Vehicle-mounted display screen defect detection method, device and equipment and storage medium

Abstract

The invention discloses a vehicle-mounted display screen defect detection method and device, equipment and a storage medium, and relates to the technical field of image processing. Performing noise filtering according to the initial image to obtain a filtered image; performing contrast defect enhancement according to the filtered image to obtain an enhanced image; and performing adaptive binarization processing and connected domain analysis according to the enhanced image so as to realize display screen defect detection. The accuracy and the detection efficiency of low-contrast vehicle-mounted display screen defect detection are improved.

Description

Technical Field

[0001] This application relates to the technical field of image processing, and particularly to a method, device, equipment and storage medium for defect detection of in-vehicle displays. Background Technique

[0002] In the production and manufacturing process of in-vehicle displays, quality inspection is a key link to ensure product quality. Among them, defect detection, as an important part of quality inspection, is of great significance for preventing defective products from entering the market and ensuring driving safety. Traditional display defect detection methods mostly rely on manual visual inspection. This method is not only inefficient but also easily affected by human factors, making it difficult to guarantee the accuracy and consistency of detection results. With the rapid development of machine vision technology, it has gradually become possible to use image processing and pattern recognition technologies to automatically detect defects in in-vehicle displays. Machine vision technology obtains image information on the surface of the display through image acquisition devices such as cameras, and then uses image processing algorithms to analyze and process the images, thereby realizing automatic recognition and positioning of defects. This method has the advantages of high efficiency, accuracy, stability, etc., and has become a research hotspot in the field of display quality inspection. However, in the defect detection of low-contrast in-vehicle displays, due to the small gray-scale difference between defects and the background, coupled with serious noise interference, the defect features are not obvious and it is difficult to effectively distinguish them from the background. This results in poor performance of traditional machine vision detection methods in low-contrast defect detection and a low defect detection rate.

[0003] Therefore, how to improve the accuracy of defect detection for low-contrast in-vehicle displays is an urgent problem to be solved at present. Summary of the Invention

[0004] The main purpose of this application is to provide a method, device, equipment and storage medium for defect detection of in-vehicle displays, aiming to solve the technical problem of how to improve the accuracy of defect detection for low-contrast in-vehicle displays.

[0005] To achieve the above purpose, this application proposes a method for defect detection of in-vehicle displays, and the method includes:

[0006] Obtain an initial image of the display surface;

[0007] Perform noise filtering on the initial image to obtain a filtered image;

[0008] Perform contrast defect enhancement on the filtered image to obtain an enhanced image;

[0009] Perform adaptive binarization processing and connected component analysis on the enhanced image to achieve defect detection of the display.

[0010] In one embodiment, the step of performing noise filtering on the initial image to obtain a filtered image includes:

[0011] Obtain a neighborhood range;

[0012] Construct a histogram set based on the initial image and the neighborhood range, where the histogram set includes a central histogram and a neighborhood histogram;

[0013] Calculate the similarity weight between the neighborhood histogram and the central pixel histogram in the histogram set;

[0014] Perform filtering processing on the initial image according to the similarity weight to obtain a filtered image.

[0015] In one embodiment, the step of constructing a histogram set based on the initial image and the neighborhood range includes:

[0016] Obtain initial image pixel points from the initial image;

[0017] Obtain a central histogram and a neighborhood histogram based on the initial image pixel points and the neighborhood range;

[0018] Construct a histogram set based on the central histogram and the neighborhood histogram.

[0019] In one embodiment, the step of calculating the similarity weight between the neighborhood histogram and the central pixel histogram in the histogram set includes:

[0020] Calculate the Manhattan distance between the neighborhood histogram and the central pixel histogram in the histogram set;

[0021] Calculate the range difference of the histogram set according to the histogram set;

[0022] Calculate the similarity weight according to the Manhattan distance and the range difference.

[0023] In one embodiment, the step of performing contrast defect enhancement on the filtered image to obtain an enhanced image includes:

[0024] Perform downsampling on the filtered image according to a preset strategy to obtain a reduced image;

[0025] Perform upsampling on the reduced image to obtain a target image;

[0026] Calculate an enhanced image according to the means in the target image and the filtered image and a pre-design.

[0027] In one embodiment, the step of performing adaptive binarization processing and connected component analysis on the enhanced image to implement display screen defect detection includes:

[0028] The enhanced image is segmented into segmented images according to a preset segmentation strategy, and the pixel mean and pixel variance of the segmented images are calculated;

[0029] A binarization threshold is calculated according to the pixel mean, the pixel variance, and a preset second configuration parameter;

[0030] The segmented images are binarized according to the binarization threshold to obtain an edge feature image;

[0031] Connected component analysis is performed on the edge feature image to obtain a candidate defect set;

[0032] Defect detection of the display screen is performed according to the candidate defect set.

[0033] In one embodiment, the step of performing defect detection on the display screen according to the candidate defect set includes:

[0034] An area threshold, an aspect ratio threshold, a first mean threshold, and a second mean threshold are obtained;

[0035] The area and aspect ratio of the minimum bounding rectangle are calculated according to the candidate defect set, and defect detection is performed according to the area and the area threshold and the aspect ratio and the aspect ratio threshold to obtain a first candidate defect set;

[0036] First edge points are obtained according to the first candidate defect set and the edge feature image, and a first pixel mean is extracted from the filtered image according to the first edge points;

[0037] Defect detection is performed according to the first pixel mean and the first mean threshold to obtain a second candidate defect set;

[0038] Second edge points are obtained according to the second candidate defect set and the edge feature image, and a second pixel mean is extracted from the filtered image according to the second edge points and a preset adjacent extraction strategy;

[0039] Defect detection is performed according to the second pixel mean and the second mean threshold to obtain a target defect set, and defect detection of the display screen is completed.

[0040] In addition, to achieve the above object, the present application also proposes a vehicle-mounted display screen defect detection device, the device includes:

[0041] An image acquisition module, configured to acquire an initial image on the surface of the display screen;

[0042] A noise filtering module, configured to perform noise filtering on the initial image to obtain a filtered image after filtering;

[0043] A defect enhancement module for enhancing contrast defects based on the filtered image to obtain an enhanced image;

[0044] A defect detection module for performing adaptive binarization processing and connected component analysis on the enhanced image to implement display screen defect detection.

[0045] In addition, to achieve the above object, the present application also provides a vehicle-mounted display screen defect detection device, the device includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, the computer program is configured to implement the steps of the vehicle-mounted display screen defect detection method as described above.

[0046] In addition, to achieve the above object, the present application also provides a storage medium, the storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium, and when the computer program is executed by a processor, it implements the steps of the vehicle-mounted display screen defect detection method as described above.

[0047] In addition, to achieve the above object, the present application also provides a computer program product, the computer program product includes a computer program, and when the computer program is executed by a processor, it implements the steps of the vehicle-mounted display screen defect detection method as described above.

[0048] The present application provides a method for detecting defects in a vehicle-mounted display screen. The method of the present application includes: obtaining an initial image on the surface of the display screen; performing noise filtering on the initial image to obtain a filtered image; enhancing contrast defects based on the filtered image to obtain an enhanced image; performing adaptive binarization processing and connected component analysis on the enhanced image to implement display screen defect detection. In summary, it can be seen that the present application filters out noise from the original image by using an image filtering algorithm based on neighborhood histogram similarity measurement to reduce the interference of noise on defect detection; uses a low-contrast defect enhancement algorithm to enhance the filtered image to make defect features more obvious; extracts edge features in the image through an adaptive binarization method and connected component analysis technology, and combines a defect grading comprehensive judgment method to screen and verify candidate defects, improving the accuracy and detection efficiency of low-contrast vehicle-mounted display screen defect detection. Description of the Drawings

[0049] The drawings here are incorporated into the specification and form a part of this specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application.

[0050] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0051] Figure 1 It is a schematic flowchart provided for the first embodiment of the method for detecting defects in vehicle-mounted display screens of the present application;

[0052] Figure 2 It is a schematic flowchart provided for the second embodiment of the method for detecting defects in vehicle-mounted display screens of the present application;

[0053] Figure 3 It is a schematic diagram for constructing a neighborhood histogram in an embodiment of the method for detecting defects in vehicle-mounted display screens of the present application;

[0054] Figure 4 It is a schematic flowchart provided for the third embodiment of the method for detecting defects in vehicle-mounted display screens of the present application;

[0055] Figure 5 It is a schematic diagram of the module structure of the device for detecting defects in vehicle-mounted display screens in the embodiment of the present application;

[0056] Figure 6 It is a schematic diagram of the device structure of the hardware operating environment involved in the method for detecting defects in vehicle-mounted display screens in the embodiment of the present application.

[0057] The realization of the purpose, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. Specific Embodiments

[0058] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0059] To better understand the technical solutions of the present application, the following will be described in detail in combination with the accompanying drawings of the specification and specific embodiments.

[0060] The main solution of the embodiment of the present application is: obtaining an initial image of the display screen surface; performing noise filtering on the initial image to obtain a filtered image; performing contrast defect enhancement on the filtered image to obtain an enhanced image; performing adaptive binarization processing and connected component analysis on the enhanced image to implement defect detection of the display screen.

[0061] In the production process of in-vehicle display screens, quality inspection is a crucial link to ensure product quality. Among them, defect detection, as an important part of quality inspection, is of great significance for preventing defective products from entering the market and ensuring driving safety. Traditional display screen defect detection methods mostly rely on manual visual inspection. This method is not only inefficient but also easily affected by human factors, making it difficult to guarantee the accuracy and consistency of detection results. With the rapid development of machine vision technology, it has gradually become possible to perform automated defect detection on in-vehicle display screens using image processing and pattern recognition technologies. Machine vision technology obtains image information on the surface of the display screen through image acquisition devices such as cameras, and then uses image processing algorithms to analyze and process the images, thereby achieving automatic identification and positioning of defects. This method has the advantages of high efficiency, accuracy, and stability, and has become a research hotspot in the field of display screen quality inspection. However, in the defect detection of low-contrast in-vehicle display screens, due to the small gray-scale difference between defects and the background, combined with severe noise interference, the defect features are not obvious and it is difficult to effectively distinguish them from the background. This results in poor performance of traditional machine vision detection methods in low-contrast defect detection and a low defect detection rate. Therefore, how to improve the accuracy of low-contrast in-vehicle display screen defect detection is an urgent problem to be solved currently.

[0062] This application filters out noise from the original image by using an image filtering algorithm based on neighborhood histogram similarity measurement to reduce the interference of noise on defect detection; uses a low-contrast defect enhancement algorithm to enhance the filtered image, making the defect features more obvious; extracts edge features in the image through an adaptive binarization method and connected component analysis technology, and combines a defect grading comprehensive judgment method to screen and verify candidate defects, improving the accuracy and detection efficiency of low-contrast in-vehicle display screen defect detection.

[0063] It should be noted that the execution subject of this embodiment can be an in-vehicle display screen defect detection system, or a computing service device with data processing, network communication, and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of implementing the above-mentioned in-vehicle display screen defect detection function. This embodiment does not specifically limit this. Hereinafter, taking the in-vehicle display screen defect detection system as an example, this embodiment and the following embodiments will be described.

[0064] Based on this, the embodiments of this application provide a method for detecting defects in in-vehicle display screens, referring to Figure 1 , Figure 1 is a schematic flowchart of the first embodiment of the method for detecting defects in in-vehicle display screens of this application.

[0065] In this embodiment, the method for detecting defects in in-vehicle display screens includes steps S10 to S40:

[0066] Step S10: Obtain the initial image on the surface of the display screen.

[0067] It should be noted that this step refers to collecting an image of the surface of the in-vehicle display screen through a camera, so as to obtain the initial image on the surface of the display screen, which is denoted as Image I. For example, in practical applications, the camera can be fixed at a specific position to ensure that the camera lens maintains a certain distance and angle from the surface of the display screen. It should be noted that parameters such as the resolution and exposure time of the camera need to be reasonably set according to the characteristics of different display screens and detection requirements to ensure that the quality of the collected image meets the requirements of subsequent processing.

[0068] Step S20: Perform noise filtering on the initial image to obtain a filtered image.

[0069] It should be noted that the filtered image refers to the image after noise filtering processing. In this step, the system will perform noise filtering processing on the obtained initial image I to obtain the filtered image. Specifically, the system will perform noise filtering according to an image filtering algorithm based on the similarity measure of the neighborhood histogram. The main process of this algorithm includes three steps: constructing a histogram, calculating the similarity weight, and filtering the image. First, for each pixel in the image, calculate the histogram of the N*N image block centered on each pixel within its neighborhood range; then, calculate the similarity weight between each histogram and the histogram of the central pixel; finally, perform filtering processing on the image according to the similarity weight to obtain the filtered image.

[0070] It can be understood that the purpose of this step is to reduce the noise interference in the image, improve the image quality, and provide more accurate image data for subsequent defect identification.

[0071] Step S30: Perform contrast defect enhancement on the filtered image to obtain an enhanced image.

[0072] It should be noted that the enhanced image refers to the image after contrast defect enhancement processing. In this step, the system will perform contrast defect enhancement processing on the obtained filtered image to obtain the enhanced image E. Specifically, the system will enhance the filtered image according to a preset low-contrast defect enhancement method. This method will first perform downsampling processing on the filtered image to obtain a new image G with reduced size; then, perform upsampling processing on image G to obtain a new image L with the same size as the original image; finally, calculate the enhanced image E according to a preset image enhancement formula.

[0073] It is understandable that since the low-contrast defect features are not obvious, in order to make its features clearly distinguishable from the background, it is necessary to enhance the filtered image, highlighting the defects while weakening the interference of the background, which is convenient for subsequent detection and recognition.

[0074] In a feasible implementation manner, the step S30 specifically includes:

[0075] Step S301: Downsample the filtered image according to a preset strategy to obtain a reduced image.

[0076] It should be noted that the preset strategy specifically refers to performing downsampling processing on the filtered image to reduce the resolution of the image, so as to obtain a reduced image G whose size is reduced to a certain proportion of the original. In this example, the size of the reduced image is 0.25 times the size of the original filtered image. Specifically, in this step, the system will perform downsampling processing on each pixel point in the filtered image according to the pre-determined downsampling ratio (such as 0.25 times), that is, selectively retain some pixel points according to the downsampling ratio, so as to obtain the reduced image G.

[0077] Step S302: Upsample the reduced image to obtain a target image.

[0078] It should be noted that in this step, the system will perform upsampling processing on the reduced image G to restore the original size of the image, so as to obtain the target image L. The upsampling processing uses the bilinear interpolation algorithm, which interpolates the gray value of the new pixel point by calculating the gray values of adjacent pixel points, so as to restore the resolution of the image. Specifically, the system will determine the target size of the upsampling. In this example, it is to restore the original size of the filtered image; then, perform bilinear interpolation processing on each pixel point in the reduced image G to obtain the target image L.

[0079] It is understandable that by upsampling to restore the resolution of the image, the enhanced image can maintain the size and detail information of the original image. At the same time, the bilinear interpolation algorithm can smoothly transition the gray values between adjacent pixel points, avoiding obvious interpolation traces.

[0080] Step S303: Calculate an enhanced image according to the mean values in the target image and the filtered image and a preset first configuration parameter.

[0081] It should be noted that in this step, the system will calculate the enhanced image according to the mean values in the target image and the filtered image and a preset first configuration parameter. The calculation of the enhanced image is shown in Formula 1:

[0082]

[0083] Wherein, Denote the filtered image mean value, M L Denote the mean value of the target image L, and α is a preset first configuration parameter. The preset first configuration parameter α is an adjustable parameter used to control the degree of contrast enhancement. It can be understood that in practical applications, the value of the parameter α can be adjusted according to factors such as the type of in-vehicle display screen, the type of defect, and the detection requirements to obtain the best detection effect. For example, in the scenario of in-vehicle display screen defect detection, for defects with extremely small gray-level differences from the background, such as low-contrast stains and slight scratches, through contrast enhancement processing, these defects can be made more prominent in the enhanced image, facilitating subsequent defect detection and processing.

[0084] Step S40: Perform adaptive binarization processing and connected component analysis on the enhanced image to achieve display screen defect detection.

[0085] It should be noted that in this step, the system will perform adaptive binarization processing on the obtained enhanced image E and achieve the detection of display screen defects through connected component analysis. Among them, adaptive binarization processing refers to the process of binarization processing according to the brightness differences in each region of the image; connected component analysis refers to the process of analyzing and processing the connected regions in the image after binarization processing. Through the combined application of these two steps, the detection and recognition of low-contrast in-vehicle display screen defects can be effectively achieved. Specifically, adaptive binarization processing means binarizing each region separately according to the brightness differences in each region of the image. For example, the enhanced image is divided into blocks; then, the mean value and variance of each image block are calculated; next, the binarization threshold of each image block is calculated according to a preset formula; finally, the pixels in each image block are binarized to obtain the edge feature image Q.

[0086] In addition, it should be noted that connected component analysis refers to analyzing and processing the connected regions in the edge feature image Q. For example, the candidate defect set in the image is extracted through a connected component analysis strategy; then, a hierarchical judgment process is performed on each candidate defect in the set. The hierarchical judgment process includes steps such as calculating the area and aspect ratio of the minimum circumscribed rectangle of the defect, extracting the pixel mean value of the defect region, etc., and identifying and classifying the defects according to a preset threshold.

[0087] It can be understood that the purpose of this step is to extract the defect features in the enhanced image and identify and classify the defects through connected component analysis.

[0088] This embodiment provides a method for detecting defects in in-vehicle displays. The method of this embodiment includes: obtaining an initial image of the display screen surface; performing noise filtering on the initial image to obtain a filtered image; enhancing contrast defects based on the filtered image to obtain an enhanced image; and performing adaptive binarization processing and connected component analysis on the enhanced image to achieve defect detection of the display screen. In summary, in this embodiment, the noise of the original image is filtered by using an image filtering algorithm based on neighborhood histogram similarity measurement to reduce the interference of noise on defect detection; a low-contrast defect enhancement algorithm is used to enhance the filtered image to make the defect features more obvious; the edge features in the image are extracted by an adaptive binarization method and connected component analysis technology, and combined with a defect grading comprehensive judgment method to screen and verify candidate defects, improving the accuracy and detection efficiency of low-contrast in-vehicle display defect detection.

[0089] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar content as that in the above-mentioned first embodiment can be referred to the above introduction and will not be repeated hereinafter. On this basis, please refer to Figure 2 , Figure 2 which is a schematic flowchart of the second embodiment of the method for detecting defects in in-vehicle displays of the present application. The specific steps of step S20 include:

[0090] Step S201: Obtain the neighborhood range.

[0091] It should be noted that in this step, for each pixel point I(x, y) in the initial image, the system will define a neighborhood range N (N is an odd number) centered on it. The size of this neighborhood range will be adjusted according to actual needs (such as 3, 5, etc.) to ensure that the image features around the pixel point can be fully captured. For example, assuming N is 3, the system will select a 3×3 neighborhood range. Then, for a certain pixel point I(x, y) in the image, its neighborhood will include 8 pixel points around it (that is, one pixel point above, below, left, right, upper left, upper right, lower left, and lower right respectively). It should be noted that the value of N here represents the size of the neighborhood, that is, an N×N image block area.

[0092] Step S202: Construct a histogram set according to the initial image and the neighborhood range, where the histogram set includes a central histogram and neighborhood histograms.

[0093] It should be noted that after determining the neighborhood range, the system will construct a histogram set according to the initial image I and the neighborhood range N. The histogram set includes a central histogram (H0) and neighborhood histograms (H1,..., H N*N-1)。The central histogram refers to the histogram calculated for the N×N image block where the central pixel I(x,y) is located, while the neighborhood histogram refers to the histograms calculated for the N×N image blocks of each pixel except the central pixel within the neighborhood range.

[0094] In addition, it should be noted that, as Figure 3 shown, the horizontal axis of the histogram represents the pixel value intervals. Each histogram is divided into 9 intervals. The width of each of the first 8 intervals is 30, and the width of the last interval is 16 (corresponding to 0 - 255). The vertical axis represents the number of pixel points within that interval. That is, interval 0 is used to count the number of pixel points with pixel values from 0 to 29 within the N neighborhood range, interval 1 is used to count the number of pixel points with pixel values from 30 to 59 within the N neighborhood range, and so on. Interval 8 is used to count the number of pixel points with pixel values from 240 to 255 within the N neighborhood range.

[0095] In a feasible implementation manner, the step S202 specifically includes:

[0096] Step A10: Obtain the initial image pixel points according to the initial image.

[0097] It should be noted that the initial image, that is, image I, is obtained by the camera collecting an image of the surface of the vehicle-mounted display screen. The initial image pixel points refer to each pixel point in image I, and these pixel points contain the gray-scale information of the display screen surface. For example, assuming the resolution of image I is 1024x768, then the initial image pixel point I(x,y) is each of these 786432 pixel points. The gray-scale values of these pixel points usually range from 0 to 255.

[0098] Step A20: Obtain the central histogram and the neighborhood histogram according to the initial image pixel points and the neighborhood range.

[0099] It should be noted that the specific process of obtaining the central histogram and the neighborhood histogram is as follows: For each pixel point I(x,y) in image I, taking it as the center, within its N neighborhood range, calculate the histograms of the N*N (N is an odd number) sized image blocks centered on each pixel, and a total of (N*N) histograms are obtained, including the histogram H0 corresponding to the central pixel point I(x,y) and the histograms H1,...,H corresponding to the other pixel points within the neighborhood N*N-1 .

[0100] For example, as Figure 3As shown, assuming N = 3, for the pixel I(x, y), within its 3-neighborhood range, with pixels {I1,..., I8} as centers respectively (excluding the case where I(x, y) itself is the center, but I(x, y) will be considered when calculating H0), calculate the histograms of the 3*3 neighborhoods of each pixel to obtain 8 neighborhood histograms {H1,..., H8}, and then add the histogram H0 of the 3*3 neighborhood of the central pixel I(x, y), resulting in a total of 9 histograms, forming a histogram set {H0, H1,..., H8}.

[0101] It can be understood that the histogram is a representation method of the statistical features of an image, which counts the number or frequency of occurrences of each gray value in the image. By constructing the histogram, the gray distribution of the image can be intuitively understood and then used in subsequent image processing and analysis processes.

[0102] Step A30: Construct a histogram set based on the central histogram and the neighborhood histograms.

[0103] It should be noted that the histogram set is {H0, H1,..., H N*N-1}, which includes the histogram H0 corresponding to the central pixel and the histograms {H1,..., H N*N-1} corresponding to other pixels in the neighborhood. Combining these histograms forms the histogram set {H0, H1,..., H N*N-1}. It can be understood that the system will use this histogram set for subsequent noise filtering. By comparing the similarity between the central histogram H0 and the neighborhood histograms {H1,..., H N*N-1}, it can be determined whether the central pixel I(x, y) is disturbed by noise and perform filtering accordingly.

[0104] Step S203: Calculate the similarity weights between the neighborhood histograms and the central pixel histogram in the histogram set.

[0105] It should be noted that in this step, the system will calculate the similarity weights between the neighborhood histograms and the central pixel histogram to evaluate the similarity degree between the neighborhood pixels and the central pixel, thereby providing a basis for subsequent filtering. Specifically, the system will calculate each neighborhood histogram (H1,..., H N*N-1The Manhattan distance between it and the central histogram (H0) is calculated, and the similarity weight is calculated based on this distance and the difference between the maximum value and the minimum value in all intervals of each histogram. For example, assuming there are 9 histograms (H0, H1,..., H8), the system will calculate the Manhattan distances between H1 to H8 and H0 respectively, and calculate the similarity weights according to these distances and the differences between the maximum and minimum values of each histogram. It should be noted that the similarity weight reflects the similarity degree between the neighborhood pixel points and the central pixel point, and the larger the weight, the higher the similarity degree.

[0106] In a feasible implementation manner, the step S203 specifically includes:

[0107] Step B10: Calculate the Manhattan distance between the neighborhood histogram and the central pixel histogram in the histogram set.

[0108] It should be noted that the Manhattan distance refers to the sum of the absolute axis distances of two points on the standard coordinate axes in the standard coordinate system. Specifically, in this step, the specific process of calculating the Manhattan distance is as follows: For each histogram H N*N-1 in the set of histograms {H1,..., H i}, calculate its Manhattan distance from H0, as shown in Equation 2:

[0109]

[0110] where H i (j) represents the value of the j-th interval in the i-th histogram H i , H0(j) represents the value of the j-th interval in the histogram H0, and d i represents the Manhattan distance between the histogram H i and H0. It can be understood that the Manhattan distance is an effective method for measuring the difference between two histograms. It takes into account the distribution differences of the histograms in each interval and can comprehensively reflect the similarity degree between the two.

[0111] Step B20: Calculate the range value of the histogram set according to the histogram set.

[0112] It should be noted that in this step, the specific process of calculating the range value is as follows: For each histogram H N*N-1 in the histogram set {H0, H1,..., H i}, calculate the difference between the maximum value and the minimum value in all its intervals, that is, obtain the range value of this histogram, as shown in Equation 3:

[0113] Hd i = max{H i (0), ……, H i(8)}-min{H i (0),……,H i (8)} i = 0, 1,......, N*N - 1

[0114] (Formula 3)

[0115] Among them, Hd i refers to the range of values of the histogram H i .

[0116] It can be understood that the range of values reflects the degree of fluctuation of the internal values of the histogram and is an important indicator for evaluating the distribution characteristics of the histogram. When calculating the similarity weight, considering the range of values can make the weight calculation more accurate and comprehensive.

[0117] Step B30: Calculate the similarity weight according to the Manhattan distance and the range of values.

[0118] It should be noted that in this step, for each histogram H in the histogram {H1,..., H N*N-1}, i the system will calculate its similarity weight with the histogram H0 according to its Manhattan distance d i and the range of values Hd i , specifically as shown in Formula 4:

[0119]

[0120] Among them, w i refers to the similarity weight between the histogram H i and the histogram H0.

[0121] Step S204: Filter the initial image according to the similarity weight to obtain a filtered image.

[0122] It should be noted that in this step, the system will filter the initial image according to the similarity weight. Specifically, for each pixel point I(x, y) in the initial image, the weighted average is calculated according to the similarity weights of all pixel points in its N×N neighborhood and the corresponding pixel gray values to obtain the gray value of the filtered pixel point, as shown in Formula 5:

[0123]

[0124] Among them, m i represents the average pixel gray value of the image block with a size of N*N centered on each pixel in the N neighborhood of the pixel I(x, y), is the gray value of the filtered image of the pixel I(x, y) after filtering, and w i represents the corresponding similarity weight.

[0125] In this embodiment, by constructing a histogram set, calculating similarity weights, and performing filtering processing, image filtering based on neighborhood histogram similarity measurement is achieved, effectively filtering out noise and improving the accuracy of subsequent low-contrast defect enhancement and detection.

[0126] Based on the first and second embodiments of this application, in the third embodiment of this application, for content that is the same as or similar to the above-mentioned first and second embodiments, reference can be made to the above introduction and will not be elaborated hereinafter. On this basis, please refer to Figure 4 , Figure 4 which is a schematic flowchart of the third embodiment of the method for detecting defects in an in-vehicle display screen of this application. The specific steps of step S40 include:

[0127] Step S401: Divide the enhanced image into block images according to a preset block strategy, and calculate the pixel mean and pixel variance of the block images.

[0128] It should be noted that the enhanced image E is obtained by performing low-contrast defect enhancement processing on the filtered image. The preset block strategy means that the enhanced image E is evenly divided according to a preset block size P, where the value range of P can be flexibly set according to actual needs, such as 5 to 15. In this way, each block image represents a local area in the enhanced image E. For each block image, calculate its pixel mean and pixel variance. Here, the mean refers to the average value of all pixel gray values in the block image, which reflects the overall brightness level of the area; the variance reflects the degree of dispersion of the pixel gray values in the area, that is, the uniformity of brightness.

[0129] Step S402: Calculate a binarization threshold according to the pixel mean, the pixel variance, and a preset second configuration parameter.

[0130] It should be noted that in this step, the calculation of the binarization threshold is based on the pixel mean M P of the block image, the pixel variance S P and a preset second configuration parameter β together. The second configuration parameter can be a fixed value or a coefficient that can be adjusted according to actual needs. Specifically, the calculation of the binarization threshold T P is shown in Formula 6:

[0131]

[0132] where β is a preset second configuration parameter, with a value range of 0 to 1, and the value of R is 127 or 255.

[0133] Step S403: Perform binarization processing on the block image according to the binarization threshold to obtain an edge feature image.

[0134] It should be noted that the binarization process refers to comparing each pixel value of the segmented image with the binarization threshold T P If the pixel value is greater than T P , then the pixel is set to 1 (indicating an edge point); if the pixel value is less than or equal to T, then the pixel is set to 0 (indicating a background point). In this way, each segmented image is converted into a binary image containing only 0 and 1. After binarizing all the segmented images, they are stitched together according to their original positions to obtain the edge feature image Q of the entire enhanced image E. In the edge feature image Q, the pixel points with a value of 1 represent the possible defect edges.

[0135] Step S404: Perform connected component analysis on the edge feature image to obtain a candidate defect set.

[0136] It should be noted that connected component analysis refers to traversing the edge feature image Q to find all sets of continuously 1-valued pixel points, i.e., connected components. Each connected component represents a possible defect area. For each connected component, its characteristic parameters such as area, aspect ratio, etc. can be calculated, and screening is performed based on these parameters and preset defect judgment criteria to obtain a candidate defect set. Each element in the candidate defect set represents a possible defect area and its characteristic parameters.

[0137] Step S405: Perform display screen defect detection based on the candidate defect set.

[0138] It should be noted that in this step, display screen defect detection refers to further grading and verification of each candidate defect in the candidate defect set to determine whether it is a real low-contrast defect. For example, a series of threshold ranges or judgment rules for defect characteristic parameters (such as area, aspect ratio, gray mean, etc.) can be set. For each defect in the candidate defect set, its characteristic parameters are calculated and compared with the preset threshold ranges or judgment rules. If the characteristic parameters of the candidate defect meet the preset defect judgment criteria, it is determined as a real low-contrast defect.

[0139] In a feasible implementation manner, step S405 specifically includes:

[0140] Step C10: Obtain an area threshold, an aspect ratio threshold, a first mean threshold, and a second mean threshold.

[0141] It should be noted that in order to accurately detect the defects in the candidate defect set, the system will obtain a series of preset threshold parameters, including the area threshold T A , the aspect ratio threshold T B , the first mean threshold T Iand a second mean threshold T II The area threshold T A and the aspect ratio threshold T B are used to determine whether the candidate defect is large enough to distinguish a true defect from minute noise and flaws. The first mean threshold T I and the second mean threshold T II are then used for subsequent pixel mean comparison to further screen and confirm defects. These threshold parameters can be flexibly adjusted according to different display screens and defect types.

[0142] Step C20: Calculate the area and aspect ratio of the minimum bounding rectangle according to the set of candidate defects, and perform defect detection based on the area and the area threshold and the aspect ratio and the aspect ratio threshold to obtain a first set of candidate defects.

[0143] It should be noted that in this step, for each candidate defect in the set of candidate defects, the system calculates the area and aspect ratio of its minimum bounding rectangle, and then compares these areas and aspect ratios with the preset area threshold T A and the aspect ratio threshold T B respectively. If the area threshold of a certain candidate defect is greater than T A and the aspect ratio is greater than the aspect ratio threshold T B , it is determined that the candidate defect is a true defect and is retained in the first set of candidate defects ; otherwise, it is excluded.

[0144] Step C30: Obtain first edge points according to the first set of candidate defects and the edge feature image, and extract the filtered image according to the first edge points to obtain a first pixel mean.

[0145] It should be noted that in this step, for each candidate defect in the first set of candidate defects , the system finds the corresponding set of edge points, that is, the first edge points, according to its position information in the edge feature image Q. Then, according to these first edge points, all the corresponding pixel values are extracted in the filtered image and the mean of these pixel values is calculated, that is, the first pixel mean.

[0146] Step C40: Perform defect detection according to the first pixel mean and the first mean threshold to obtain a second set of candidate defects.

[0147] It should be noted that the system compares the first pixel mean of each candidate defect in the first set of candidate defects with the preset first mean threshold T I respectively. If the first pixel mean of a certain candidate defect is greater than or equal to the first mean threshold TI , it is determined that the candidate defect is a genuine defect and it is retained in the second candidate defect set ; otherwise, it is excluded.

[0148] Step C50: Obtain second edge points based on the second candidate defect set and the edge feature image, and extract the filtered image according to the second edge points and a preset adjacent extraction strategy to obtain a second pixel mean value.

[0149] It should be noted that in this step, for each candidate defect in the second candidate defect set , according to its position information in the edge feature image Q again, the corresponding edge point set, that is, the second edge points, is found. Then, according to these second edge points and a preset adjacent extraction strategy (that is, extract all pixels adjacent to the second edge points in the x direction and y direction), the corresponding pixel values are extracted from the filtered image, and the mean value of these pixel values is calculated, that is, the second pixel mean value.

[0150] Step C60: Perform defect detection based on the second pixel mean value and the second mean threshold to obtain a target defect set, and complete the defect detection of the display screen.

[0151] It should be noted that the system will compare the second pixel mean value of each candidate defect in the second candidate defect set with a preset second mean threshold T II . If the second pixel mean value of a certain candidate defect is greater than or equal to the second mean threshold T II , it is determined as a genuine defect and added to the target defect set; otherwise, it is excluded.

[0152] It can be understood that the target defect set is a set of low-contrast defects that are finally detected and free from interference by other defects. These defects can improve the detection accuracy and efficiency in the subsequent production detection process to improve the quality and reliability of the in-vehicle display screen.

[0153] In this embodiment, through block processing, calculating the binarization threshold, binarization processing, connected component analysis, and hierarchical defect detection, the feature extraction and defect recognition of the enhanced image are realized, effectively coping with the image brightness difference, accurately extracting the edge features, and screening candidate defects through a multi-level judgment strategy, improving the accuracy and efficiency of low-contrast in-vehicle display screen defect detection.

[0154] This application also provides an in-vehicle display screen defect detection device. Please refer to Figure 5 , the in-vehicle display screen defect detection device includes:

[0155] An image acquisition module 10, configured to acquire an initial image of the display screen surface;

[0156] A noise filtering module 20, configured to perform noise filtering on the initial image to obtain a filtered image after filtering;

[0157] A defect enhancement module 30, configured to perform contrast defect enhancement on the filtered image to obtain an enhanced image;

[0158] A defect detection module 40, configured to perform adaptive binarization processing and connected component analysis on the enhanced image to implement defect detection of the display screen.

[0159] The in-vehicle display screen defect detection device provided by this application adopts the in-vehicle display screen defect detection method in the above embodiment, and can solve the technical problem of how to improve the accuracy of in-vehicle display screen defect detection. Compared with the prior art, the beneficial effects of the in-vehicle display screen defect detection device provided by this application are the same as those of the in-vehicle display screen defect detection method provided by the above embodiment, and other technical features in the in-vehicle display screen defect detection device are the same as the features disclosed in the method of the above embodiment, and will not be elaborated here.

[0160] In one embodiment, the noise filtering module 20 is further configured to obtain a neighborhood range; construct a histogram set according to the initial image and the neighborhood range, where the histogram set includes a central histogram and a neighborhood histogram; calculate a similarity weight between the neighborhood histogram and the central pixel histogram in the histogram set; perform filtering processing on the initial image according to the similarity weight to obtain a filtered image.

[0161] In one embodiment, the noise filtering module 20 is further configured to obtain initial image pixel points according to the initial image; calculate a central histogram and a neighborhood histogram according to the initial image pixel points and the neighborhood range; construct a histogram set according to the central histogram and the neighborhood histogram.

[0162] In one embodiment, the noise filtering module 20 is further configured to calculate the Manhattan distance between the neighborhood histogram and the central pixel histogram in the histogram set; calculate the extreme difference value of the histogram set according to the histogram set; calculate a similarity weight according to the Manhattan distance and the extreme difference value.

[0163] In one embodiment, the defect enhancement module 30 is further configured to perform downsampling on the filtered image according to a preset strategy to obtain a reduced image; perform upsampling on the reduced image to obtain a target image; calculate an enhanced image according to the mean values in the target image and the filtered image and a preset first configuration parameter.

[0164] In one embodiment, the defect detection module 40 is further configured to divide the enhanced image into block images according to a preset block strategy, and calculate the pixel mean and pixel variance of the block images; calculate a binarization threshold according to the pixel mean, the pixel variance, and a preset second configuration parameter; perform binarization processing on the block images according to the binarization threshold to obtain an edge feature image; perform connected component analysis on the edge feature image to obtain a candidate defect set; and perform display screen defect detection according to the candidate defect set.

[0165] In one embodiment, the defect detection module 40 is further configured to obtain an area threshold, an aspect ratio threshold, a first mean threshold, and a second mean threshold; calculate the area and aspect ratio of the minimum bounding rectangle according to the candidate defect set, and perform defect detection according to the area and the area threshold and the aspect ratio and the aspect ratio threshold to obtain a first candidate defect set; obtain first edge points according to the first candidate defect set and the edge feature image, and extract the filtered image according to the first edge points to obtain a first pixel mean; perform defect detection according to the first pixel mean and the first mean threshold to obtain a second candidate defect set; obtain second edge points according to the second candidate defect set and the edge feature image, and extract the filtered image according to the second edge points and a preset adjacent extraction strategy to obtain a second pixel mean; perform defect detection according to the second pixel mean and the second mean threshold to obtain a target defect set, and complete the display screen defect detection.

[0166] The present application provides a vehicle-mounted display screen defect detection device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the vehicle-mounted display screen defect detection method in the first embodiment above.

[0167] The following refers to Figure 6 , which shows a schematic structural diagram of a vehicle-mounted display screen defect detection device suitable for implementing the embodiments of the present application. The vehicle-mounted display screen defect detection device in the embodiments of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6The shown in-vehicle display defect detection device is merely an example and should not impose any limitations on the functions and application scope of the embodiments of this application.

[0168] As Figure 6 shown, the in-vehicle display defect detection device may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in the ROM (Read Only Memory) 1002 or the program loaded from the storage device 1003 into the RAM (Random Access Memory) 1004. In the RAM 1004, various programs and data required for the operation of the in-vehicle display defect detection device are also stored. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other through a bus 1005. The input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems may be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, an LCD (Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the in-vehicle display defect detection device to communicate with other devices wirelessly or wiredly to exchange data. Although the in-vehicle display defect detection device with various systems is shown in the figure, it should be understood that it is not required to implement or have all the shown systems. Instead, more or fewer systems may be implemented or had.

[0169] Specifically, according to the embodiments disclosed in this application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in this application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program codes for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device, or installed from the storage device 1003, or installed from the ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiments disclosed in this application are executed.

[0170] The in-vehicle display defect detection device provided by this application adopts the in-vehicle display defect detection method in the above-mentioned embodiment, and can solve the technical problem of how to improve the accuracy of defect detection for in-vehicle displays with low contrast. Compared with the prior art, the beneficial effects of the in-vehicle display defect detection device provided by this application are the same as those of the in-vehicle display defect detection method provided by the above-mentioned embodiment, and other technical features in this in-vehicle display defect detection device are the same as those disclosed in the method of the previous embodiment, which will not be elaborated here.

[0171] It should be understood that each part disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in a suitable manner in any one or more embodiments or examples.

[0172] The above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in this application, and all should be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

[0173] This application provides a computer-readable storage medium with computer-readable program instructions (i.e., computer programs) stored thereon, and the computer-readable program instructions are used to execute the in-vehicle display defect detection method in the above-mentioned embodiment.

[0174] The computer-readable storage medium provided by this application can be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or components, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable Read Only Memory or flash memory), optical fibers, CD-ROM (CD-Read Only Memory, portable compact disk read-only memory), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this embodiment, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or component. The program code contained on the computer-readable storage medium can be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0175] The above computer-readable storage medium can be included in the in-vehicle display defect detection device; or it can exist separately without being assembled into the in-vehicle display defect detection device.

[0176] The above computer-readable storage medium carries one or more programs. When the above one or more programs are executed by the in-vehicle display defect detection device, the in-vehicle display defect detection device is enabled to: obtain an initial image of the display screen surface; perform noise filtering on the initial image to obtain a filtered image; perform contrast defect enhancement on the filtered image to obtain an enhanced image; perform adaptive binarization processing and connected component analysis on the enhanced image to achieve in-vehicle display defect detection.

[0177] Computer program code for performing the operations of this application can be written in one or more programming languages or combinations thereof. The above-mentioned programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any kind of network, including a LAN (Local Area Network) or a WAN (Wide Area Network), or it can be connected to an external computer (for example, by connecting through the Internet using an Internet service provider).

[0178] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and this module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks can occur in a different order than that marked in the accompanying drawings. For example, two consecutively represented blocks can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0179] The modules described in the embodiments of this application can be implemented in software or in hardware. Among them, the name of the module does not constitute a limitation on the unit itself in some cases.

[0180] The readable storage medium provided by this application is a computer-readable storage medium. The computer-readable storage medium stores computer-readable program instructions (i.e., computer programs) for performing the above-mentioned vehicle-mounted display defect detection method, and can solve the technical problem of how to improve the accuracy of low-contrast vehicle-mounted display defect detection. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by this application are the same as those of the vehicle-mounted display defect detection method provided in the above embodiments, and will not be elaborated here.

[0181] The present application also provides a computer program product, including a computer program, and when the computer program is executed by a processor, it implements the steps of the vehicle-mounted display defect detection method as described above.

[0182] The computer program product provided by the present application can solve the technical problem of how to improve the accuracy of defect detection for vehicle-mounted displays with low contrast. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as those of the vehicle-mounted display defect detection method provided in the above embodiments, and will not be elaborated here.

[0183] The above are only partial embodiments of the present application, and thus do not limit the patent scope of the present application. Any equivalent structural transformation made under the technical concept of the present application by using the content of the specification and drawings of the present application, or any direct / indirect application in other related technical fields, is included in the patent protection scope of the present application.

Claims

1. A method for defect detection of in-vehicle display screens, characterized in that, The method includes: Obtaining an initial image on the surface of the display screen; Performing noise filtering on the initial image to obtain a filtered image; Performing contrast defect enhancement on the filtered image to obtain an enhanced image; Performing adaptive binarization processing and connected component analysis on the enhanced image to implement display screen defect detection.

2. The method according to claim 1, characterized in that, The step of performing noise filtering on the initial image to obtain a filtered image includes: Obtaining a neighborhood range; Constructing a histogram set according to the initial image and the neighborhood range, where the histogram set includes a central histogram and a neighborhood histogram; Calculating the similarity weight between the neighborhood histogram and the central pixel histogram in the histogram set; Performing filtering processing on the initial image according to the similarity weight to obtain a filtered image.

3. The method according to claim 2, wherein The step of constructing a histogram set according to the initial image and the neighborhood range includes: Obtaining initial image pixel points according to the initial image; Obtaining a central histogram and a neighborhood histogram according to the initial image pixel points and the neighborhood range; Constructing a histogram set according to the central histogram and the neighborhood histogram.

4. The method according to claim 2, wherein The step of calculating the similarity weight between the neighborhood histogram and the central pixel histogram in the histogram set includes: Calculating the Manhattan distance between the neighborhood histogram and the central pixel histogram in the histogram set; Calculating the extreme difference value of the histogram set according to the histogram set; Calculating the similarity weight according to the Manhattan distance and the extreme difference value.

5. The method according to claim 1, wherein The step of performing contrast defect enhancement on the filtered image to obtain an enhanced image includes: Performing downsampling on the filtered image according to a preset strategy to obtain a reduced image; Performing upsampling on the reduced image to obtain a target image; Calculating an enhanced image according to the means in the target image and the filtered image and a preset first configuration parameter.

6. The method according to claim 1, wherein The step of performing adaptive binarization processing and connected component analysis on the enhanced image to implement display screen defect detection includes: Dividing the enhanced image into blocks according to a preset block strategy to obtain a block image, and calculating the pixel mean and pixel variance of the block image; Calculating a binarization threshold according to the pixel mean, the pixel variance, and a preset second configuration parameter; Performing binarization processing on the block image according to the binarization threshold to obtain an edge feature image; Performing connected component analysis on the edge feature image to obtain a candidate defect set; Performing display screen defect detection according to the candidate defect set.

7. The method according to claim 6, wherein The step of performing display screen defect detection according to the candidate defect set includes: Obtaining an area threshold, an aspect ratio threshold, a first mean threshold, and a second mean threshold; Calculating the area and aspect ratio of the minimum bounding rectangle according to the candidate defect set, and performing defect detection according to the area and the area threshold and the aspect ratio and the aspect ratio threshold to obtain a first candidate defect set; Obtaining first edge points according to the first candidate defect set and the edge feature image, and extracting the filtered image according to the first edge points to obtain a first pixel mean; Defect detection is performed based on the first pixel mean and the first mean threshold to obtain a second candidate defect set; Second edge points are obtained based on the second candidate defect set and the edge feature image, and a second pixel mean is extracted from the filtered image according to the second edge points and a preset adjacent extraction strategy; Defect detection is performed based on the second pixel mean and the second mean threshold to obtain a target defect set, completing the defect detection of the display screen.

8. An in-vehicle display defect detection device, characterized in that, The device includes: An image acquisition module, configured to acquire an initial image on the surface of the display screen; A noise filtering module, configured to perform noise filtering on the initial image to obtain a filtered image after filtering; A defect enhancement module, configured to perform contrast defect enhancement on the filtered image to obtain an enhanced image; A defect detection module, configured to perform adaptive binarization processing and connected component analysis on the enhanced image to implement defect detection of the display screen.

9. An in-vehicle display defect detection device, characterized in that, The device includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, the computer program being configured to implement the steps of the vehicle-mounted display screen defect detection method according to any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the vehicle-mounted display screen defect detection method according to any one of claims 1 to 7 are implemented.

Images