyzes the display screen performance parameters to obtain the performance parameter evaluation coefficient of the target display screen; Display screen image anomaly detection module: Based on the image anomaly parameter features, it detects and analyzes the display screen image anomalies to obtain the image anomaly feature coefficient of the target display screen; Display screen image anomaly control module: Based on the comparison between the image anomaly feature coefficient of the target display screen and the preset image anomaly feature coefficient, it filters out the image anomaly data and controls the image anomaly data through the display screen image anomaly control coefficient; Display screen detection quality analysis module: It is used to analyze and obtain 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; Display screen detection result display module: It is used to display the display screen detection results in the form of a report on the mobile device of the management personnel and store the detection data in the database.

2. The multi-parameter detection system for a display screen according to claim 1, wherein: The execution method of the display screen image preprocessing module is specifically as follows: Mark the preprocessed image as the to-be-detected display screen image. The to-be-detected display screen image includes n frames of images, and they are numbered 1, 2,... i,... n in sequence, where i is the number of each frame of the to-be-detected display screen image.

3. A multi-parameter detection system for a display screen according to claim 1, wherein: The execution method of the display screen image feature extraction module is specifically as follows: Use an image feature recognition algorithm based on deep learning to extract the display screen feature map from the to-be-detected display screen image, and obtain the performance parameter features and image anomaly parameter features of the display screen feature map; The image performance parameter features include: brightness feature, contrast feature, and color gamut feature of each frame of the to-be-detected display screen image; The image anomaly parameter features include: dead pixel feature, bright pixel feature, and scratch feature of each frame of the to-be-detected display screen image.

4. A multi-parameter detection system for a display screen according to claim 1, characterized in that: The execution method of the display screen performance parameter detection module is specifically as follows: Brightness values based on the brightness characteristics of each frame of the display screen image to be detected Br i , analyze the brightness uniformity of each frame of the display screen image to be detected. Specifically: divide each frame of the display screen image to be detected into Q regular sub-regions, where Q is the total number of sub-regions. According to the formula , calculate the brightness uniformity of the i-th frame of the display screen image to be detected , where represents the average brightness of the k-th sub-region corresponding to the i-th frame of the display screen image to be detected, 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, and k is the number of each sub-region, k = 1, 2,... Q; Based on the average brightness of each frame of the display screen image to be detected , analyze the contrast index of each frame of the display screen image to be detected. Specifically: perform grayscale processing on each frame of the display screen image to be detected to obtain each frame of the grayscale image of the display screen to be detected, and obtain the standard deviation of the grayscale values of each frame of the grayscale image of the display screen to be detected. According to the formula , calculate the contrast index of the i-th frame of the display screen image to be detected 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; Based on the gamut characteristics of each frame of the display screen image to be detected, analyze the gamut coverage rate of each frame of the display screen image to be detected. Specifically: obtain the area of the display screen gamut in the chromaticity diagram of each frame of the display screen image to be detected A i , and at the same time obtain the area of the standard gamut , from , calculate the gamut coverage rate of the i-th frame of the display screen image to be detected Cgc i , A i represents the area of the display screen gamut in the chromaticity diagram of the i-th frame of the display screen image to be detected; Read the brightness uniformity, contrast index, and color gamut coverage rate of each frame of the to-be-detected display screen image, analyze the display screen performance parameters, and obtain the performance parameter evaluation coefficient of the target display screen. The specific calculation formula is as follows: , where PEC represents the performance parameter evaluation coefficient of the target display screen, represents the maximum value of the preset contrast index, Gcd i represents the gamut coverage deviation of the i-th frame of the display screen image to be detected, , represents the preset standard gamut coverage, represents the exponential function.

5. A multi-parameter detection system for a display screen according to claim 1, characterized in that: The execution method of the display screen image anomaly detection module is specifically as follows: Based on the bad pixel features of each frame of the display screen image to be detected, analyze the bad pixel uniformity index of each frame of the display screen image to be detected. Specifically: Use the object detection model recognition algorithm based on deep learning to identify each frame of the display screen image to be detected, and obtain the bad pixel coordinates of each frame of the display screen image to be detected , and calculate the bad pixel uniformity index of the i-th frame of the display screen image to be detected according to the formula . UI i , represents the variance of the abscissa of the bad pixels in the i-th frame of the display screen image to be detected, represents the variance of the ordinate of the bad pixels in 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; Based on the scratch features of each frame of the display screen image to be detected, analyze the scratch rate of each frame of the display screen image to be detected. Specifically: Import each frame of the display screen image to be detected into an edge detection algorithm to identify the scratch edge lines in each frame of the display screen image to be detected. Use threshold segmentation technology to convert each frame of the display screen image to be detected into a binary image, with the scratch area being white and the background being black, and perform statistics on it to obtain the number of pixels in the scratch area of each frame of the display screen image to be detected 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 , substitute them into the formula , and obtain the scratch rate of the i-th frame of the display screen image to be detected Sr i ; Read the dead pixel uniformity index and scratch rate of each frame of the to-be-detected display screen image, calculate the image anomaly feature coefficient of the target display screen. The specific calculation formula is as follows: , where ACC represents the image anomaly characteristic 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.

6. The multi-parameter detection system for a display screen according to claim 5, wherein: The acquisition method of the bright pixel density of the i-th frame of the to-be-detected display screen image is specifically as follows: Obtain the display screen images to be detected for each frame, and the pixel value range of the images is , where 255 represents the brightest pixel value; Perform grayscale processing on each frame of the display screen image to be detected to obtain the grayscale image of the display screen to be detected for each frame. Traverse all pixels of the grayscale image and count the number of pixels in the grayscale image of the display screen to be detected for each frame whose brightness value is greater than or equal to the brightness threshold T Nb i , and from the formula , calculate the highlight density of the i-th frame of the display screen image to be detected Db i , Nb i represents the number of highlight pixels in 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, where the brightness threshold T is set to 200.

7. The multi-parameter detection system for a display screen according to claim 1, characterized in that: The execution method of the display screen image anomaly control module is specifically as follows: Read the image anomaly characteristic coefficient of the target display screen ACC , compare it with the preset image anomaly characteristic coefficient, filter out the data where the image anomaly characteristic coefficient of the target display screen is greater than the preset image anomaly characteristic coefficient, and mark it as image anomaly data, and control the image anomaly data through the display screen image anomaly control coefficient; Among them, the calculation formula of the display screen image abnormality control coefficient is specifically as follows: , where represents the display screen image abnormality control coefficient, represents the preset image abnormality characteristic coefficient.

8. The multi-parameter detection system for a display screen according to claim 1, wherein: The execution method of the display screen detection quality analysis module is as follows: Obtain the performance parameter evaluation coefficient of the target display screen PEC and the image abnormality feature coefficient of the target display screen ACC , and analyze to obtain the quality evaluation index of the target display screen , and the calculation formula is: ; Compare the quality evaluation index of the target display screen with the 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. Mark the results of normal and abnormal detection quality as the detection results of the target display screen respectively.

9. A method for detecting multiple parameters of a display screen, which is used for a system for detecting multiple parameters of a display screen according to any one of claims 1-8 above, characterized in that, It includes the following steps: S1: Collect display screen images: Use a high-resolution image acquisition device to collect the image of the target display screen and mark it as the to-be-processed display screen image. S2: Preprocess the display screen image: Preprocess the to-be-processed display screen image through preprocessing methods such as image enhancement and filtering algorithms, and mark the preprocessed image as the to-be-detected display screen image. S3: Extract display screen image features: Extract image features from the to-be-detected display screen image, and the image features include image performance parameter features and image anomaly parameter features. S4: Detect and analyze display screen performance parameters: Detect and analyze the display screen performance parameters based on the image performance parameter features to obtain the performance parameter evaluation coefficient of the target display screen. S5: Detect and analyze display screen image anomalies: Detect and analyze the display screen image anomalies based on the image anomaly parameter features to obtain the image anomaly feature coefficient of the target display screen. S6: Control display screen image anomalies: Compare the image anomaly feature coefficient of the target display screen with the preset image anomaly feature coefficient, screen out the image anomaly data, and control the image anomaly data through the display screen image anomaly control coefficient. S7: Analyze the detection quality of the display screen: Analyze and obtain 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. S8: Display the detection results of the display screen: Display the detection results of the display screen on the mobile device of the management personnel in the form of a report, and store the detection data in the database.

Images