Liquid crystal display dead pixel detection method and device and storage medium

Through preset testing schemes and feature analysis technology, combined with watershed algorithms and bad point feature networks, the location and causes of the broken point of the LCD screen are identified, and the problem of misjudgment and insufficient linkage of the existing detection methods is solved, achieving efficient and accurate The detection of the broken point of LCD screen and the optimization of production line have reduced the defective yield rate.

CN119068787AActive Publication Date: 2024-12-03SHENZHEN HONGSHENGTONG PHOTOELECTRIC CO LTD

Patent Information

Application Number
CN202411256394.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-09
Publication Date
2024-12-03
Estimated Expiration
2044-09-09

AI Technical Summary

Technical Problem

The existing LCD screen bad point detection methods have misjudgment of uneven light, reflected light, noise and other factors that affect the detection results. It is difficult to identify subtle bad points, and the linkage and integration are low, resulting in high product defect rate.

Method used

The preset test scheme is used to obtain the standard and actual gradient value matrix of the LCD screen, combined with the watershed algorithm and the knowledge tree diagram network for bad point features, comprehensive bad point position analysis and feature recognition, and reduce noise through Fourier transform and median filtering. , identify the locations and causes of bad points, and use the Internet of Things and regression analysis to optimize the production line.

Benefits of technology

It realizes comprehensive and accurate detection of the broken point of the LCD screen, improves detection efficiency and accuracy, reduces the defective product rate, and optimizes the production line through intelligent feedback, improving product quality and production efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119068787A_ABST
    Figure CN119068787A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of liquid crystal display detection, in particular to a liquid crystal display dead pixel detection method and device and a storage medium. Controlling the test equipment to test the target liquid crystal screen based on a preset test scheme, obtaining a screen characteristic image of the target liquid crystal screen, and constructing an actual gradient value matrix of the target liquid crystal screen according to the screen characteristic image; carrying out dead pixel position analysis on the target liquid crystal screen according to the actual gradient value matrix and the standard gradient value matrix of the target liquid crystal screen to obtain a dead pixel position area in the screen characteristic image; segmenting the screen characteristic image to obtain a sub-characteristic image corresponding to a dead pixel position area in the target liquid crystal screen; and feature analysis is performed on each sub-feature image based on the defective pixel feature knowledge tree graph probability network to obtain defective pixel names and defective pixel inducements of all defective pixel position areas in the target liquid crystal display, comprehensive and accurate defective pixel detection of the target liquid crystal display can be realized through the method, and the detection efficiency and accuracy are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of liquid crystal screen detection, and in particular to a method, a detection device and a storage medium for detecting bad pixels of a liquid crystal screen. Background Art

[0002] With the popularity of smart phones and the increasing requirements of users for screen display quality, the problem of bad pixels on mobile phone LCD screens has received increasing attention. In order to improve the efficiency and accuracy of bad pixel detection on mobile phone LCD screens, bad pixel detection methods based on image processing technology have gradually developed in recent years. By using a camera to capture images of the LCD screen and identifying the location of bad pixels through image processing algorithms, automatic bad pixel detection can be achieved. However, the existing detection methods of image processing technology still have certain limitations: First, due to the complex structure and optical properties of the LCD screen, the image acquisition and processing process is easily affected by factors such as uneven illumination, reflected light, and noise, resulting in misjudgment of the detection results. Secondly, some subtle bad pixels, such as color cast and light leakage, are difficult to accurately identify through existing image processing algorithms, and more complex algorithms and more sophisticated equipment are required for detection. Finally, the existing methods have low linkage and integration with the production line, and cannot perform intelligent feedback adjustment on the production line according to the detection results, resulting in a high product defect rate. Therefore, overcoming these technical obstacles and developing more accurate, intelligent, and automated bad pixel detection methods are important directions for the development of mobile phone LCD screen quality detection technology. Summary of the invention

[0003] The present invention overcomes the limitations of existing detection methods and provides a liquid crystal screen bad pixel detection method, a detection device and a storage medium.

[0004] To achieve the above object, the present invention discloses a method for detecting bad pixels of a liquid crystal screen, comprising the following steps: Obtaining a preset test scheme for a target LCD screen, determining a standard gradient value corresponding to each pixel point in the target LCD screen when testing the target LCD screen according to the preset test scheme, and generating a standard gradient value matrix for the target LCD screen according to the standard gradient values ​​corresponding to each pixel point; Controlling the test equipment to test the target LCD screen based on the preset test scheme, and acquiring a screen characteristic image of the target LCD screen, and constructing an actual gradient value matrix of the target LCD screen according to the screen characteristic image; Performing bad pixel position analysis on the target LCD screen according to the actual gradient value matrix and the standard gradient value matrix of the target LCD screen to obtain one or more bad pixel position regions in the screen characteristic image; performing segmentation processing on the screen characteristic image based on the watershed algorithm to obtain a sub-characteristic image corresponding to the bad pixel position region in the target LCD screen; Based on the bad pixel feature knowledge tree graph network, feature analysis is performed on each sub-characteristic image to obtain the bad pixel names and bad pixel causes of all bad pixel location areas in the target LCD screen, and the bad pixel names and bad pixel causes of all bad pixel location areas in the target LCD screen are uploaded to the detection database.

[0005] Preferably, the actual gradient value matrix of the target liquid crystal screen is constructed according to the screen characteristic image, specifically: The screen characteristic image is grayed out, and the grayed out screen characteristic image is imported into the OpenCV library; Based on the cv2.Laplacian function in the OpenCV library, a convolution operation is performed on each pixel in the screen characteristic image; the convolution result is used as the gradient value of each pixel, the magnitude of the gradient value represents the degree of change of the pixel, and the direction represents the direction of change; Constructing a blank matrix, storing the gradient value of each pixel point in the blank matrix, and obtaining a preliminary gradient value matrix of the target liquid crystal screen; Performing Fourier transform processing on the preliminary gradient value matrix to obtain a frequency spectrum of the preliminary gradient value matrix; wherein the horizontal axis of the frequency spectrum represents frequency, and the vertical axis represents energy corresponding to the frequency; Obtain the frequency intensity value of each element in the preliminary gradient value matrix according to the spectrum diagram of the preliminary gradient value matrix; compare the frequency intensity value of each element in the preliminary gradient value matrix with a preset frequency intensity value threshold; Mark the position area of ​​the elements corresponding to the frequency intensity value greater than the preset frequency intensity value threshold in the preliminary gradient value matrix, and define it as the high-frequency position area; The high-frequency position area of ​​the preliminary gradient value matrix is ​​filtered based on the median filtering algorithm to generate the actual gradient value matrix of the target LCD screen.

[0006] Preferably, the target LCD screen is subjected to bad pixel position analysis according to the actual gradient value matrix and the standard gradient value matrix of the target LCD screen to obtain one or more bad pixel position areas in the screen characteristic image, specifically: Calculate the absolute difference between two elements in each identical matrix position of the actual gradient value matrix and the standard gradient value matrix in the target LCD screen; Construct an absolute difference matrix based on the absolute difference between two elements in each same matrix position of the actual gradient value matrix and the standard gradient value matrix; Acquire process accuracy requirement information of the target liquid crystal screen, and preset a limit difference threshold value according to the process accuracy requirement information; compare each absolute difference in the absolute difference matrix with the limit difference threshold value one by one; If each absolute difference in the absolute difference matrix is ​​not greater than the limit difference threshold, it means that there is no bad pixel in the target LCD screen, indicating that the target LCD screen is a qualified product, and the test result that the target LCD screen is a qualified product is uploaded to the test database; If there is one or more absolute difference values ​​in the absolute difference matrix that are greater than the limit difference threshold, it indicates that there are bad pixels in the target LCD screen, indicating that the target LCD screen is a defective product, and the detection result that the target LCD screen is a defective product is uploaded to the detection database; Furthermore, if there is one or more absolute difference values ​​in the absolute difference matrix that are greater than the limit difference threshold, the element position nodes whose absolute difference values ​​are greater than the limit difference threshold are marked in the actual gradient value matrix as bad pixel positions, and the marked bad pixel positions are aligned in the screen characteristic image; All independent closed areas marked as bad pixel locations in the screen characteristic image are acquired to obtain one or more bad pixel location areas in the screen characteristic image.

[0007] Preferably, based on the bad pixel feature knowledge tree graph network, feature analysis is performed on each sub-characteristic image to obtain the bad pixel names and bad pixel causes of all bad pixel location areas in the target LCD screen, specifically: Obtain the bad pixel feature images corresponding to various types of bad pixels in the LCD screen through the big data network, and obtain the bad pixel causes of various types of bad pixels; Constructing a knowledge tree graph network, and treating each type of bad pixel in the LCD screen as a cutting node, cutting out a plurality of branch nodes in the knowledge tree graph network according to each cutting node, and assigning a corresponding bad pixel name label to each branch node according to the corresponding type of bad pixel; The bad pixel feature images and bad pixel inducements of various types of bad pixels in the LCD screen are mapped to the corresponding branch nodes to obtain the bad pixel feature knowledge tree graph network; Obtaining a sub-characteristic image corresponding to a bad pixel location area in a target LCD screen, and importing the sub-characteristic image into the bad pixel feature knowledge tree graph network; Calculating the image similarity between the sub-characteristic image and the bad pixel feature image to which each branch node in the bad pixel feature knowledge tree graph network belongs based on the perceptual hash algorithm; The calculated similarities of each image are used to mark the branch node with the greatest image similarity, and the corresponding bad pixel name and bad pixel inducement are extracted from the branch node with the greatest image similarity to obtain the bad pixel name and bad pixel inducement of the corresponding bad pixel position area in the target LCD screen; Repeat the above steps to obtain the bad pixel names and bad pixel causes of all bad pixel locations in the target LCD screen.

[0008] The following steps are also included: Acquire detection data of each LCD screen within a preset time period in a detection database; wherein the detection data includes the detection results of each LCD screen, and the names and causes of bad pixels of the LCD screens with unqualified detection results; Obtaining the defective rate of the current production batch of LCD screens according to the detection data of each LCD screen within a preset time period, and determining whether the defective rate is greater than a preset defective rate threshold; If the defective rate is greater than a preset defective rate threshold, the required production volume of the current production batch of LCD screens is calculated according to the defective rate, supplementary warning information is generated according to the required production volume, and the supplementary warning information is sent to a preset terminal; At the same time, the production performance parameter information of the production line producing the current production batch of LCD screens is obtained, as well as the order information of the current production batch of LCD screens, and the delivery time node of the current production batch of LCD screens is determined according to the order information; Acquire the production lines in the production workshop that are in an idle state before the delivery time node, and acquire the production performance parameter information of the production lines in the idle state; Analyze the attention score between the production performance parameter information of the production line producing the current production batch of LCD screens and the production performance parameter information of the production line in an idle state based on the local sensitive attention mechanism; Only production lines in an idle state whose attention scores are greater than a preset score threshold are extracted and defined as available supplementary production lines; operation log information of each available supplementary production line is obtained, and the failure probability of each available supplementary production line is obtained according to the operation log information; An available supplementary production line with the smallest failure probability value is obtained as a recommended supplementary production line, and the recommended supplementary production line is sent to a preset terminal.

[0009] The following steps are also included: If the defective product rate is greater than a preset defective product rate threshold, the bad pixel cause of the LCD screen whose detection result is defective within a preset time period is obtained; Performing statistical analysis on the causes of bad pixels of LCD screens that are unqualified products within a preset time period to obtain the occurrence frequency values ​​of various causes of bad pixels; Mark the bad pixel inducement whose occurrence frequency value is greater than the preset frequency threshold as a high-incidence bad pixel inducement, and mark the bad pixel inducement whose occurrence frequency value is not greater than the preset frequency threshold as a low-incidence bad pixel inducement; Obtaining process characteristic information of each process station in the production line, combining the process characteristic information of each process station and introducing a regression analysis algorithm to analyze the influence of each process station in the production line on the cause of high incidence of bad pixels; Acquire various real-time process parameters of process stations whose influence is greater than a preset influence threshold based on the Internet of Things, and acquire various preset process parameters of process stations whose influence is greater than a preset influence threshold; Calculate the process parameter difference between various real-time process parameters of the process stations whose influence degree is greater than a preset influence degree threshold and the preset process parameters; The real-time process parameters corresponding to the process parameter differences that are greater than the preset differences are marked, and the marked real-time process parameters are corrected based on the corresponding process parameter differences.

[0010] In addition, to achieve the above-mentioned purpose, the present invention also discloses a liquid crystal screen bad pixel detection device, the liquid crystal screen bad pixel detection device includes a memory and a processor, the memory stores a liquid crystal screen bad pixel detection method program, when the liquid crystal screen bad pixel detection method program is executed by the processor, the steps of any one of the liquid crystal screen bad pixel detection methods are implemented.

[0011] In addition, to achieve the above-mentioned purpose, the present invention also discloses a computer-readable storage medium, which includes a LCD bad pixel detection method program. When the LCD bad pixel detection method program is executed by a processor, the steps of any one of the LCD bad pixel detection methods are implemented.

[0012] The present invention solves the technical defects existing in the background technology, and has the following beneficial effects: based on a preset test scheme, a test device is controlled to test a target LCD screen, a screen characteristic image of the target LCD screen is obtained, and an actual gradient value matrix of the target LCD screen is constructed according to the screen characteristic image; a bad pixel position analysis is performed on the target LCD screen according to the actual gradient value matrix of the target LCD screen and a standard gradient value matrix, and one or more bad pixel position areas in the screen characteristic image are obtained; based on a watershed algorithm, the screen characteristic image is segmented to obtain a sub-characteristic image corresponding to the bad pixel position area in the target LCD screen; based on a bad pixel feature knowledge tree graph network, feature analysis is performed on each sub-characteristic image to obtain the bad pixel names and bad pixel inducements of all bad pixel position areas in the target LCD screen. The method can realize comprehensive and accurate bad pixel detection of the target LCD screen, thereby improving detection efficiency and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, drawings of other embodiments can be obtained based on these drawings without paying creative work.

[0014] Figure 1A first method flow chart of a method for detecting bad pixels of a liquid crystal screen; Figure 2 A flow chart of a second method of a method for detecting bad pixels on a liquid crystal screen; Figure 3 The third method flow chart of a method for detecting bad pixels of a liquid crystal display is shown in FIG. DETAILED DESCRIPTION

[0015] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0016] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0017] like Figure 1 As shown, the present invention discloses a method for detecting bad pixels of a liquid crystal screen, comprising the following steps: S102: Acquire a preset test scheme of a target LCD screen, determine a standard gradient value corresponding to each pixel point in the target LCD screen when testing the target LCD screen according to the preset test scheme, and generate a standard gradient value matrix of the target LCD screen according to the standard gradient value corresponding to each pixel point; S104: controlling the test device to test the target LCD screen based on the preset test scheme, and obtaining a screen characteristic image of the target LCD screen, and constructing an actual gradient value matrix of the target LCD screen according to the screen characteristic image; S106: performing bad pixel position analysis on the target LCD screen according to the actual gradient value matrix and the standard gradient value matrix of the target LCD screen to obtain one or more bad pixel position regions in the screen characteristic image; performing segmentation processing on the screen characteristic image based on the watershed algorithm to obtain a sub-characteristic image corresponding to the bad pixel position region in the target LCD screen; S108: Perform feature analysis on each sub-characteristic image based on the bad pixel feature knowledge tree graph network to obtain the bad pixel names and bad pixel causes of all bad pixel location areas in the target LCD screen, and upload the bad pixel names and bad pixel causes of all bad pixel location areas in the target LCD screen to the detection database.

[0018] It should be noted that, first, the preset test scheme of the target LCD screen is obtained, and the standard gradient value of each pixel is determined according to the scheme to generate a standard gradient value matrix. Then, the target LCD screen is tested by controlling the test equipment, the screen characteristic image is obtained, and the actual gradient value matrix is ​​constructed. Next, the bad pixel position analysis of the target LCD screen is performed according to the actual gradient value matrix and the standard gradient value matrix to obtain the bad pixel position area. Then, the screen characteristic image is segmented using the watershed algorithm to obtain a sub-characteristic image. Finally, based on the bad pixel feature knowledge tree graph network, feature analysis is performed on each sub-characteristic image to obtain the bad pixel name and bad pixel inducement, and upload them to the detection database. Through this method, comprehensive and accurate bad pixel detection of the target LCD screen can be achieved, and the detection efficiency and accuracy are improved. Based on the bad pixel feature knowledge tree graph network, feature analysis is performed on each sub-characteristic image, different types of bad pixels can be identified, and their inducements can be analyzed, which provides strong support for the quality assessment and improvement of the LCD screen.

[0019] Preferably, the actual gradient value matrix of the target liquid crystal screen is constructed according to the screen characteristic image, specifically: The screen characteristic image is grayed out, and the grayed out screen characteristic image is imported into the OpenCV library; Based on the cv2.Laplacian function in the OpenCV library, a convolution operation is performed on each pixel in the screen characteristic image; the convolution result is used as the gradient value of each pixel, the magnitude of the gradient value represents the degree of change of the pixel, and the direction represents the direction of change; Constructing a blank matrix, storing the gradient value of each pixel point in the blank matrix, and obtaining a preliminary gradient value matrix of the target liquid crystal screen; Performing Fourier transform processing on the preliminary gradient value matrix to obtain a frequency spectrum of the preliminary gradient value matrix; wherein the horizontal axis of the frequency spectrum represents frequency, and the vertical axis represents energy corresponding to the frequency; Obtain the frequency intensity value of each element in the preliminary gradient value matrix according to the spectrum diagram of the preliminary gradient value matrix; compare the frequency intensity value of each element in the preliminary gradient value matrix with a preset frequency intensity value threshold; Mark the position area of ​​the elements corresponding to the frequency intensity value greater than the preset frequency intensity value threshold in the preliminary gradient value matrix, and define it as the high-frequency position area; The high-frequency position area of ​​the preliminary gradient value matrix is ​​filtered based on the median filtering algorithm to generate the actual gradient value matrix of the target LCD screen.

[0020] It should be noted that first, the screen characteristic image is grayed to simplify the image data for subsequent processing. Then, the cv2.Laplacian function in the OpenCV library is used to perform convolution operations on the image to calculate the gradient value of each pixel. The gradient value reflects the degree and direction of pixel changes around the pixel, which helps to identify the edges and details in the image. A blank matrix is ​​constructed to store the gradient values ​​of all pixels to form a preliminary gradient value matrix. Through Fourier transform, the preliminary gradient value matrix is ​​converted into a spectrum diagram, which uses frequency and energy as coordinate axes to intuitively display the distribution of different frequency components in the image. According to the spectrum diagram analysis, high-frequency position areas can be identified, which contain the edges and important details of the image. Next, the elements in the preliminary gradient value matrix whose frequency intensity values ​​are greater than the preset threshold are marked as high-frequency position areas. This is based on the understanding of image features, and the high-frequency area is the noise point of the matrix. In order to further purify these high-frequency position areas and reduce the influence of noise, the median filtering algorithm is used for processing. Median filtering is a nonlinear filtering method that is particularly suitable for removing isolated noise points in images, maintaining edges and details while reducing interference. Finally, after the above processing steps, the actual gradient value matrix of the target LCD screen is obtained. This matrix contains detailed characteristic information of the LCD screen, including not only the positioning of edges and details, but also the suppression of noise, providing basic data for subsequent analysis and quality control. This method can efficiently and accurately analyze the characteristics of the LCD screen, which is of great significance for improving product quality and performance.

[0021] Preferably, if Figure 2 As shown, the target LCD screen is subjected to bad pixel position analysis according to the actual gradient value matrix and the standard gradient value matrix of the target LCD screen, and one or more bad pixel position areas in the screen characteristic image are obtained, specifically: S202: Calculate the absolute difference between two elements in each same matrix position of the actual gradient value matrix and the standard gradient value matrix in the target LCD screen; S204: constructing an absolute difference matrix according to the absolute difference between two elements in each same matrix position of the actual gradient value matrix and the standard gradient value matrix; S206: Acquire process accuracy requirement information of the target LCD screen, preset a limit difference threshold value according to the process accuracy requirement information; compare each absolute difference in the absolute difference matrix with the limit difference threshold value one by one; S208: If each absolute difference in the absolute difference matrix is ​​not greater than the limit difference threshold, it means that there is no bad pixel in the target LCD screen, indicating that the target LCD screen is a qualified product, and the test result that the target LCD screen is a qualified product is uploaded to the test database; S210: If there is one or more absolute difference values ​​in the absolute difference matrix that are greater than the limit difference threshold, it indicates that there are bad pixels in the target LCD screen, indicating that the target LCD screen is a defective product, and the detection result that the target LCD screen is a defective product is uploaded to the detection database; S212: If there is one or more absolute difference values ​​in the absolute difference matrix that are greater than the limit difference threshold, then in the actual gradient value matrix, element position nodes whose absolute difference values ​​are greater than the limit difference threshold are marked as bad pixel positions, and the marked bad pixel positions are aligned in the screen characteristic image; S214: Acquire all independent closed areas marked as bad pixel locations in the screen characteristic image to obtain one or more bad pixel location areas in the screen characteristic image.

[0022] It should be noted that by comparing the actual gradient value matrix of the target LCD screen with the standard gradient value matrix, it is determined whether the LCD screen has quality problems. Specifically, first, the absolute difference between the actual gradient value matrix and the standard gradient value matrix at the corresponding position is calculated, and then these differences are organized into a new matrix, namely the absolute difference matrix. This step is intended to quantify the difference between the two and provide a data basis for subsequent quality assessment. Secondly, according to the process accuracy requirements of the target LCD screen, a limit difference threshold is pre-set, and this threshold is used to determine whether the LCD screen meets the quality standards. Next, each difference in the absolute difference matrix is ​​compared with the limit difference threshold. If all the differences are less than or equal to the threshold, it means that the LCD screen meets the quality requirements and is judged as a qualified product, and its test results are recorded in the database. On the contrary, if there are one or more differences exceeding the threshold, it indicates that the LCD screen has quality problems and is judged as an unqualified product, and the test results are also recorded in the database. For those cases where the difference exceeds the threshold, the specific element position will be identified in the actual gradient value matrix and marked as a "bad pixel position". At the same time, these locations will also be marked on the screen characteristic image to intuitively display the problem areas on the LCD screen. Finally, all independent closed areas are extracted from the screen characteristic image with the bad pixel locations marked to form one or more bad pixel location areas. These areas represent the specific locations of quality problems on the LCD screen, providing a clear reference for further analysis or improvement work. This method uses mathematical calculations and image processing to achieve efficient and accurate detection of LCD screen quality. It can not only quickly identify unqualified products, but also accurately locate the problem and improve the reliability of product quality detection and control.

[0023] Preferably, if Figure 3 As shown, based on the bad pixel feature knowledge tree graph network, the feature analysis of each sub-feature image is performed to obtain the bad pixel names and bad pixel causes of all bad pixel location areas in the target LCD screen, specifically: S302: Obtaining bad pixel feature images corresponding to various types of bad pixels in the LCD screen through a big data network, and obtaining bad pixel causes of various types of bad pixels; Among them, the types of bad pixels on LCD screens mainly include the following, each type has its own specific appearance and potential causes, namely "bad pixel inducements": Monochrome bad pixels: These bad pixels usually appear as one or more fixed color dots (usually black, white or other specific colors) on the screen. They may be caused by a circuit break or short circuit in a certain pixel; Light leakage: Light leakage usually occurs when light leaks from a certain part of the screen against a dark background, forming visible bright spots or stripes. This may be caused by a poor seal of the backlight module or screen panel, or a fault in the control circuit of the LED backlight source. Rainbow effect: The rainbow effect is caused by uneven color mixing between pixels, usually manifested as color bands or blocks when the screen displays transition colors. This is mainly caused by the uneven arrangement of liquid crystal molecules; Color deviation: Color deviation means that the color output of a certain pixel is incorrect under a specific color, such as a pixel that should display red but displays other colors. This may be caused by the red, green and blue primary color filters of the pixel or related circuit failure; Dark corners: Dark corners usually appear at the edges of the screen, showing lower brightness than the center area. This may be caused by uneven backlighting, optical design problems, or defects in the screen panel itself; S304: constructing a knowledge tree graph network, and treating each type of bad pixel in the LCD screen as a cutting node, cutting out a plurality of branch nodes in the knowledge tree graph network according to each cutting node, and assigning a corresponding bad pixel name label to each branch node according to the corresponding type of bad pixel; S306: Mapping bad pixel feature images and bad pixel causes of various types of bad pixels in the LCD screen to corresponding branch nodes to obtain a bad pixel feature knowledge tree graph network; S308: Obtain a sub-characteristic image corresponding to the bad pixel location area in the target LCD screen, and import the sub-characteristic image into the bad pixel feature knowledge tree graph network; S310: Calculating the image similarity between the sub-characteristic image and the bad pixel feature image to which each branch node in the bad pixel feature knowledge tree graph network belongs based on the perceptual hash algorithm; S312: Mark the branch node with the greatest image similarity based on the calculated image similarities, extract the corresponding bad pixel name and bad pixel inducement from the branch node with the greatest image similarity, and obtain the bad pixel name and bad pixel inducement of the corresponding bad pixel position area in the target LCD screen; S314: Repeat the above steps to obtain the bad pixel names and bad pixel causes of all bad pixel location areas in the target LCD screen.

[0024] It should be noted that by collecting and analyzing a large amount of bad pixel data of LCD screens, including various types of bad pixel feature images and their causes, a bad pixel feature knowledge tree graph network containing rich knowledge is constructed. This network structure allows the branch nodes with specific attributes to be divided by cutting nodes (representing different types of bad pixels), and each branch node is given a corresponding bad pixel name label. In practical applications, when it is necessary to diagnose the bad pixels of a specific LCD screen, the system will obtain the sub-characteristic image of a certain bad pixel location area in the LCD screen and import it into the constructed bad pixel feature knowledge tree graph network. By using the perceptual hashing algorithm, the system can calculate the similarity between the sub-characteristic image and the bad pixel feature image represented by each branch node in the knowledge tree graph network. The branch node with the highest similarity is usually the most matched with the bad pixel type represented by the sub-characteristic image. Therefore, the system can extract the corresponding bad pixel name and cause from the branch node, thereby identifying the bad pixel type and possible cause in the LCD screen. Through big data and machine learning methods, the system can quickly and accurately identify and classify various bad pixels on the LCD screen, which can effectively improve the detection efficiency, improve the reliability of the detection results, and is of great significance to improving product quality. In addition, the system can also continuously improve its diagnostic capabilities through continuous learning and updating, and adapt to different types of bad pixels and changing market demands.

[0025] The following steps are also included: Acquire detection data of each LCD screen within a preset time period in a detection database; wherein the detection data includes the detection results of each LCD screen, and the names and causes of bad pixels of the LCD screens with unqualified detection results; Obtaining the defective rate of the current production batch of LCD screens according to the detection data of each LCD screen within a preset time period, and determining whether the defective rate is greater than a preset defective rate threshold; If the defective rate is greater than a preset defective rate threshold, the required production volume of the current production batch of LCD screens is calculated according to the defective rate, supplementary warning information is generated according to the required production volume, and the supplementary warning information is sent to a preset terminal; At the same time, the production performance parameter information of the production line producing the current production batch of LCD screens is obtained, as well as the order information of the current production batch of LCD screens, and the delivery time node of the current production batch of LCD screens is determined according to the order information; Among them, production performance parameter information usually includes but is not limited to production rate, equipment utilization, downtime, energy consumption, raw material consumption, etc.; Acquire the production lines in the production workshop that are in an idle state before the delivery time node, and acquire the production performance parameter information of the production lines in the idle state; Analyze the attention score between the production performance parameter information of the production line producing the current production batch of LCD screens and the production performance parameter information of the production line in an idle state based on the local sensitive attention mechanism; Only production lines in an idle state whose attention scores are greater than a preset score threshold are extracted and defined as available supplementary production lines; operation log information of each available supplementary production line is obtained, and the failure probability of each available supplementary production line is obtained according to the operation log information; An available supplementary production line with the smallest failure probability value is obtained as a recommended supplementary production line, and the recommended supplementary production line is sent to a preset terminal.

[0026] It should be noted that, first, the system obtains the inspection data of each LCD screen within the preset time period in the inspection database, including the inspection results and detailed information of defective products. By analyzing these data, the system can count the defective rate of the current production batch and compare it with the preset threshold. If the defective rate exceeds the standard, the system will calculate the number of supplementary production required, generate supplementary warning information, and promptly notify the relevant departments to ensure the adjustment of the production plan and the effective allocation of resources. Secondly, the system obtains the order information and delivery time node of the current production batch, and combines the production performance parameters of the production line to predict the production capacity gap that may occur before delivery. Through the local sensitive attention mechanism, the system analyzes the performance matching between the current production line and the idle production line, and selects the idle production line that matches the performance of the current production line and has a low probability of failure as the recommended supplementary production line. This step helps to quickly respond to production needs and improve production efficiency and product quality. Through real-time data processing, predictive analysis and decision support, the entire system realizes the refined management of the LCD production process, effectively improves production efficiency, reduces the defective rate, optimizes resource allocation, and enhances production flexibility and response speed. Through intelligent forecasting and optimization strategies, the system can effectively respond to market changes, ensure the smooth execution of production plans, and improve corporate competitiveness.

[0027] The following steps are also included: If the defective product rate is greater than a preset defective product rate threshold, the bad pixel cause of the LCD screen whose detection result is defective within a preset time period is obtained; Performing statistical analysis on the causes of bad pixels of LCD screens that are unqualified products within a preset time period to obtain the occurrence frequency values ​​of various causes of bad pixels; Mark the bad pixel inducement whose occurrence frequency value is greater than the preset frequency threshold as a high-incidence bad pixel inducement, and mark the bad pixel inducement whose occurrence frequency value is not greater than the preset frequency threshold as a low-incidence bad pixel inducement; Obtaining process characteristic information of each process station in the production line, combining the process characteristic information of each process station and introducing a regression analysis algorithm to analyze the influence of each process station in the production line on the cause of high incidence of bad pixels; The process characteristic information of each process station in the production line refers to the unique attributes and characteristics of each process station in the production process. This information describes the role of each station in the entire production process, the mode of operation, the equipment and tools used, the required raw materials or parts, process parameters, quality control requirements, and the connection relationship with other stations. Extract data related to the causes of high incidence of bad pixels from the database, including but not limited to process parameters, equipment operating status, operation records, quality inspection results, etc.; select appropriate regression analysis models, such as linear regression, logistic regression, multivariate linear regression, etc., according to actual conditions. The construction of the model needs to consider independent variables (process characteristic information of each process station) and dependent variables (frequency of occurrence of high incidence of bad pixel causes). Use historical data to train the model, and adjust the model parameters so that the model can better fit the historical data. And verify the accuracy and reliability of the model through cross-validation, residual analysis and other methods. According to the results of regression analysis, evaluate the influence of the process characteristic information of each process station on the causes of high incidence of bad pixels. This can be obtained through coefficient estimation, significance test and other methods. The size and positive and negative signs of the coefficients can reflect the direction and intensity of the influence of the variables on the results; interpret the analysis results as the contribution of each process station in the production line to the causes of high incidence of bad pixels, and provide decision-making basis for the optimization of the production process, such as adjusting process parameters, improving equipment, optimizing operation procedures, etc., to reduce the defective rate and improve production efficiency and product quality; Acquire various real-time process parameters of process stations whose influence is greater than a preset influence threshold based on the Internet of Things, and acquire various preset process parameters of process stations whose influence is greater than a preset influence threshold; Calculate the process parameter difference between various real-time process parameters of the process stations whose influence degree is greater than a preset influence degree threshold and the preset process parameters; The real-time process parameters corresponding to the process parameter differences that are greater than the preset differences are marked, and the marked real-time process parameters are corrected based on the corresponding process parameter differences.

[0028] It should be noted that when the defective product rate exceeds the preset threshold, the system will obtain the bad pixel causes of the defective products and perform statistical analysis to find out the high-frequency bad pixel causes and the low-frequency bad pixel causes. Then, the system will combine the process characteristic information of each process station in the production line and use the regression analysis algorithm to analyze the degree of influence of each process station on the high-frequency bad pixel causes. The system obtains the real-time process parameters and preset process parameters of the process station with a greater degree of influence, and calculates the difference between the two. Finally, the system will mark the real-time process parameters with a large difference in process parameters, and correct them according to the corresponding difference. This method can quickly and accurately find the main causes of defective products, and through real-time monitoring and correction of process parameters, timely adjust the production process, reduce the defective rate, and improve product quality and production efficiency.

[0029] The present invention may further include the following steps during practical application: Obtain the historical working data of each process station in each production line when it is in an abnormal state during the historical working process; and obtain the historical working data of each process station in each production line before it is in an abnormal state during the historical working process; Based on the fuzzy algorithm, fuzzy analysis is performed on the historical working data of each process station when it is in an abnormal state during the historical working process, and the fuzzy features of each process station when it is in an abnormal state are obtained; and based on the fuzzy algorithm, fuzzy analysis is performed on the historical working data of each process station in each production line before it is in an abnormal state during the historical working process, and the fuzzy features of each process station before it is in an abnormal state are obtained; A Monte Carlo model is introduced, and the fuzzy features of each process station when it is in an abnormal state and the fuzzy features before it is in an abnormal state are introduced into the Monte Carlo model to perform random deduction of probability states, so as to obtain the transition probability of each process station from before it is in an abnormal state to each abnormal state; Construct an operation state prediction model based on a deep learning network, construct a probability state transfer matrix according to the transition probability of each process station from being in an abnormal state to each abnormal state, import the probability state transfer matrix into the operation state prediction model for back propagation learning training, until the model meets the preset requirements, and output the trained operation state prediction model; If the defective product rate is greater than a preset defective product rate threshold, then various real-time process parameters of the process station whose influence degree is greater than the preset influence degree threshold are obtained, and the various real-time process parameters of the process station whose influence degree is greater than the preset influence degree threshold are imported into the trained operation state prediction model for prediction, and the state transition probability of the process station whose influence degree is greater than the preset influence degree threshold is output; When the state transition probability of a process station whose impact degree is greater than a preset impact degree threshold is greater than a preset probability value, the process station whose impact degree is greater than the preset impact degree threshold is controlled to shut down production and generate fault warning information.

[0030] It should be noted that by analyzing historical data, a probability model of the operating status of the process station is established, and real-time data is used for prediction, and potential failure risks are warned in advance, thereby effectively reducing the downtime rate and defective product rate in the production process. First, the system collects the historical working data of each process station in normal and abnormal states, and uses fuzzy algorithms to analyze these data to extract the characteristics of each station in different states. Then, the system imports these feature data into the Monte Carlo model, simulates the probability transition process of the station from normal state to different abnormal states, and obtains the transition probability of each state. Next, the deep learning network is used to build an operating state prediction model, and the probability state transition matrix calculated by the Monte Carlo model is used as the training data of the model for back propagation learning, and finally a model that can predict the state change of the process station is obtained. When the defective product rate exceeds the preset threshold, the system will obtain the real-time process parameters of the process station with a greater impact, and input them into the trained operating state prediction model to predict the probability of failure of the station. If the prediction result shows that the probability of failure exceeds the preset threshold, the system will control the station to stop production and issue a fault warning message to remind the staff to check and repair. This method combines fuzzy algorithms, Monte Carlo models and deep learning networks to achieve accurate prediction of the operating status of process stations, and can provide early warning of potential failures, effectively reducing the defective rate in the production process and improving production efficiency and product quality.

[0031] The present invention may further include the following steps during practical application: Obtaining negative review data of LCD screens fed back by users, and constructing a negative review heat map of LCD screens according to the negative review data of LCD screens; Acquire detection data of each LCD screen within a preset time period in a detection database, and construct a thermal map of LCD screen detection results according to the detection data; Performing registration processing on the LCD screen negative review heat map and the LCD screen detection result heat map based on the ICP algorithm, and after the registration is completed, calculating the cosine similarity between each sub-region in the LCD screen negative review heat map and the LCD screen detection result heat map based on the cosine similarity algorithm; Only the sub-regions corresponding to the cosine similarity greater than the cosine similarity are extracted, which are defined as the bad review overlap region, and the process stations that are functionally related to the bad review overlap region during the production of the LCD screen are obtained, which are defined as the key monitoring process stations; Acquire the real-time process parameters of the key monitoring process station, import the real-time process parameters of the key monitoring process station into the trained operation state prediction model for prediction, and output the state transition probability of the key monitoring process station; When the state transition probability of a key monitored process station is greater than a preset probability value, the corresponding key monitored process station is controlled to shut down production and generate fault warning information.

[0032] It should be noted that by collecting and analyzing the negative comments (i.e., "bad reviews") of users on LCD screens and the test data of LCD screens, possible problem areas in the production process can be identified and located. First, the negative review data of LCD screens is collected from user feedback, and then the data is used to construct a heat map of negative reviews of LCD screens. This step helps to intuitively show which areas or parts of LCD screens are more frequently negatively reviewed, thereby indicating possible quality problems. Next, the test data of each LCD screen within a preset time period is obtained to construct a heat map of LCD screen test results. This step aims to compare the actual test results with user feedback to further verify and locate the problem areas. Subsequently, the heat map of negative reviews of LCD screens is registered with the heat map of test results through the ICP algorithm to ensure that the two correspond to each other in space. After that, the cosine similarity algorithm is applied to calculate the similarity between each sub-area in the two heat maps to evaluate the consistency between the negative reviews and the test results. The system will screen out sub-areas with high cosine similarity, define them as "negative review overlap areas", and identify process stations that have functional relevance to these areas as "key monitoring process stations". These stations may be key links in the production process where problems are prone to occur. Next, the system will obtain the real-time process parameters of these key monitoring process stations and input these parameters into the pre-trained operation status prediction model. The model predicts the state transition probability of the station, that is, the probability of predicting possible problems in the future. Finally, if the state transition probability of a key monitoring process station exceeds the preset threshold, the system will automatically control the station to stop production and generate fault warning information so that timely measures can be taken to avoid potential quality problems. In general, this process realizes real-time monitoring and problem location of the production process by integrating user feedback, detection data and machine learning technology, which helps to improve product quality, reduce production costs and improve overall production efficiency. Combine user feedback with production process data to realize an intelligent system for LCD production quality control. By correlating user feedback with production process data, potential quality problems can be identified in advance and timely measures can be taken to prevent them, thereby effectively reducing the defective rate, improving product quality and improving user satisfaction.

[0033] In addition, to achieve the above-mentioned purpose, the present invention also discloses a liquid crystal screen bad pixel detection device, the liquid crystal screen bad pixel detection device includes a memory and a processor, the memory stores a liquid crystal screen bad pixel detection method program, when the liquid crystal screen bad pixel detection method program is executed by the processor, the steps of any one of the liquid crystal screen bad pixel detection methods are implemented.

[0034] In addition, to achieve the above-mentioned purpose, the present invention also discloses a computer-readable storage medium, which includes a LCD bad pixel detection method program. When the LCD bad pixel detection method program is executed by a processor, the steps of any one of the LCD bad pixel detection methods are implemented.

[0035] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A method for detecting bad pixels on a liquid crystal display, characterized in that: The following steps are involved: Obtaining a preset test scheme for a target LCD screen, determining a standard gradient value corresponding to each pixel point in the target LCD screen when testing the target LCD screen according to the preset test scheme, and generating a standard gradient value matrix for the target LCD screen according to the standard gradient value corresponding to each pixel point; Controlling the test equipment to test the target LCD screen based on the preset test scheme, obtaining a screen characteristic image of the target LCD screen, and constructing an actual gradient value matrix of the target LCD screen according to the screen characteristic image; performing bad pixel location analysis on the target LCD screen based on an actual gradient value matrix and a standard gradient value matrix to obtain one or more bad pixel location regions in a screen characteristic image; performing segmentation processing on the screen characteristic image based on a watershed algorithm to obtain sub-characteristic images corresponding to the bad pixel location regions in the target LCD screen; Based on the bad pixel feature knowledge tree graph network, feature analysis is performed on each sub-feature image to obtain the bad pixel names and bad pixel causes of all bad pixel location areas in the target LCD screen, and the bad pixel names and bad pixel causes of all bad pixel location areas in the target LCD screen are uploaded to the detection database.

2. A method for detecting bad pixels on a liquid crystal display according to claim 1, characterized in that: The actual gradient value matrix of the target LCD screen is constructed according to the screen characteristic image, specifically: Gray-value processing is performed on the screen characteristic image, and the gray-value processed screen characteristic image is imported into the OpenCV library; Performing a convolution operation on each pixel in the screen characteristic image based on the cv2.Laplacian function in the OpenCV library; using the convolution result as the gradient value of each pixel, where the magnitude of the gradient value represents the degree of change of the pixel, and the direction represents the direction of change; Constructing a blank matrix, storing the gradient value of each pixel in the blank matrix, and obtaining a preliminary gradient value matrix of the target LCD screen; Performing Fourier transform processing on the preliminary gradient value matrix to obtain a frequency spectrum of the preliminary gradient value matrix; wherein the horizontal axis of the frequency spectrum represents frequency and the vertical axis represents energy corresponding to the frequency; Obtaining a frequency intensity value of each element in the preliminary gradient value matrix according to a spectrum diagram of the preliminary gradient value matrix; comparing the frequency intensity value of each element in the preliminary gradient value matrix with a preset frequency intensity value threshold; Mark the location area of ​​the elements corresponding to the frequency intensity value greater than the preset frequency intensity value threshold in the preliminary gradient value matrix, and define it as the high-frequency location area; The high-frequency position area of ​​the preliminary gradient value matrix is ​​filtered based on the median filtering algorithm to generate the actual gradient value matrix of the target LCD screen.

3. The method for detecting bad pixels on a liquid crystal display according to claim 1, wherein: The target LCD screen is analyzed for bad pixel locations based on the actual gradient value matrix and the standard gradient value matrix to obtain one or more bad pixel location areas in the screen characteristic image, specifically: Calculate the absolute difference between two elements in each identical matrix position of the actual gradient value matrix and the standard gradient value matrix in the target LCD screen; Construct an absolute difference matrix based on the absolute difference between the two elements in each same matrix position of the actual gradient value matrix and the standard gradient value matrix; Obtaining process accuracy requirement information of a target liquid crystal display, and presetting a limit difference threshold value according to the process accuracy requirement information; comparing each absolute difference value in the absolute difference matrix with the limit difference threshold value one by one; If each absolute difference in the absolute difference matrix is ​​not greater than the limit difference threshold, it indicates that there are no bad pixels in the target LCD screen, indicating that the target LCD screen is a qualified product, and the test result that the target LCD screen is a qualified product is uploaded to the test database; If one or more absolute differences in the absolute difference matrix are greater than the limit difference threshold, it indicates that there are bad pixels in the target LCD screen, indicating that the target LCD screen is a defective product, and the detection result that the target LCD screen is a defective product is uploaded to the detection database; Furthermore, if one or more absolute difference values ​​in the absolute difference matrix are greater than the limit difference threshold, the element position nodes whose absolute difference values ​​are greater than the limit difference threshold are marked in the actual gradient value matrix as bad pixel positions, and the marked bad pixel positions are mapped in the screen characteristic image; All independent closed areas marked as bad pixel locations in the screen characteristic image are acquired to obtain one or more bad pixel location areas in the screen characteristic image.

4. The method for detecting bad pixels on a liquid crystal display according to claim 1, wherein: Based on the bad pixel feature knowledge tree graph network, the feature analysis of each sub-feature image is performed to obtain the bad pixel names and bad pixel causes of all bad pixel location areas in the target LCD screen, specifically: Obtain the bad pixel feature images corresponding to various types of bad pixels in the LCD screen through the big data network, and obtain the bad pixel inducements of various types of bad pixels; Constructing a knowledge tree graph network, treating each type of bad pixel in the LCD screen as a cutting node, cutting out a plurality of branch nodes in the knowledge tree graph network according to each cutting node, and assigning a corresponding bad pixel name label to each branch node according to the corresponding type of bad pixel; The bad pixel feature images and bad pixel inducements of various types of bad pixels in the LCD screen are mapped to corresponding branch nodes to obtain a bad pixel feature knowledge tree graph network; Obtaining a sub-characteristic image corresponding to a bad pixel location area in a target LCD screen, and importing the sub-characteristic image into the bad pixel feature knowledge tree graph network; Calculating image similarity between the sub-characteristic image and the bad pixel feature image to which each branch node in the bad pixel feature knowledge tree graph network belongs based on a perceptual hash algorithm; The calculated image similarities are used to mark the branch node with the greatest image similarity, and the corresponding bad pixel name and bad pixel inducement are extracted from the branch node with the greatest image similarity to obtain the bad pixel name and bad pixel inducement of the corresponding bad pixel location area in the target LCD screen; Repeat the above steps to obtain the bad pixel names and bad pixel causes of all bad pixel locations in the target LCD screen.

5. The method for detecting bad pixels on a liquid crystal display according to claim 1, wherein: The following steps are also included: Acquiring test data of each LCD screen within a preset time period from a test database; wherein the test data includes the test results of each LCD screen, and the names and causes of bad pixels of LCD screens with unqualified test results; Obtaining a defective rate of LCD screens in a current production batch based on test data of each LCD screen within a preset time period, and determining whether the defective rate is greater than a preset defective rate threshold; If the defective rate is greater than a preset defective rate threshold, the required replenishment output of the current production batch of LCD screens is calculated based on the defective rate, supplementary warning information is generated based on the required replenishment output, and the supplementary warning information is sent to a preset terminal; At the same time, obtaining production performance parameter information of the production line producing the current production batch of LCD screens, and obtaining order information of the current production batch of LCD screens, and determining the delivery time node of the current production batch of LCD screens based on the order information; Obtaining production lines in the production workshop that are in an idle state before the delivery time node, and obtaining production performance parameter information of the production lines in the idle state; Analyze the attention score between the production performance parameter information of the production line producing the current batch of LCD screens and the production performance parameter information of the idle production line based on the local sensitive attention mechanism; Only idle production lines with attention scores greater than a preset score threshold are extracted and defined as available supplementary production lines; operation log information of each available supplementary production line is obtained, and the failure probability of each available supplementary production line is obtained based on the operation log information; An available supplementary production line with the smallest failure probability value is obtained as a recommended supplementary production line, and the recommended supplementary production line is sent to a preset terminal.

6. A method for detecting bad pixels on a liquid crystal display according to claim 5, characterized in that: The following steps are also included: If the defective product rate is greater than a preset defective product rate threshold, obtaining the cause of the bad pixels of the LCD screens whose detection results are defective within a preset time period; Perform statistical analysis on the causes of bad pixels of LCD screens that are unqualified products within a preset time period to obtain the occurrence frequency values ​​of various causes of bad pixels; Mark the bad pixel inducement whose occurrence frequency value is greater than the preset frequency threshold as a high-incidence bad pixel inducement, and mark the bad pixel inducement whose occurrence frequency value is not greater than the preset frequency threshold as a low-incidence bad pixel inducement; Obtaining process characteristic information of each process station in the production line, combining the process characteristic information of each process station and introducing a regression analysis algorithm to analyze the degree of influence of each process station in the production line on the cause of the high incidence of bad pixels; Acquiring various real-time process parameters of process stations whose impact is greater than a preset impact threshold based on the Internet of Things, and acquiring various preset process parameters of process stations whose impact is greater than a preset impact threshold; Calculating process parameter differences between various real-time process parameters of process stations whose influence levels are greater than a preset influence level threshold and preset process parameters; The real-time process parameters corresponding to process parameter differences greater than the preset differences are marked, and the marked real-time process parameters are corrected based on the corresponding process parameter differences.

7. A device for detecting bad pixels on a liquid crystal display, characterized in that: The LCD screen bad pixel detection device includes a memory and a processor, and the memory stores a LCD screen bad pixel detection method program. When the LCD screen bad pixel detection method program is executed by the processor, the steps of the LCD screen bad pixel detection method as described in any one of claims 1 to 6 are implemented.

8. A computer-readable storage medium, characterized in that The readable storage medium includes a liquid crystal display bad pixel detection method program, and when the liquid crystal display bad pixel detection method program is executed by a processor, the steps of the liquid crystal display bad pixel detection method according to any one of claims 1 to 6 are implemented.

Citation Information

Patent Citations

  • Method for detecting electric performance of lattice liquid crystal display screen

    CN103698909A

  • Method and system for detecting screen dead pixel based on camera

    CN105163114A

  • Large-size liquid crystal display screen defect detecting method based on machine vision

    CN108760767A

  • Turning flutter acceleration collection system and method based on machine vision

    CN110091217A

  • Liquid crystal screen edge broken line detection method based on gradient transformation

    CN112598652A

Cited By

  • Liquid crystal display dead pixel detection method and system

    CN119850610A

  • A method and system for detecting dead pixels of a liquid crystal display screen

    CN119850610B

  • Detection method for dense dead pixels of light-emitting display screen, electronic equipment and storage medium

    CN121904039A

  • Method for detecting dense bad points of light-emitting display screen, electronic device and storage medium

    CN121904039B