Method and system for analyzing abnormal image displayed by liquid crystal screen

Abstract

The invention discloses a liquid crystal display abnormal image analysis method and system, and belongs to the technical field of image recognition, and the method comprises the following steps: S1, obtaining an optimized display image of a liquid crystal display; s2, setting a first specification sliding window and a second specification sliding window to respectively perform sliding detection on the optimized display picture of the liquid crystal screen to obtain a pixel block abnormity judgment result, if the pixel block abnormity judgment result is qualified, counting qualified pixel blocks, and storing the qualified pixel blocks in a qualified image temporary storage area, if the abnormal judgment result of the pixel blocks is abnormal, counting abnormal pixel blocks and storing the abnormal pixel blocks in an abnormal image temporary storage area, and if the abnormal judgment result of the pixel blocks is conflict, carrying out conflict adjustment; and S3, obtaining each abnormal pixel clustering block and an abnormal parameter corresponding to each abnormal pixel clustering block, thereby obtaining a fault type of an abnormal image displayed by the liquid crystal screen, avoiding acquisition interference caused by improper parameters of image acquisition equipment, and solving the problem that defects are not easy to successfully detect due to image noise interference in the prior art.

Description

Technical Field

[0001] The present invention relates to the field of image recognition technology, and in particular to a method and system for analyzing abnormal images displayed on a liquid crystal screen. Background Art

[0002] Existing LCD display abnormality detection systems use image analysis combined with modeling and prediction to detect screen faults. They first identify candidate defect locations in the screen image. Then, using an autoregressive analysis model based on these candidate defect locations, they calculate the expected distribution of these locations. This expected distribution is then used to determine if the display fault point is present.

[0003] For example, the screen display fault detection method, device, equipment and storage medium disclosed in the Chinese invention patent with announcement number: CN119228713A include: determining the candidate defect locations of the screen image to be processed; determining the expected distribution of the candidate defect locations through a preset display fault detection model, and the preset display fault detection model is an autoregressive analysis model established with the candidate defect locations in the image as independent variables; and determining the display fault point of the screen displaying the screen image to be processed according to the expected distribution.

[0004] For example, a Chinese invention patent with publication number CN113379752B discloses an image segmentation method for a dual-layer LCD display. The method includes: first determining the physical resolution of the front and rear LCD screens and the resolution of the input image, and then selecting whether to upsample or downsample the input image. If the resolution of the input image is the same as the physical resolution of the front LCD screen, the input image is not processed. Subsequently, the grayscale values ​​of all pixels of the input image are arranged into a one-dimensional vector from top to bottom and from left to right, and a matrix Sθ with a viewing angle of θ is constructed to record the position of light passing through the front and rear LCD screens. Then, a one-dimensional vector X of the grayscale values ​​of all pixels on the front and rear LCD screens is constructed. All variables in vector X are initially assigned random values. The product of Sθ and X is calculated to obtain a one-dimensional vector Cθ. The LSQLIN operator is used to solve the variables in vector X. The variables in X are input into the dual-layer LCD screen to overlay and display the final image.

[0005] However, in the process of implementing the technical solutions of the invention in the embodiments of the present application, the present application found that the above technology has at least the following technical problems:

[0006] Existing technologies ignore noise interference factors in the image acquisition process, such as high-frequency stripe interference, isolated bright spots, and other interferences that may be generated by image acquisition equipment during imaging. However, these interferences will mask the true defect characteristics or misjudge non-defective areas as abnormal areas, seriously affecting the accuracy and stability of defect detection. Therefore, there is a problem that defects are difficult to detect successfully due to image noise interference. Summary of the Invention

[0007] In order to solve the technical problem that defects are not easy to be successfully detected due to image noise interference existing in the prior art, the embodiment of the present application provides a liquid crystal screen display abnormal image analysis method and system.

[0008] In one aspect, a liquid crystal screen display abnormal image analysis method is provided, which comprises the following steps: S1, obtaining a liquid crystal screen display picture through an image acquisition device, and performing picture optimization and adjustment to obtain a liquid crystal screen optimized display picture; S2, setting a first specification sliding window and a second specification sliding window to perform sliding detection on the liquid crystal screen optimized display picture to obtain a pixel block abnormality determination result, if the pixel block abnormality determination result is qualified, counting the qualified pixel blocks and storing them in a qualified image temporary storage area, if the pixel block abnormality determination result is abnormal, counting the abnormal pixel blocks and storing them in an abnormal image temporary storage area, and if the pixel block abnormality determination result is conflict, performing conflict adjustment; and S3, obtaining the abnormal pixel blocks in the abnormal image temporary storage area, and processing to obtain each abnormal pixel cluster block and the abnormal parameters corresponding to each abnormal pixel cluster block, thereby obtaining the fault type of the liquid crystal screen display abnormal image.

[0009] In another aspect, a liquid crystal screen display abnormal image analysis system is provided, which comprises a picture optimization and adjustment module, an abnormality determination module and a fault type analysis module; wherein the picture optimization and adjustment module is configured to obtain a liquid crystal screen display picture through an image acquisition device, and perform picture optimization and adjustment to obtain a liquid crystal screen optimized display picture; the abnormality determination module is configured to set a first specification sliding window and a second specification sliding window to perform sliding detection on the liquid crystal screen optimized display picture to obtain a pixel block abnormality determination result, if the pixel block abnormality determination result is qualified, count the qualified pixel blocks and store them in a qualified image temporary storage area, if the pixel block abnormality determination result is abnormal, count the abnormal pixel blocks and store them in an abnormal image temporary storage area, and if the pixel block abnormality determination result is conflict, perform conflict adjustment; and the fault type analysis module is configured to obtain the abnormal pixel blocks in the abnormal image temporary storage area, and process to obtain each abnormal pixel cluster block and the abnormal parameters corresponding to each abnormal pixel cluster block, thereby obtaining the fault type of the liquid crystal screen display abnormal image.

[0010] The technical scheme provided by the embodiment of the present application has at least the following beneficial effects:

[0011] 1. The liquid crystal screen display abnormal image analysis method provided by the present application obtains image acquisition interference influence parameters and analyzes them to dynamically adjust the image gain value, thereby obtaining a liquid crystal screen optimized display picture, and further avoiding image acquisition interference caused by improper setting of the parameters of the image acquisition device, and effectively solving the problem that defects are not easy to be successfully detected due to image noise interference in the prior art.

[0012] 2. The present invention performs multi-scale sliding detection on the LCD screen optimized display image by setting two sliding windows of different specifications, thereby obtaining different types of abnormal pixel blocks, thereby achieving accurate acquisition of pixel block abnormality judgment results, and avoiding the problem of abnormal omission or misjudgment caused by single window size detection.

[0013] 3. By merging connected areas of abnormal pixel blocks based on spatial connectivity clustering algorithm and obtaining abnormal parameters based on coordinate position analysis, accurate identification of abnormal pixel cluster blocks is achieved, effectively improving the accuracy of spatial positioning and feature extraction of abnormal areas.

[0014] 4. The present invention realizes intelligent identification of fault types by combining an LCD display abnormality model preset based on a database, abnormal pixel clustering blocks and corresponding abnormal parameters as input variables, thereby improving the fault diagnosis efficiency and accuracy of LCD abnormal images. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0016] Figure 1 A flowchart of a method for analyzing abnormal images displayed on a liquid crystal display provided in an embodiment of the present application;

[0017] Figure 2 A macroscopic determination flow chart of the method for analyzing abnormal images displayed on a liquid crystal display provided in an embodiment of the present application;

[0018] Figure 3 A flow chart of conflict adjustment for the method for analyzing abnormal images displayed on a liquid crystal display provided in an embodiment of the present application;

[0019] Figure 4 This is a first example diagram of image acquisition of the LCD display abnormality image analysis system provided by an embodiment of the present application;

[0020] Figure 5 A second example diagram of image acquisition of the LCD display abnormality image analysis system provided in an embodiment of the present application;

[0021] Figure 6 A first example diagram of pixel defect results of the LCD display abnormality image analysis system provided by an embodiment of the present application;

[0022] Figure 7 A partially enlarged image of the first example image of pixel defect results of the LCD display abnormality image analysis system provided by an embodiment of the present application;

[0023] Figure 8 A pixel defect result second example diagram of the liquid crystal screen display abnormal image analysis system provided by the embodiment of the present application;

[0024] Figure 9 A partial enlarged image of the pixel defect result second example diagram of the liquid crystal screen display abnormal image analysis system provided by the embodiment of the present application;

[0025] Figure 10 A structural schematic diagram of the liquid crystal screen display abnormal image analysis system provided by the embodiment of the present application. DETAILED DESCRIPTION

[0026] The technical solutions in the present application will be described below with reference to the drawings.

[0027] In the embodiments of the present application, the words such as "exemplary", "for example", etc. are used to represent an example, illustration or description. Any embodiment or design scheme described as "exemplary" in the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. In fact, the word "exemplary" is intended to present the concept in a specific manner. In addition, in the embodiments of the present application, the meaning expressed by "and / or" can be both, or can be one of the two optionally.

[0028] In the embodiments of the present application, "image" and "picture" can be used interchangeably at times. It should be pointed out that the meanings expressed are consistent when the distinction is not emphasized. The words "of", "corresponding" and "corresponding" can be used interchangeably at times. It should be pointed out that the meanings expressed are consistent when the distinction is not emphasized.

[0029] In the embodiments of the present application, sometimes the subscript such as W1 can be written in the form of non-subscript such as W1. The meanings expressed are consistent when the distinction is not emphasized.

[0030] In order to make the technical problems, technical solutions and advantages of the present application clearer, specific embodiments will be described in detail below with reference to the drawings.

[0031] As Figure 1As shown, it is a flow chart of the method for analyzing abnormal images displayed on a liquid crystal display provided by an embodiment of the present application, and the method includes the following steps: S1, obtaining a liquid crystal display image through an image acquisition device, and optimizing and adjusting the image to obtain an optimized display image of the liquid crystal display; S2, setting a first specification sliding window and a second specification sliding window to respectively perform sliding detection on the optimized display image of the liquid crystal display to obtain a pixel block abnormality determination result, if the pixel block abnormality determination result is qualified, then the qualified pixel blocks are counted and stored in a qualified image temporary storage area, if the pixel block abnormality determination result is abnormal, then the abnormal pixel blocks are counted and stored in an abnormal image temporary storage area, if the pixel block abnormality determination result is conflict, conflict adjustment is performed; S3, obtaining abnormal pixel blocks in the abnormal image temporary storage area, and processing to obtain each abnormal pixel cluster block and the abnormal parameters corresponding to each abnormal pixel cluster block, thereby obtaining the fault type of the abnormal image displayed on the liquid crystal display.

[0032] In this embodiment, if Figure 1 As shown, Figure 1 This is a flowchart of the method for analyzing abnormal images displayed on a liquid crystal display provided in an embodiment of the present application. At the beginning of the process, an LCD display image is collected and optimized and adjusted to obtain an optimized LCD display image; a sliding detection analysis is performed on the optimized LCD display image to determine its abnormality and obtain a pixel block abnormality determination result. The pixel block abnormality determination result is divided into qualified, abnormal and conflicting. Qualified pixel blocks are counted and stored in a qualified image temporary storage area, and abnormal pixel blocks are counted and stored in an abnormal image temporary storage area. If the pixel block abnormality determination result is a conflict, conflict adjustment is performed to obtain a pixel block abnormality determination result after conflict adjustment, including pixel block abnormality and pixel block qualified. At the same time, if the pixel block abnormality determination result is pixel block abnormality, the abnormal pixel block is stored in the abnormal image temporary storage area; if the pixel block abnormality determination result is pixel block qualified, the qualified pixel block is saved in the qualified image temporary storage area; the abnormal pixel blocks in the abnormal image temporary storage area are counted and analyzed to obtain each abnormal pixel cluster block and the abnormal parameters corresponding to each abnormal pixel cluster block. Therefore, each abnormal pixel cluster block and the abnormal parameters corresponding to each abnormal pixel cluster block are input into the LCD display abnormality model, and the specific fault type is output, completing the intelligent fault diagnosis and positioning of the LCD abnormal image.

[0033] The application improves the consistency of image quality and the pre-detection processing effect by introducing the comparison between the image acquisition device parameters and the ideal execution set, obtaining the image acquisition interference value and performing image gain adjustment; the precision of abnormal detection is effectively improved by setting a double-specification sliding window for image scanning, and combining the abnormal feature value with the preset threshold for pixel block level judgment; the abnormal pixel block is connected and merged by using the spatial connectivity clustering algorithm, and the abnormal parameters including length, width and area are extracted based on the position coordinate information of the clustering block, which provides a basis for subsequent fault type identification; the abnormal clustering block and its parameters are taken as input, and the specific fault type is output by combining the preset liquid crystal screen abnormal model, which realizes the structured expression and automatic classification and identification of the abnormal image of the liquid crystal screen display, and improves the accuracy, stability and intelligent level of the detection.

[0034] Further, an optimized display picture of the liquid crystal screen is obtained, and the specific method is as follows: an image acquisition interference parameter is obtained, the image acquisition interference parameter including the focal length, exposure time, frame rate and ISO sensitivity of the image acquisition device; a preset image acquisition ideal execution set in the database is obtained, and a difference degree analysis is performed on the image acquisition interference parameter, to obtain an image acquisition difference degree analysis result; a corresponding weighting factor is introduced based on the image acquisition difference degree analysis result for coupling processing, to obtain an image acquisition interference value; the image acquisition ideal execution set includes a focal length ideal execution value, an exposure time ideal execution value, a frame rate ideal execution value and an ISO sensitivity ideal execution value; the image acquisition interference value is matched with the database, to obtain an image gain adjustment execution coefficient, and the image gain value of the liquid crystal screen display picture is reduced and adjusted based on the image gain adjustment execution coefficient, thereby obtaining the optimized display picture of the liquid crystal screen.

[0035] In the embodiment, the focal length, exposure time, frame rate and ISO sensitivity of the image acquisition device can be obtained through the liquid crystal screen display detection background system, and the device parameters of the image acquisition device need to be uploaded to the liquid crystal screen display detection background system for unified storage after being set.

[0036] The image acquisition interference value is obtained, and the specific method is as follows:

[0037] ;

[0038] In the formula, TG represents an image acquisition interference value, TJ represents a focal length of the image acquisition device, GJ represents an ideal execution value of the focal length, TH represents an exposure time of the image acquisition device, GH represents an ideal execution value of the exposure time, TP represents a frame rate of the image acquisition device, GP represents an ideal execution value of the frame rate, TD represents an ISO sensitivity of the image acquisition device, and GD represents an ideal execution value of the ISO sensitivity. ω1 represents a focal length weighting factor, ω2 represents an exposure time weighting factor, ω3 represents a frame rate weighting factor, and ω4 represents an ISO sensitivity weighting factor.

[0039] The focal length weighting factor, the exposure time weighting factor, the frame rate weighting factor, and the ISO sensitivity weighting factor can be obtained from a database. For example, the focal length weighting factor can be obtained by analyzing a historical focal length set stored in the database. The difference between each historical focal length in the historical focal length set and the focal length of the image acquisition device is calculated to obtain each historical focal length difference. A preset focal length difference threshold interval in the database is obtained and compared with each historical focal length difference. If a certain historical focal length difference is within the focal length difference threshold interval, the historical focal length corresponding to the historical focal length difference is obtained and marked as a historical control focal length, thereby obtaining each historical control focal length. After removing the maximum and minimum values of each historical control focal length, the standard deviation is obtained to obtain the historical control focal length standard deviation. A preset historical reference focal length weighting factor, historical control focal length standard deviation reference, historical control standard deviation gradient, and focal length weighting factor single-level adjustment amount in the database are obtained. The historical control focal length standard deviation is calculated by subtracting the historical control focal length standard deviation reference value to obtain the historical control focal length standard deviation mean. The historical control focal length standard deviation mean is multiplied by the historical control standard deviation gradient to obtain the historical control gradient multiple. The historical control gradient multiple is multiplied by the focal length weighting factor single-level adjustment amount to obtain the focal length weighting factor comprehensive adjustment amount. The historical control focal length standard deviation is compared with the historical control focal length standard deviation reference value. If the historical control focal length standard deviation is greater than the historical control focal length standard deviation reference value, the historical reference focal length weighting factor is added to the focal length weighting factor comprehensive adjustment amount to obtain the focal length weighting factor. Otherwise, the historical reference focal length weighting factor is subtracted from the focal length weighting factor comprehensive adjustment amount to obtain the focal length weighting factor. The other weighting factors are obtained in the same way as the focal length weighting factor. The exposure time weighting factor corresponds to the historical control exposure time standard deviation mean, the frame rate weighting factor corresponds to the historical control frame rate standard deviation mean, and the ISO sensitivity weighting factor corresponds to the historical control ISO sensitivity standard deviation mean.

[0040] By analyzing the image acquisition interference influence parameters including the focal length, exposure time, frame rate and ISO sensitivity of the image acquisition device, the mutual influence relationship between these parameters is considered, for example: the focal length, exposure time, frame rate and ISO sensitivity in the image acquisition device are mutually restricted, cooperatively affect the imaging quality in the imaging process. The focal length determines the imaging magnification and field of view, indirectly affects the light amount; the exposure time controls the time of receiving light per frame, the longer the time, the more light is introduced, but it is also more prone to motion blur; the frame rate improvement means that more frames are collected per unit time, the single frame exposure time needs to be shortened, thereby reducing the light amount; the ISO sensitivity is used to make up for the lack of light, the higher the value, the more sensitive to light, which will amplify the image noise.

[0041] By obtaining the focal length, exposure time, frame rate and ISO sensitivity and other interference influence parameters of the image acquisition device, and analyzing the difference degree with the ideal execution value preset in the database, the interference influence caused by the fluctuation of device parameters in the image acquisition process is quantitatively evaluated, which effectively avoids the problems such as brightness drift, color shift, detail blur and image noise caused by improper setting of the image acquisition device, especially the phenomena such as stripe interference, overexposure or underexposure, motion blur, which will directly affect the accuracy and stability of subsequent defect detection. If the interference factors of the image acquisition device are not evaluated and optimized, the quality of the collected image is uncertain, which will lead to an increase in error of abnormal detection results, an increase in missed detection rate, and an impact on the accurate identification of liquid crystal display defects. Therefore, by introducing the image acquisition interference value and obtaining the image gain adjustment execution coefficient, the dynamic adjustment of the image gain can be realized, and the accuracy and correctness of the liquid crystal display image abnormal identification are improved.

[0042] Further, a pixel block abnormality determination result is obtained. Specifically, a first specification sliding window and a second specification sliding window are set, the first specification sliding window is larger than the second specification sliding window; the liquid crystal screen optimized display picture is detected by sliding based on the first specification sliding window and a first preset step, and each time the pixel block obtained by sliding detection is jointly marked as a first specification unit, thereby obtaining each first specification unit; the liquid crystal screen optimized display picture is detected by sliding based on the second specification sliding window and a second preset step, and each time the pixel block obtained by sliding detection is jointly marked as a second specification unit, thereby obtaining each second specification unit; an abnormal feature parameter is obtained, and an abnormal feature value is obtained by analysis, the abnormal feature value including a first abnormal feature value of each first specification unit and a second abnormal feature value of each second specification unit; a preset abnormal feature threshold value in a database is obtained, the first abnormal feature value of each first specification unit is compared with the abnormal feature threshold value, and a first specification unit abnormality determination result is obtained, the second abnormal feature value of each second specification unit is compared with the abnormal feature threshold value, and a second specification unit abnormality determination result is obtained; and the pixel block abnormality determination result is obtained based on the first specification unit abnormality determination result and the second specification unit abnormality determination result.

[0043] In the embodiment, the first specification sliding window and the second specification sliding window each include a plurality of pixel blocks, wherein the pixel block refers to the smallest pixel unit. The first specification sliding window (for example, 16x16 pixel blocks) and the second specification sliding window (for example, 16x4 pixel blocks) are set, wherein the width of the first specification sliding window is consistent with the width of the second specification sliding window.

[0044] The first abnormal feature value of each first specification unit is compared with the abnormal feature threshold value, and a first specification unit abnormality determination result is obtained. Specifically, the first abnormal feature value of each first specification unit is compared with the abnormal feature threshold value, if the first abnormal feature value of a certain first specification unit is above the abnormal feature threshold value, the first specification unit abnormality determination result is abnormal, otherwise, the first specification unit abnormality determination result is normal.

[0045] The second abnormal feature value of each second specification unit is compared with the abnormal feature threshold value, and a second specification unit abnormality determination result is obtained. Specifically, the second abnormal feature value of each second specification unit is compared with the abnormal feature threshold value, if the second abnormal feature value of a certain second specification unit is above the abnormal feature threshold value, the second specification unit abnormality determination result is abnormal, otherwise, the second specification unit abnormality determination result is normal.

[0046] The first specification sliding window and the second specification sliding window are adopted to slide and detect the optimized display picture of the liquid crystal screen, mainly to consider the overall recognition of large range abnormal features and the fine detection of small range details in the image analysis process. The first specification sliding window can effectively cover a wider area due to its larger size, which is helpful to recognize large scale display abnormalities such as bright band, dark band, whole block brightness deviation or color deviation; and the second specification sliding window is more suitable for detecting fine grain defects such as bad points, fine bright spots and edge breakage due to its smaller size and higher local resolution. The comprehensive and sensitivity of the detection can be improved by setting two sliding windows with different specifications and combining their respective step lengths for sliding detection, rather than using a fixed window, so as to reduce the abnormal detection blind area or omission phenomenon caused by single window size, and ensure the accurate coverage of defects with different sizes and different forms.

[0047] Further, the abnormal feature value is obtained by: obtaining an abnormal feature parameter, the abnormal feature parameter including a brightness mean value, a brightness standard deviation, a color channel deviation mean value and an edge intensity mean value; obtaining a preset abnormal feature standard set in a database, and performing difference degree analysis on the abnormal feature parameter to obtain an abnormal feature difference degree analysis result, and introducing a corresponding weighting factor based on the abnormal feature difference degree analysis result for coupling processing to obtain the abnormal feature value; the abnormal feature standard set includes a brightness standard value, a brightness standard deviation allowable value, a color channel deviation allowable value and an edge intensity standard value.

[0048] In the embodiment, the abnormal feature parameter is obtained, and the abnormal feature value is analyzed to obtain the first abnormal feature value of each first specification unit and the second abnormal feature value of each second specification unit. The abnormal feature parameter includes a brightness mean value, a brightness standard deviation, a color channel deviation mean value and an edge intensity mean value.

[0049] The brightness mean value is the mean value of the difference between the brightness of each pixel block in the specification unit (such as the first specification unit) and the brightness standard value. The brightness standard deviation is the standard deviation of the brightness of the pixel blocks in the specification unit (such as the first specification unit). The color channel deviation mean value is the mean value of the difference between the color channel of the pixel blocks in the specification unit (such as the first specification unit) and the color channel deviation allowable value. The edge intensity mean value is the mean value of the edge intensity of the pixel blocks in the specification unit (such as the first specification unit).

[0050] The abnormal feature value is obtained by:

[0051] ;

[0052] In the formula, YCi represents an abnormal characteristic value, i represents the number of a specification unit, i = 1, 2, wherein i = 1 represents a first abnormal characteristic value of a first specification unit, i = 2 represents a second abnormal characteristic value of a second specification unit, YLi represents a brightness average value of the i-th specification unit, CL represents a brightness standard value, YBi represents a brightness standard deviation of the i-th specification unit, CB represents a brightness standard deviation allowable value of the i-th specification unit, r represents a constant, YTi represents a color channel deviation average value of the i-th specification unit, CT represents a color channel deviation allowable value, YQi represents an edge intensity average value of the i-th specification unit, CQ represents an edge intensity standard value, φ1 represents a brightness average value weighting factor, φ2 represents a brightness standard deviation weighting factor, φ3 represents a color channel deviation average value weighting factor, and φ4 represents an edge intensity average value weighting factor.

[0053] It should be noted that r represents a very small constant, in order to avoid computer calculation errors when the brightness standard deviation allowable value is zero.

[0054] The brightness mean weighting factor, the brightness standard deviation weighting factor, the color channel deviation mean weighting factor, and the edge intensity mean weighting factor can be obtained from a database. For example, the brightness mean weighting factor can be obtained by analyzing a set of historical brightness means stored in the database. The difference between each historical brightness mean in the set and the brightness mean of the image capture device is calculated. A predetermined threshold interval for the brightness mean difference is obtained from the database and compared with the historical brightness mean differences. If a historical brightness mean difference falls within the threshold interval, the historical brightness mean corresponding to the historical brightness mean difference is obtained and marked as a historical reference brightness mean. In this way, a set of historical reference brightness means is obtained. The standard deviation of the historical reference brightness means after removing the maximum and minimum values is calculated to obtain the historical reference brightness mean standard deviation. A historical reference brightness mean weighting factor, a historical reference brightness mean standard deviation reference value, a historical reference standard deviation gradient, and a single-level adjustment amount for the brightness mean weighting factor are obtained from the database. The difference between the historical reference brightness mean standard deviation and the historical reference brightness mean standard deviation reference value is calculated to obtain a historical reference brightness mean standard deviation mean. The historical reference brightness mean standard deviation mean is multiplied by the historical reference standard deviation gradient to obtain a historical reference gradient multiple. The historical reference gradient multiple is multiplied by the single-level adjustment amount for the brightness mean weighting factor to obtain a comprehensive adjustment amount for the brightness mean weighting factor. The historical reference brightness mean standard deviation is compared with the historical reference brightness mean standard deviation reference value. If the historical reference brightness mean standard deviation is greater than the historical reference brightness mean standard deviation reference value, the historical reference brightness mean weighting factor is added to the comprehensive adjustment amount for the brightness mean weighting factor to obtain the brightness mean weighting factor. Otherwise, the historical reference brightness mean weighting factor is subtracted from the comprehensive adjustment amount for the brightness mean weighting factor to obtain the brightness mean weighting factor.

[0055] By analyzing the abnormal feature parameters including brightness mean value, brightness standard deviation, color channel deviation mean value and edge intensity mean value, the abnormal feature values are obtained considering the mutual influence relationship between these parameters. For example, the brightness mean value determines the overall light and dark level of the image, and the value change will directly affect the fluctuation degree of the brightness standard deviation. For example, when the brightness is too low, the overall image is dark, the brightness standard deviation tends to be small, and the brightness distribution is uneven, and the image is dark. When the brightness is too high, the brightness standard deviation increases, and overexposure or local bright spots are generated. The color channel deviation mean value reflects the difference in brightness of each RGB channel. If a channel is too strong, it will cause the brightness mean value to deviate, and at the same time cause local color deviation, further causing edge information distortion, thereby affecting the accuracy of the edge intensity mean value. The edge intensity mean value depends on the brightness gradient change and color contrast. When the brightness standard deviation is too small or the color deviation is not obvious, the edge contour is blurred and the edge intensity is weakened. On the contrary, when the brightness and color contrast are enhanced, the edge intensity rises, but if the contrast is too large, it will also amplify image noise, leading to misjudgment.

[0056] Further, the pixel block abnormality determination result is obtained, specifically including: obtaining the pixel block corresponding to each first specification unit, if there is a pixel block in different first specification units, and the multiple first specification unit abnormality determination results corresponding to the pixel block show inconsistency, then the first specification unit abnormality determination result of the pixel block is the abnormality determination result obtained by the first sliding detection of the pixel block; obtaining the pixel block corresponding to each second specification unit, if there is a pixel block in different second specification units, and the multiple second specification unit abnormality determination results corresponding to the pixel block show inconsistency, then the second specification unit abnormality determination result of the pixel block is the abnormality determination result obtained by the first sliding detection of the pixel block; counting the pixel block and the first specification unit abnormality determination result and the second specification unit abnormality determination result corresponding to the pixel block in the liquid crystal screen optimized display picture, if there is a pixel block in the first specification unit abnormality determination result and the second specification unit abnormality determination result, the first specification unit abnormality determination result is normal and the second specification unit abnormality determination result is normal, then the pixel block abnormality determination result of the pixel block is qualified; if there is a pixel block in the first specification unit abnormality determination result and the second specification unit abnormality determination result, the first specification unit abnormality determination result is abnormal and the second specification unit abnormality determination result is abnormal, then the pixel block abnormality determination result of the pixel block is abnormal; if there is a pixel block in the first specification unit abnormality determination result and the second specification unit abnormality determination result, the first specification unit abnormality determination result and the second specification unit abnormality determination result show inconsistency, then the pixel block abnormality determination result of the pixel block is conflict.

[0057] In this embodiment, image detection is performed using a sliding window approach. Due to the sliding nature of the detection process, a pixel block is often repeatedly covered by multiple sliding windows at different positions. This is particularly true when the step size of the first or second specification windows is small, as a pixel block may belong to multiple adjacent specification units. This overlap can result in different abnormality determination results for the same pixel block in different specification units, leading to inconsistent abnormality states. To prevent instability or interference with the overall determination caused by subsequent detection results, the determination result obtained from the first sliding detection is used as the standard. This ensures the traceability and logical consistency of the determination results and avoids fluctuations introduced by changes in the detection sequence.

[0058] To ensure the accuracy of the final pixel block anomaly determination results, this solution introduces a dual-scale determination mechanism, which requires simultaneously counting the anomaly determination results of each pixel block in both the first and second scale units. By cross-validating the determination results at two scales, the coverage of both macro anomalies and local detail anomalies can be maximized, improving the robustness of the overall determination. Only when both scales are normal can the pixel block be considered fully qualified; only when both scales are abnormal can the pixel block be confirmed to be significantly abnormal and have sufficient confidence. When the determination results of the two scale windows are inconsistent, it indicates that the abnormal features of the pixel block have edge fuzziness or scale sensitivity. If a conclusion is drawn directly at this time, it may be misjudged due to interference from factors such as the sliding window coverage edge and image feature changes. Therefore, it is set to a "conflict" state and enters the subsequent conflict adjustment process. The determination accuracy can be further improved through differentiated parameter analysis and adjustment, avoiding judgment deviations caused by differences in sliding window positions.

[0059] Further, conflict adjustment is performed. Specifically, if the pixel block abnormality determination result is conflict, the pixel block abnormality determination result is conflict is marked as a conflict pixel block, and the first specification unit abnormality determination result and the second specification unit abnormality determination result corresponding to the conflict pixel block are obtained. If the first specification unit abnormality determination result is abnormal and the second specification unit abnormality determination result is normal, the conflict pixel block is marked as a first specification problem pixel block, otherwise, it is marked as a second specification problem pixel block. A first adjustment coefficient is obtained by matching the first abnormality characteristic value of the first specification problem pixel block. The gamma correction value and the color temperature white balance adjustment coefficient of the first specification problem pixel block are reduced based on the first adjustment coefficient to obtain an optimized adjustment first abnormality characteristic value. The pixel block abnormality determination result is obtained by comparing the optimized adjustment first abnormality characteristic value with the abnormality characteristic threshold. A second adjustment coefficient is obtained by matching the second abnormality characteristic value of the second specification problem pixel block. The local contrast and the blue channel gain value of the second specification problem pixel block are increased based on the second adjustment coefficient to obtain an optimized adjustment second abnormality characteristic value. The pixel block abnormality determination result is obtained by comparing the optimized adjustment second abnormality characteristic value with the abnormality characteristic threshold. If the pixel block abnormality determination result is a qualified pixel block, the pixel block is stored in the qualified image temporary storage area. If the pixel block abnormality determination result is a pixel block abnormality, the pixel block is stored in the abnormal image temporary storage area.

[0060] In the embodiment, as shown in Figure 3 Figure 3 The conflict adjustment flowchart of the liquid crystal screen display abnormal image analysis method provided by the embodiment is shown. After receiving the conflict adjustment signal, the first specification unit abnormality determination result and the second specification unit abnormality determination result corresponding to the conflict pixel block are obtained. If the first specification unit abnormality determination result is abnormal and the second specification unit abnormality determination result is normal, the conflict pixel block is marked as a first specification problem pixel block. If the first specification unit abnormality determination result is normal and the second specification unit abnormality determination result is abnormal, the conflict pixel block is marked as a second specification problem pixel block. The first adjustment coefficient is obtained by analyzing the first specification problem pixel block. The gamma correction value and the color temperature white balance adjustment coefficient of the first specification problem pixel block are reduced based on the first adjustment coefficient to obtain the pixel block abnormality determination result. The second adjustment coefficient is obtained by analyzing the second specification problem pixel block. The local contrast and the blue channel gain value of the second specification problem pixel block are increased based on the second adjustment coefficient to obtain the pixel block abnormality determination result. If the pixel block abnormality determination result is a qualified pixel block, the pixel block is stored in the qualified image temporary storage area. If the pixel block abnormality determination result is a pixel block abnormality, the pixel block is stored in the abnormal image temporary storage area.

[0061] ​The gamma correction value and the color temperature white balance adjustment coefficient of the first specification problem pixel block are reduced based on a first adjustment coefficient, and the specific method is as follows: ; wherein γ1 represents the reduced and adjusted gamma correction value of the first specification problem pixel block, γ0 represents the gamma correction value of the first specification problem pixel block, and r1 represents the first adjustment coefficient. ; wherein X1 represents the reduced and adjusted color temperature white balance adjustment coefficient of the first specification problem pixel block, X0 represents the color temperature white balance adjustment coefficient of the first specification problem pixel block, and r1 represents the first adjustment coefficient.

[0062] The first abnormal feature value is optimized and adjusted, and the specific method is as follows: the liquid crystal screen optimized display picture after the gamma correction value and the color temperature white balance adjustment coefficient of the first specification problem pixel block are reduced and adjusted is subjected to abnormal feature value again to obtain the first abnormal feature value that is optimized and adjusted.

[0063] The pixel block abnormality determination result is obtained by comparing the first abnormal feature value that is optimized and adjusted with an abnormal feature threshold value, and the specific method is as follows: the first abnormal feature value that is optimized and adjusted is compared with the abnormal feature threshold value, if the first abnormal feature value that is optimized and adjusted is above the abnormal feature threshold value, the pixel block abnormality determination result is pixel block abnormality, otherwise, the pixel block abnormality determination result is pixel block qualification.

[0064] The second adjustment coefficient is matched based on the second abnormal feature value of the second specification problem pixel block, and the specific method is as follows: the second abnormal feature values of each sample pixel block in the database and the historical second adjustment coefficients of each sample pixel block are obtained; the second abnormal feature difference values between the second specification problem pixel block and each sample pixel block are counted; the preset sample second abnormal feature difference interval in the database is obtained and compared, if the second abnormal feature difference value between the second specification problem pixel block and a certain sample pixel block is within the sample second abnormal feature difference interval, the sample pixel block is obtained as a reference sample pixel block; the historical second adjustment coefficients of each reference sample pixel block are counted and processed by mean value to obtain the historical second adjustment coefficient mean value, which is taken as the second adjustment coefficient.

[0065] The local contrast and the blue channel gain value of the second specification problem pixel block are increased based on the second adjustment coefficient, and the specific method is as follows: ; wherein W1 represents the increased and adjusted local contrast of the second specification problem pixel block, W0 represents the local contrast of the second specification problem pixel block, and r2 represents the second adjustment coefficient. ; wherein L1 represents the increased and adjusted blue channel gain value of the second specification problem pixel block, L0 represents the blue channel gain value of the second specification problem pixel block, and r2 represents the second adjustment coefficient.

[0066] The second abnormal characteristic value after optimization adjustment is obtained by performing abnormal characteristic value on the liquid crystal screen optimization display picture after increasing the local contrast and the blue channel gain value of the second specification problem pixel block.

[0067] The pixel block abnormality determination result is obtained by comparing the first abnormal characteristic value after optimization adjustment with the abnormal characteristic threshold value. Specifically, the first abnormal characteristic value after optimization adjustment is compared with the abnormal characteristic threshold value. If the first abnormal characteristic value after optimization adjustment is above the abnormal characteristic threshold value, the pixel block abnormality determination result is pixel block abnormality. Otherwise, the pixel block abnormality determination result is pixel block qualified.

[0068] The first specification problem pixel block (large sliding block) corresponds to a reduced gamma correction value, which is to reduce the over-bright area (such as bright spots, backlight spots, etc.) in the display of the liquid crystal screen, weaken the over-enhancement effect of the high-light area on the image edge, suppress the image "flicker pseudo-defect" caused by high-light sensitive response, and reduce the interference such as stripes and noise caused by camera shooting, thereby reducing the overall pseudo-abnormal risk of the sliding block and reducing the color temperature white balance adjustment coefficient. Because the large window detection covers a wide range and is easily affected by the environment cold light source or the display screen color deviation, reducing the white balance color temperature can effectively weaken the blue deviation and red deviation under the guidance of cold light, reduce the color spot misjudgment caused by illumination or electromagnetic interference, and improve the color consistency judgment accuracy.

[0069] The second specification problem pixel block (small sliding block) corresponds to an increased local contrast, because the small window focuses on details, and the contrast is too low, which is easy to miss small defects. Enhancing the local contrast can highlight the feature texture in the low-light area of the image, improve the detection sensitivity, and prevent small defects at the pixel level (such as micro-bright spots and dot-shaped dark spots) from being hidden or blurred by the background. Increasing the blue channel gain value is because the small sliding window is easy to ignore the cold color defects (such as cold leakage and backlight edge defects) in low light or cold color environment, and appropriately enhancing the blue channel response is helpful to restore the detail performance and compensate for the local color distortion caused by white balance deviation, thereby improving the abnormal identification ability in cold color background.

[0070] In the pixel block abnormality determination result analysis, there are only two cases of pixel block qualified and pixel block abnormal after conflict adjustment, which is because the image features after adjustment will be closer to the real image performance, and under the premise that the original interference factors are effectively weakened or eliminated, the comparison with the abnormal characteristic threshold value can realize more stable and accurate classification and determination. Therefore, the adjustment result only exists in two clear states of "pixel block qualified" and "pixel block abnormal", which is because the interference factors have been effectively alleviated.

[0071] AsFigure 4 、 Figure 5 as shown in FIG. 1, Figure 4 FIG. 1 is a first example diagram of image acquisition of a liquid crystal screen display abnormal image analysis system provided by an embodiment of the present application, Figure 5 FIG. 2 is a second example diagram of image acquisition of a liquid crystal screen display abnormal image analysis system provided by an embodiment of the present application, from which the device connection state parameters can be viewed, and the liquid crystal screen display images under different test conditions can be acquired.

[0072] Further, the first adjustment coefficient is obtained, and the specific method is as follows: the first abnormal feature value of each sample pixel block in the database and the historical first adjustment coefficient of each sample pixel block are acquired; the first abnormal feature difference value between the first specification problem pixel block and each sample pixel block is counted; the preset sample first abnormal feature difference value interval in the database is acquired and compared, if the first abnormal feature difference value between the first specification problem pixel block and a certain sample pixel block is within the sample first abnormal feature difference value interval, the sample pixel block is acquired as a reference sample pixel block; the historical first adjustment coefficients of each reference sample pixel block are counted and processed by mean value to obtain the historical first adjustment coefficient mean value, which is taken as the first adjustment coefficient.

[0073] In the embodiment, the first abnormal feature value of the current first specification problem pixel block is compared by difference with the sample pixel block feature values accumulated in the database, and the reference samples with similar features are selected within the preset difference interval, so that the historical first adjustment coefficients of these reference samples are calculated by mean value, which can effectively realize the experience transfer and dynamic adaptation of the adjustment strategy, focus on the actual adjustment experience of similar historical samples, extract reusable adjustment rules, and thus realize more stable, fine and higher matching image parameter optimization processing. Especially in the processing of complex pseudo-defect scenes caused by camera interference, environmental light change, screen brightness fluctuation, etc., the stability and response speed of the system in dealing with nonlinear interference characteristics and local feature blur problems can be improved.

[0074] Further, each abnormal pixel clustering block and the abnormal parameters corresponding to each abnormal pixel clustering block are obtained, and the specific method is as follows: the abnormal pixel blocks in the abnormal image temporary storage area are acquired, and a clustering algorithm based on spatial connectivity is used to merge the abnormal pixel blocks to obtain each abnormal pixel clustering block; a coordinate system is established based on the preset position of the liquid crystal screen optimization display picture as the origin and the plane on which the liquid crystal screen optimization display picture is located as the coordinate plane to obtain the coordinate position of each abnormal pixel clustering block; the abnormal parameters corresponding to each abnormal pixel clustering block are analyzed based on the coordinate position of each abnormal pixel clustering block, and the abnormal parameters corresponding to each abnormal pixel clustering block include the maximum abnormal length, the maximum abnormal width and the abnormal area.

[0075] In this embodiment, the abnormal pixel blocks are merged into connected regions by using a clustering algorithm based on spatial connectivity. Specifically, a clustering algorithm based on spatial connectivity (such as a connected region marking algorithm) is used to gather abnormal pixels that are connected or close in position into a "cluster block" according to certain adjacency rules (for example, 4-adjacency), thereby obtaining each abnormal pixel cluster block. The analysis of each abnormal pixel cluster block is to merge "discrete abnormal pixel blocks" into "continuous abnormal regions" according to their relative positions in the image space.

[0076] The preset position of the liquid crystal screen optimized display picture is the origin, and the coordinate system is established based on the plane of the liquid crystal screen optimized display picture as the coordinate plane to obtain the coordinate position of each abnormal pixel cluster block. Specifically, the liquid crystal screen optimized display picture is defined as a two-dimensional plane (for example, the upper left corner is the origin), and the liquid crystal screen optimized display picture is a rectangle. Therefore, the straight line where the length and width of the liquid crystal screen optimized display picture are located can be used as the horizontal and vertical coordinates of the coordinate system, so that the coordinates of each pixel can be represented as (x, y). After the connected region merging is completed, the abnormal parameters of each abnormal pixel cluster block can be obtained, wherein the maximum abnormal length refers to the maximum horizontal length of the abnormal pixel cluster block, and the maximum abnormal width refers to the maximum vertical length of the abnormal pixel cluster block.

[0077] By introducing a clustering algorithm based on spatial connectivity to merge the connected regions of abnormal pixel blocks, the abnormal regions with spatial continuity and correlation can be effectively classified into unified cluster blocks, thereby improving the accuracy and integrity of abnormal positioning. At the same time, a two-dimensional coordinate system based on the plane of the liquid crystal screen is established, so that each abnormal cluster block has a clear position identifier, which provides a geometric basis for subsequent fault type identification and positioning analysis. By extracting parameters such as maximum abnormal length, maximum abnormal width, and abnormal area, the spatial range and morphological features of each cluster block can be quantified, which helps to identify specific fault types such as bright spots, dark lines, and stripe interference.

[0078] As shown in Figure 6 , Figure 7 , Figure 8 , Figure 9 , Figure 6 , Figure 7 are pixel defect result example diagrams of the liquid crystal screen display abnormal image analysis system provided by the embodiments of the present application, wherein Figure 6 shows a dark spot defect in the pixel defect fault type, Figure 7 is an enlarged view of the dark spot defect, Figure 8 shows a dark line defect in the pixel defect fault type, Figure 9 is an enlarged view of the dark line defect. From the diagrams, the approximate position of the liquid crystal screen fault and the cause of the fault can be seen.

[0079] Further, the fault type of the liquid crystal screen display abnormal image is obtained, and the specific method is as follows: a preset liquid crystal screen display abnormal model in the database is obtained; each abnormal pixel clustering block and the abnormal parameters corresponding to each abnormal pixel clustering block are input into the liquid crystal screen display abnormal model as input variables, and thus the fault type of the liquid crystal screen display abnormal image is output.

[0080] In the embodiment, the liquid crystal screen display abnormal model refers to a model constructed by a machine learning modeling method and used for identifying the abnormal type of the liquid crystal screen. The modeling process includes the following steps. First, a large number of liquid crystal screen display abnormal image samples of known fault types are collected, and each image is labeled with a specific abnormal type (such as bright spot, dark line, color deviation, bright line, etc.). Then, the image data is standardized, including size scaling, color normalization, noise removal, and other preprocessing steps. A CNN structure suitable for image classification tasks (such as ResNet, VGG, etc.) is selected, and the image and its labeled data are input into the model for supervised training. In the training process, the model parameters are continuously adjusted by optimizing the cross-entropy loss function, so that the model has the ability to identify different types of liquid crystal screen display abnormalities. Finally, the model performance is evaluated on the validation set and optimized, and finally a stable liquid crystal screen display abnormal model is obtained, which realizes the automatic identification of the abnormal type in the actual detection image. The core purpose of the liquid crystal screen display abnormal model is to automatically judge the specific fault type of the abnormality according to the input abnormal region features (such as size, shape, position, etc.), and to realize the closed-loop analysis from image abnormality to fault attribution.

[0081] By calling the preset liquid crystal screen display abnormal model in the database and combining each abnormal pixel clustering block and its corresponding abnormal parameters as input, the precise fault type identification of the liquid crystal screen display abnormal image is realized, which can effectively integrate the spatial clustering features and quantitative abnormal parameters, improve the automation and accuracy of fault diagnosis, and avoid errors caused by manual subjective judgment.

[0082] For example, Figure 10As shown, the structure schematic diagram of the liquid crystal screen display abnormal image analysis system provided by the embodiment of the present application, the liquid crystal screen display abnormal image analysis system provided by the embodiment of the present application comprises: a picture optimization adjustment module, an abnormality determination module and a fault type analysis module; wherein the picture optimization adjustment module is used for acquiring the liquid crystal screen display picture through an image acquisition device, and performing picture optimization adjustment to obtain the liquid crystal screen optimized display picture; the abnormality determination module is used for setting a first specification sliding window and a second specification sliding window to respectively perform sliding detection on the liquid crystal screen optimized display picture, to obtain a pixel block abnormality determination result, if the pixel block abnormality determination result is qualified, then the qualified pixel blocks are counted and stored in a qualified image temporary storage area, if the pixel block abnormality determination result is abnormal, then the abnormal pixel blocks are counted and stored in an abnormal image temporary storage area, and if the pixel block abnormality determination result is conflict, then conflict adjustment is performed; the fault type analysis module is used for acquiring the abnormal pixel blocks in the abnormal image temporary storage area, and processing to obtain each abnormal pixel clustering block and the abnormal parameters corresponding to each abnormal pixel clustering block, so as to obtain the fault type of the liquid crystal screen display abnormal image.

[0083] In summary, the embodiment acquires the image acquisition interference influence parameters and analyzes, thereby dynamically adjusting the image gain value, obtaining the liquid crystal screen optimized display picture, and further avoiding the image acquisition interference caused by improper parameter setting of the image acquisition device, and effectively solving the problem that the defects are not easy to be successfully detected due to image noise interference in the prior art.

[0084] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program codes.

[0085] The present application is described with reference to flowcharts and / or block diagrams of the method, device (system) and computer program product according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 The function specified in one flow or multiple flows and / or blocks Figure 1 The device for implementing the function specified in one block or multiple blocks.

[0086] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0087] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0088] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0089] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A method for analyzing abnormal images displayed on a liquid crystal display, characterized in that: The following steps are involved: S1. Obtaining a picture displayed on a liquid crystal screen through an image acquisition device, and optimizing and adjusting the picture to obtain an optimized picture displayed on the liquid crystal screen; S2. Setting a first-specification sliding window and a second-specification sliding window to perform sliding detection on the LCD optimized display image, respectively, to obtain pixel block abnormality determination results. If the pixel block abnormality determination result is qualified, the qualified pixel blocks are counted and stored in a qualified image temporary storage area. If the pixel block abnormality determination result is abnormal, the abnormal pixel blocks are counted and stored in an abnormal image temporary storage area. If the pixel block abnormality determination result is conflict, conflict adjustment is performed. S3. Acquire abnormal pixel blocks in the abnormal image temporary storage area, and process to obtain abnormal pixel cluster blocks and abnormal parameters corresponding to each abnormal pixel cluster block, thereby obtaining the fault type of the LCD screen displaying the abnormal image.

2. The method for analyzing abnormal images displayed on a liquid crystal display according to claim 1, wherein: The specific method for obtaining the optimized display image on the LCD screen is as follows: Obtaining image acquisition interference influencing parameters, wherein the image acquisition interference influencing parameters include focal length, exposure time, frame rate, and ISO sensitivity of the image acquisition device; Obtain the preset ideal execution set of image acquisition in the database, and perform difference analysis on it with the image acquisition interference influencing parameters to obtain the image acquisition difference degree analysis result. Based on the image acquisition difference degree analysis result, introduce the corresponding empowerment factor for coupling processing to obtain the image acquisition interference value; The image acquisition ideal execution set includes an ideal execution value of focal length, an ideal execution value of exposure time, an ideal execution value of frame rate and an ideal execution value of ISO sensitivity; Based on the image acquisition interference value, the image gain adjustment execution coefficient is matched with the database, and the image gain value of the LCD display picture is reduced based on the image gain adjustment execution coefficient, thereby obtaining the LCD optimized display picture.

3. The method for analyzing abnormal images displayed on a liquid crystal display according to claim 1, wherein: The specific method for obtaining the pixel block abnormality determination result is as follows: Setting a first-size sliding window and a second-size sliding window, wherein the first-size sliding window is larger than the second-size sliding window; Performing sliding detection on the LCD screen optimized display image based on a first-specification sliding window according to a first preset step size, and jointly marking pixel blocks obtained from each sliding detection as first-specification units, thereby obtaining each first-specification unit; Performing sliding detection on the LCD optimized display image based on a second-specification sliding window according to a second preset step length, and jointly marking pixel blocks obtained from each sliding detection as second-specification units, thereby obtaining each second-specification unit; Acquire abnormal characteristic parameters and analyze to obtain abnormal characteristic values, wherein the abnormal characteristic values ​​include a first abnormal characteristic value of each first specification unit and a second abnormal characteristic value of each second specification unit; Obtaining an abnormal feature threshold preset in a database, comparing the first abnormal feature value of each first specification unit with the abnormal feature threshold to obtain an abnormality determination result for each first specification unit, and comparing the second abnormal feature value of each second specification unit with the abnormal feature threshold to obtain an abnormality determination result for each second specification unit; The pixel block abnormality determination result is obtained based on the analysis of each first specification unit abnormality determination result and each second specification unit abnormality determination result.

4. The method for analyzing abnormal images displayed on a liquid crystal display according to claim 3, wherein: The specific method for obtaining the abnormal characteristic value is as follows: Acquire abnormal characteristic parameters, wherein the abnormal characteristic parameters include brightness mean, brightness standard deviation, color channel deviation mean and edge intensity mean; Obtaining the abnormal feature standard set preset in the database, and performing difference degree analysis with the abnormal feature parameters to obtain the abnormal feature difference degree analysis results, and introducing the corresponding empowerment factor based on the abnormal feature difference degree analysis results for coupling processing to obtain the abnormal feature value; The abnormal feature standard set includes a brightness standard value, a brightness standard deviation allowable value, a color channel deviation allowable value and an edge intensity standard value.

5. The method for analyzing abnormal images displayed on a liquid crystal display according to claim 1, wherein: Obtaining the pixel block abnormality determination result specifically includes: Obtain pixel blocks corresponding to each first standard unit. If a pixel block is located in a different first standard unit and the abnormality determination results of each first standard unit corresponding to the pixel block are inconsistent, the first standard unit abnormality determination result of the pixel block is the abnormality determination result obtained by the first sliding detection of the pixel block. Obtain the pixel blocks corresponding to each second standard unit. If a pixel block is located in a different second standard unit and the abnormality determination results of each second standard unit corresponding to the pixel block are inconsistent, the abnormality determination result of the second standard unit for the pixel block is the abnormality determination result obtained by the first sliding detection of the pixel block; Counting pixel blocks in the LCD optimized display image and the first specification unit abnormality determination results and the second specification unit abnormality determination results corresponding to the pixel blocks; if the first specification unit abnormality determination result of a certain pixel block is normal and the second specification unit abnormality determination result is normal, the pixel block abnormality determination result of the pixel block is qualified; If the abnormality determination result of the first specification unit in which a certain pixel block is located is abnormal and the abnormality determination result of the second specification unit is abnormal, the abnormality determination result of the pixel block of the pixel block is abnormal; If the abnormality determination result of the first specification unit and the abnormality determination result of the second specification unit for a certain pixel block are inconsistent, the abnormality determination result of the pixel block is conflicting.

6. The method for analyzing abnormal images displayed on a liquid crystal display according to claim 1, wherein: The specific method for conflict adjustment is as follows: If the pixel block abnormality determination result is a conflict, the pixel block with the pixel block abnormality determination result as a conflict is marked as a conflict pixel block, and the first specification unit abnormality determination result and the second specification unit abnormality determination result corresponding to the conflict pixel block are obtained, wherein if the first specification unit abnormality determination result is abnormal and the second specification unit abnormality determination result is normal, the conflict pixel block is marked as a first specification problem pixel block, otherwise it is marked as a second specification problem pixel block; obtaining a first adjustment coefficient based on a first abnormal feature value of the first specification problem pixel block, reducing and adjusting a gamma correction value and a color temperature and white balance adjustment coefficient of the first specification problem pixel block based on the first adjustment coefficient to obtain an optimized and adjusted first abnormal feature value, and comparing the optimized and adjusted first abnormal feature value with an abnormal feature threshold to obtain a pixel block abnormality determination result; obtaining a second adjustment coefficient based on a second abnormal feature value matching of the second-specification problematic pixel block, increasing the local contrast and the blue channel gain value of the second-specification problematic pixel block based on the second adjustment coefficient to obtain an optimized and adjusted second abnormal feature value, and comparing the optimized and adjusted second abnormal feature value with an abnormal feature threshold to obtain a pixel block abnormality determination result; If the pixel block abnormality determination result is that the pixel block is qualified, the pixel block is stored in a qualified image temporary storage area; If the pixel block abnormality determination result is that the pixel block is abnormal, the pixel block is stored in the abnormal image temporary storage area.

7. The method for analyzing abnormal images displayed on a liquid crystal display according to claim 6, wherein: The specific method for obtaining the first adjustment coefficient is as follows: Obtaining a first abnormal characteristic value of each sample pixel block and a historical first adjustment coefficient of each sample pixel block in a database; Counting the first abnormal feature difference between the first specification problem pixel block and each sample pixel block; Obtaining a preset sample first abnormal feature difference interval in the database and comparing them; if the first abnormal feature difference between the first specification problem pixel block and a sample pixel block is within the sample first abnormal feature difference interval, obtaining the sample pixel block as a reference sample pixel block; The historical first adjustment coefficients of each reference sample pixel block are counted and averaged to obtain the average of the historical first adjustment coefficients, and the average is used as the first adjustment coefficient.

8. The method for analyzing abnormal images displayed on a liquid crystal display according to claim 1, wherein: The specific method for obtaining each abnormal pixel cluster block and the abnormal parameters corresponding to each abnormal pixel cluster block is as follows: Obtain abnormal pixel blocks in the abnormal image temporary storage area, and use a clustering algorithm based on spatial connectivity to merge the connected areas of the abnormal pixel blocks to obtain abnormal pixel cluster blocks; A coordinate system is established based on the preset position of the LCD optimized display image as the origin and the plane where the LCD optimized display image is located as the coordinate plane to obtain the coordinate position of each abnormal pixel cluster block; Based on the coordinate position analysis of each abnormal pixel cluster block, abnormal parameters corresponding to each abnormal pixel cluster block are obtained, and the abnormal parameters corresponding to each abnormal pixel cluster block include a maximum abnormal length, a maximum abnormal width, and an abnormal area.

9. The method for analyzing abnormal images displayed on a liquid crystal display according to claim 1, wherein: The specific method for obtaining the fault type of the abnormal image displayed by the LCD screen is as follows: Obtaining the LCD display abnormality model preset in the database; Based on each abnormal pixel cluster block and the abnormal parameters corresponding to each abnormal pixel cluster block, they are input into the LCD display abnormality model as input variables, thereby outputting the fault type of the LCD display abnormal image.

10. A liquid crystal display abnormality image analysis system, applying the liquid crystal display abnormality image analysis method according to any one of claims 1 to 9, characterized in that: include: Image optimization and adjustment module, anomaly determination module and fault type analysis module; The image optimization and adjustment module is used to obtain the LCD display image through the image acquisition device, and optimize and adjust the image to obtain the LCD optimized display image; The abnormality determination module is used to set a first specification sliding window and a second specification sliding window to respectively perform sliding detection on the LCD optimized display image to obtain a pixel block abnormality determination result. If the pixel block abnormality determination result is qualified, the qualified pixel blocks are counted and stored in the qualified image temporary storage area; if the pixel block abnormality determination result is abnormal, the abnormal pixel blocks are counted and stored in the abnormal image temporary storage area; if the pixel block abnormality determination result is conflict, conflict adjustment is performed; The fault type analysis module is used to obtain abnormal pixel blocks in the abnormal image temporary storage area, and process them to obtain each abnormal pixel cluster block and the abnormal parameters corresponding to each abnormal pixel cluster block, thereby obtaining the fault type of the LCD screen displaying the abnormal image.

Images