Method, device and equipment for detecting defects of liquid crystal display screen and storage medium

Abstract

The invention discloses a method, device and equipment for detecting defects of a liquid crystal display screen and a storage medium. The method comprises the steps that an effective display area image of the display screen is acquired; repairing a region-of-interest mask of the effective display area image, the region-of-interest mask determining an effective pixel range of the effective display area image for blank pressing defect detection; removing the repaired inner ring image of the interest area mask in the effective display area image to obtain an outer ring image of a preset pixel layer number; unfolding the outer ring image and splicing the outer ring image into a strip-shaped image; and based on the strip-shaped image, detecting the defect of the display screen blank pressing area. By means of the method, the capability of detecting the edge pressing defects of the corner areas of the liquid crystal display screen can be improved.

Description

Technical Field

[0001] The present invention generally relates to the field of defect detection. More specifically, the present invention relates to a method, apparatus, device, and storage medium for detecting defects in liquid crystal display screens. Background Art

[0002] Liquid Crystal Displays (LCDs) can develop edge-pressing defects around the edges of the screen due to factors such as improper pressure, material issues, or poor assembly during the production process. This can severely impact the display quality. To address this, the typical LCD edge-pressing defect detection process begins by capturing an image of the LCD's active area (AA area). This image undergoes horizontal and vertical morphological processing, followed by blob analysis to detect edge-pressing defects.

[0003] However, these detection methods often fail to effectively address corners. This is because using a horizontal filter kernel for horizontal morphological processing can detect defects at the top and bottom edges of the LCD, but has limited detection capabilities for defects at the left and right edges. The opposite is true when using a vertical filter kernel for vertical morphological processing. This means that the corners of the LCD cannot be adequately addressed, especially when the LCD's corners are curved. Regardless of whether a horizontal filter kernel, a vertical filter kernel, or a square kernel is used, detection results are suboptimal.

[0004] In view of this, there is an urgent need to provide a method for detecting defects in liquid crystal display screens so as to improve the detection capability of edge pressing defects in the corner areas of LCDs. Summary of the Invention

[0005] In order to at least solve one or more of the technical problems mentioned above, the present application proposes a method, apparatus, device and storage medium for detecting defects in a liquid crystal display screen in multiple aspects.

[0006] In a first aspect, the present application provides a method for detecting defects in a liquid crystal display screen, comprising: obtaining an image of an effective display area of ​​the display screen; repairing a region of interest mask of the effective display area image, wherein the region of interest mask determines an effective pixel range of the effective display area image for edge pressure defect detection; removing the inner circle image of the repaired region of interest mask from the effective display area image to obtain an outer circle image with a preset number of pixel layers; expanding the outer circle image and splicing it into a strip image; and detecting defects in the edge pressure area of ​​the display screen based on the strip image.

[0007] In some embodiments, repairing the region of interest mask of the effective display area image includes: obtaining contour points of the region of interest mask; filtering out contour points to be repaired from the contour points; and performing polygon fitting based on the contour points to be repaired to repair the region of interest mask.

[0008] In some embodiments, expanding the outer circle image and splicing it into a strip image includes: expanding the outer circle image into corresponding linear vectors according to the pixel layer; padding the linear vectors at the beginning and end according to the half value of the length of the preset strip filter kernel; and splicing the linear vectors after padding at the beginning and end to obtain the strip image.

[0009] In some embodiments, the step of splicing the linear vectors after filling the head and tail to obtain the strip image includes: sorting the linear vectors based on their lengths, and splicing the linear vectors together from top to bottom in sequence to obtain an initial trapezoidal image; determining a length reference of the initial trapezoidal image; and adjusting the lengths of the linear vectors of each layer of the initial trapezoidal image to be consistent based on the length reference, to obtain the strip image.

[0010] In some embodiments, detecting defects in the edge-pressed area of ​​the display screen based on the strip image also includes: constructing a corresponding filter kernel for the strip image and performing morphological processing on the strip image based on the filter kernel to obtain a corresponding target linear vector; performing threshold segmentation on the target linear vector to detect the defect and obtain a final linear vector response map and a linear vector result map marked with the defect; and restoring the final linear vector response map and the linear vector result map to the effective display area image to display the detected defect in the edge-pressed area of ​​the display screen.

[0011] In some embodiments, constructing a corresponding filter kernel for the strip image and performing morphological processing on the strip image based on the filter kernel includes: constructing a strip filter kernel and a vertical filter kernel for the strip image; performing morphological operations on the strip image based on the strip filter kernel to obtain a defect detection response map; and performing an expansion operation on the defect detection response map based on the vertical filter kernel to extract the target linear vector.

[0012] In some embodiments, the threshold segmentation of the target linear vector includes: removing the elements filled at the beginning and end of the target linear vector to obtain the final response map of the linear vector; comparing each element in the final response map of the linear vector with a preset response threshold; if there are a preset target number of elements that are continuously greater than the preset response threshold, marking the corresponding element as a defect; after the comparison of each element in the final response map of the linear vector is completed, obtaining the linear vector result map marked with the defect.

[0013] In a second aspect, the present application also provides a device for detecting defects in liquid crystal display screens, comprising: an acquisition module for acquiring an effective display area image of the display screen; a repair module for repairing the region of interest mask of the effective display area image, wherein the region of interest mask determines the effective pixel range of the effective display area image for edge pressure defect detection; a removal module for removing the repaired inner circle image of the region of interest mask in the effective display area image to obtain an outer circle image with a preset number of pixel layers; a splicing module for expanding and splicing the outer circle image into a strip image; and a detection module for detecting defects in the edge pressure area of ​​the display screen based on the strip image.

[0014] In a third aspect, the present disclosure also provides a device for detecting defects in liquid crystal displays, comprising: a processor; and a memory storing program instructions for detecting defects in liquid crystal displays, wherein when the program instructions are executed by the processor, any of the methods described above is implemented.

[0015] In a fourth aspect, the present disclosure further provides a computer-readable storage medium storing computer program instructions for detecting defects in liquid crystal display screens. When the computer program instructions are executed by a processor, any of the methods described above is implemented.

[0016] By means of the method, apparatus, device and storage medium for detecting defects in liquid crystal display screens as provided above. The embodiment of the present application provides a method for detecting defects in liquid crystal display screens, repairs the mask of the area of ​​interest in the visible area image of the display screen, and obtains the outer circle image of the preset pixel layer after removing the inner circle image of the mask of the area of ​​interest in the effective display area image. The outer circle image is then expanded and spliced ​​into a strip image, which is used to detect defects in the edge pressing area of ​​the display screen. Through the above method, the outer circle image can be integrated into a strip image, which is more conducive to defect detection in the edge pressing area and improves the defect detection efficiency of the liquid crystal display screen. Furthermore, in some embodiments, the present application also constructs a strip filter kernel for the strip image and performs morphological processing, which facilitates subsequent morphological operations to ensure the output of accurate defect positions. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The above and other objects, features and advantages of the exemplary embodiments of the present application will become readily understood by reading the detailed description below with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present application are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein: Figure 1 An exemplary flow chart showing a method for detecting defects in a liquid crystal display screen according to some embodiments of the present application is provided; Figure 2 An exemplary flow chart showing a method for detecting defects in a liquid crystal display screen according to other embodiments of the present application is provided; Figure 3 An exemplary flow chart showing a method for detecting defects in a liquid crystal display screen according to yet other embodiments of the present application; Figure 4 An exemplary flow chart showing a method for detecting defects in a liquid crystal display screen according to other embodiments of the present application is provided; Figure 5 A schematic diagram of an image of an effective display area in an embodiment of the present application is shown; Figure 6 A schematic diagram showing the comparison of the mask repair of the region of interest before and after the embodiment of the present application is shown; Figure 7 A partial enlarged schematic diagram of an outer ring image defect in an embodiment of the present application is shown; Figure 8 A schematic diagram of an enlarged stripe image defect in an embodiment of the present application is shown; Figure 9 A schematic diagram showing the position restoration of the linear vector final response diagram and the linear vector result diagram in an embodiment of the present application is shown; Figure 10 An exemplary structural block diagram of an apparatus for detecting defects on a liquid crystal display screen according to an embodiment of the present application is shown; Figure 11 An exemplary structural diagram of a device for detecting defects in a liquid crystal display screen according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0019] It should be understood that the terms "include" and "comprising" used in the description and claims of this application indicate the presence of described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or collections thereof.

[0020] It should also be understood that the terms used in this specification are for the purpose of describing specific embodiments only and are not intended to limit this application. As used in this specification and claims, the singular forms "a," "an," and "the" are intended to include the plural forms unless the context clearly indicates otherwise. It should also be further understood that the term "and / or" as used in this specification and claims refers to any and all possible combinations of one or more of the associated listed items, including and including these combinations.

[0021] As used in this specification and claims, the term “if” can be interpreted as “when” or “upon” or “in response to determining” or “in response to detecting,” depending on the context. Similarly, the phrase “if it is determined” or “if [described condition or event] is detected” can be interpreted as meaning “upon determination” or “in response to determining” or “upon detection of [described condition or event]” or “in response to detecting [described condition or event],” depending on the context.

[0022] The specific implementation of the present application will be described in detail below with reference to the accompanying drawings.

[0023] Reference Figure 1 , to introduce the method 10 for detecting defects in liquid crystal display screens of the present application. Figure 1 As shown, in step S101, an image of the effective display area of ​​the display screen is obtained. In some embodiments, the display screen can be a liquid crystal display screen of any electronic device. The effective display area (Active Area, referred to as AA area) of the display screen refers to the actual area on the screen that can display content. This area can display images, text, and other content. Figure 5 ,AA area image can clearly show the effective display area of ​​the display screen, which can be obtained by image acquisition equipment such as cameras, for easy observation, Figure 5 A red arrow is used to highlight the edge-pressing defect in the AA area image. In one embodiment, a high-resolution industrial camera can be used to acquire the AA area image of the display screen. This means the industrial camera is parallel to the display screen and aligned with the AA area for image acquisition. The high-resolution industrial camera ensures that defects in the edge-pressing area of ​​the display screen are captured, and the acquired AA area image is used for subsequent edge-pressing area defect detection.

[0024] Next, at step S102, the region of interest mask of the effective display area image is repaired. In some embodiments, the region of interest in the region of interest mask (ROImask) refers to a specific area of ​​interest in the effective display area image when performing edge pressure defect detection. The region of interest mask determines the effective pixel range for edge pressure defect detection in the effective display area image, which can be formed by manual annotation or a specific area detection algorithm. Figure 6 (A) After mask processing, the effective display area image is a binary image, with the area of ​​interest being white (pixel value 1) and the rest of the area being black (pixel value 0). The edge pressure defect of the display will cause the mask of the area of ​​interest to be missing (e.g. Figure 6 (The area pointed by the red arrow in (A)). The purpose of repairing the ROI mask is to make up for the missing parts and expand the effective pixel range.

[0025] In one embodiment, a specific algorithm (such as the Graham scan method) can be used to repair missing portions of the ROI mask to expand the effective pixel area of ​​the defective region. Alternatively, in other feasible embodiments, interpolation methods can be used to repair missing portions, or morphological operations can be used to repair discontinuous mask boundaries of the ROI mask.

[0026] Reference Figure 6 , Figure 6 The arc-shaped area pointed by the red arrow in the lower right corner of (A) shows the situation where the edge pressure defect causes the mask of the region of interest to be missing. It can be seen that there is a small missing (black) area with irregular boundaries in the mask of the region of interest pointed by the red arrow. Figure 6 (B) shows the situation after restoration. It can be seen that the ROI mask at the corresponding area is no longer missing and the contour of the arc area becomes smooth.

[0027] In the above embodiment, the ROImask obtained after repair has higher accuracy and a larger effective pixel range, which is more conducive to the subsequent positioning of the edge pressing defect.

[0028] Furthermore, in step S103, the inner ring image of the repaired ROI mask is removed from the effective display area image to obtain an outer ring image with a preset number of pixel layers. In some embodiments, edge compression defects are primarily located at the edges of the display screen. Therefore, when processing the effective display area image, the inner ring image of the ROI mask can be removed, retaining only the outer ring image with a preset number of pixel layers. This can be understood as removing most of the white area within the ROI mask, leaving only the white area at the outer edge. To facilitate this removal, in one embodiment, the image area encompassing the outermost N pixel layers of the image can be predefined as the outer ring image. The outer ring layer 0 includes pixels at the image boundary and has the largest length; the outer ring layer 1 includes pixels one layer away from the outer ring and has a slightly smaller length; the outer ring layer 2 includes pixels one layer away from the outer ring and has an even smaller length, and so on, up to the Nth layer. Accordingly, N represents the preset number of pixel layers, which can be set based on the range within the effective display area image that fully preserves the edge compression defect. When removing the inner circle image, a mask can be constructed, that is, a mask is created for the inner circle image to erase it from the effective display area image, while retaining the outer circle image of N pixel layers. Figure 7 , Figure 7 The figure shows a partially enlarged schematic diagram of the outer circle image defect obtained after removing the inner circle image, where the white strip area is the outer circle image of N pixel layers, the missing part marked in the red rectangular box in the lower right corner is the edge pressure defect, and the black area to the left of the white strip area is the state after removing the inner circle image.

[0029] In the above embodiment, the outer circle image is obtained by erasing unnecessary inner circle images from the effective display area image. This effectively preserves the image information of the edge pressure area of ​​the display screen, preventing irrelevant inner circle areas from interfering with the defect detection process. It also reduces the amount of computation and improves processing efficiency.

[0030] Furthermore, at step S104, the outer ring image is expanded and spliced ​​into a strip image. In some embodiments, the outer ring image of N pixel layers is expanded into linear vectors starting from the outermost layer (layer 0). Next, N-1 (layers 1, 2, 3, ... N-1) are sequentially expanded into N-1 linear vectors. It is understood that the lengths of these N linear vectors decrease in sequence. In certain cases, it is not ruled out that a compression defect exists at the starting position of the pixel layer expansion. To prevent the compression defect at the starting position from being undetectable, each of the N linear vectors is padded at the beginning and end in this step to form a closed loop. The padded process can be understood as intercepting a number of elements from the end of the linear vector and padding them in front of the starting position of the linear vector, and intercepting the same number of elements from the beginning of the linear vector and padding them to the end. This ensures that even if a compression defect exists at the starting position of the linear vector after expansion, it can still be fully detected. Then, these N linear vectors with decreasing lengths are spliced ​​together from top to bottom, and the spliced ​​state is now an inverted trapezoid. The length of the linear vectors in each layer of the inverted trapezoid is adjusted to a uniform length, and the spliced ​​strip image can be finally obtained. Figure 8 , Figure 8 The diagram shows the enlarged defect in the strip image. The area marked by the red rectangle is Figure 7 The edge pressing defect marked in .

[0031] The resulting strip image, generated through this processing, integrates the outer ring of the effective display area image and includes all defects in the edge-pressing region. In subsequent inspections, a single inspection of the strip image is sufficient to detect all defects in the edge-pressing region. Furthermore, to further enhance the accuracy of the inspection results, the strip image can be subjected to mean filtering to eliminate interference factors such as texture.

[0032] Finally, at step S105, defects in the edge pressing area of ​​the display screen are detected based on the strip image. In some embodiments, the strip image contains all defects in the edge pressing area. Based on the strip image, all defects in the edge pressing area can be detected at one time. In one embodiment, the process of detecting defects in the edge pressing area of ​​the display screen based on the strip image can first construct a corresponding filter kernel, which includes a strip filter kernel and a vertical filter kernel. The strip filter kernel and the vertical filter respectively focus on defect detection in different directions. Using the strip filter kernel for morphological operations can effectively detect dark defects and bright defects, while using the vertical filter kernel to perform expansion operations on the operation results of the strip filter kernel and extract the middle row is more conducive to accurately locating the position of the defect. By using the strip filter kernel and the vertical filter kernel to perform morphological operations on the strip image in succession, the target linear vector corresponding to the strip image can be finally obtained.

[0033] Next, the target linear vector is segmented using a threshold. This process involves removing the leading and trailing padding elements to obtain a final linear vector response map. Each element of the final linear vector response map is then compared to a preset response threshold to identify defects. It should be noted that after traversing all elements in the final linear vector response map, a linear vector result map with defects marked is obtained.

[0034] Finally, the linear vector final response graph and the linear vector result graph are restored to the corresponding positions of the effective display area image to display the defects of the edge pressing area detected. Figure 9 , Figure 9 (A) shows the final response map of the linear vector after position restoration, Figure 9 (B) shows the linear vector result diagram after position restoration. It can be seen that the red rectangle in the lower right corner of the result diagram marks a pressure edge defect. It should be noted that for the convenience of observation, Figure 9 The result image shown in (B) is a portion of the restored effective display area image and does not represent the complete display effect.

[0035] In the above process, by constructing a strip filter kernel and a vertical filter kernel for the strip image and then performing morphological processing on the strip image, it is easier to locate the location of defects. Moreover, the constructed filter kernel can adapt to the edge type of the edge of the pressure area, regardless of whether it is a circular edge, a right-angle edge, or an irregular edge. At the same time, the strip image contains all defects in the pressure area, so only a single inspection of the strip image is required to detect all defects. In addition, the detected defects are restored to the original image (the image of the effective display area), and the specific location of the defect in the original image can be accurately marked. This is crucial for subsequent processes such as quality control and production line inspection.

[0036] Reference Figure 2 , to introduce the method 20 for detecting defects of liquid crystal display screens of the present application. It should be noted that the method 20 for detecting defects of liquid crystal display screens is the aforementioned Figure 1 A specific implementation of step S102 in , so the features described above can be similarly applied here. At step S201, the contour points of the region of interest mask are obtained. In some embodiments, the Graham scanning method can be used to repair the missing parts of the ROImask. In this process, the contour points of the ROImask need to be calculated first. As mentioned above, the ROImask is a binary image. Based on this, the contour extraction function can be used to extract the contour of the ROImask and return the extracted contour point set. The contour point set can be returned in the form of a list, and the elements in the list are the coordinates of the contour points.

[0037] Furthermore, at step S202, the contour points to be repaired are screened from the contour points. In some embodiments, the previously extracted contour points include contour points of the missing area of ​​the ROI mask. The missing area is precisely the area to be repaired. Therefore, it is necessary to screen out the contour points to be repaired corresponding to the outline of the missing area in order to perform subsequent repair work on it. In this process, the coordinates of the contour points are first sorted. That is, the contour point closest to the origin of the image coordinate system is used as the reference point, and then the polar angles of all remaining contour points relative to the reference point are calculated and sorted from small to large. If the polar angles are the same, they are sorted from near to far based on their distance from the reference point.

[0038] Next, the first two contour points sorted by polar angle (referred to here as P0 and P1 for ease of understanding) are taken and placed into the stack, with the next contour point P2 being the current contour point to be determined. Based on the first two contour points at the top of the stack, vectors P0P1 and P0P2 are created, and the cross product of vectors P0P1 and P0P2 is calculated. If the cross product is >= 0, it indicates that point P2 is located to the left of vector P0P1 or on the line where P0P1 is located. At this point, P2 can be determined as the contour point to be repaired and is pushed into the stack. It can be understood that the contour points in the stack at this time include P0, P1, and P2, with P2 at the top of the stack. Furthermore, a determination is made as to whether the current contour point to be determined is the last contour point sorted by polar angle. If not, the next contour point is set as the new current contour point to be determined. Continue to select the first two contour points P2 and P1 at the top of the stack and the new current contour point to be judged to form two vectors and calculate the cross product. Similarly, according to the judgment logic of whether the cross product is greater than or equal to 0, determine whether the contour point is the contour point to be repaired. If so, perform the same operation as the previous contour point. It can be understood that if the cross product of the vector composed of the current contour point to be judged and the first two elements at the top of the stack is less than 0, it can be determined that the contour point is not the contour point to be repaired, and there is no need to push it into the stack. Similarly, all contour points sorted by polar angles are judged as contour points to be repaired according to the above logic until the judgment of the last contour point in the sort is completed.

[0039] Through the above process, the contour points to be repaired from all the contour points can be screened out, thereby facilitating the subsequent repair operation of the ROI mask based on these contour points to be repaired.

[0040] Finally, in step S203, polygon fitting is performed based on the contour points to be repaired to repair the ROI mask. In some embodiments, an approximate polygon can be obtained by performing polygon fitting on the contour points to be repaired. A new mask is created based on the polygon and filled into the defective area of ​​ROImask, thus completing the repair work for ROImask. Figure 6(B) It can be seen that after repair, the missing area of ​​the ROI mask in the lower right corner has been completely repaired.

[0041] In the above embodiment, by repairing the missing portion of the ROImask caused by the edge pressing defect, the effective pixel area of ​​the defective area can be expanded, thereby improving the detection efficiency of the edge pressing defect.

[0042] Reference Figure 3 , to introduce the method 30 for detecting defects of liquid crystal display screens of the present invention. It should also be noted that the method 30 for detecting defects of liquid crystal display screens is the aforementioned Figure 1 This is a specific implementation of step S104 in

[15] , so the features described above can be similarly applied here. At step S301, the outer circle image is expanded into corresponding linear vectors by pixel layer. In some embodiments, after erasing the inner circle image, an outer circle image of N pixel layers can be obtained. This outer circle image is expanded into linear vectors starting from the outermost layer, i.e., the 0th layer of pixels. Then, the N-1 inner layers (1st, 2nd, 3rd, ... N-1 layers) are sequentially expanded into N-1 linear vectors, resulting in N linear vectors of successively decreasing length.

[0043] Furthermore, at step S302, the linear vectors are padded at the ends according to half the length of the preset strip filter kernel. In some embodiments, it is necessary to perform padded at the ends of the N linear vectors to prevent edge compression defects present at the expanded portion from being undetected. This padded process is performed at half the length of the preset strip filter kernel. This facilitates the subsequent morphological processing of the strip image formed by the linear vectors by the strip filter kernel.

[0044] In one embodiment, the half-value of the strip filter kernel length is represented as half. The padding process for a linear vector at a layer is as follows: half the elements at the end of the linear vector are padded to the front of the beginning of the vector, and half the elements before the beginning of the vector are padded to the back of the end of the vector. The padding at the beginning and end is to form a closed loop to ensure that defects at the starting position of the expansion can be fully detected.

[0045] Finally, at step S303, the linear vectors with the filling at the head and tail are spliced ​​to obtain a strip image. In some embodiments, after the above operations, N linear vectors with the filling at the head and tail and the lengths decreasing successively will be obtained. Then, based on the length sorting of these N linear vectors, they are spliced ​​together from long to short and from top to bottom, and an image with an inverted trapezoidal appearance can be obtained. For ease of distinction, it is referred to as the initial trapezoidal image here. Subsequently, the length W of the linear vector of the middle layer is used as a reference, and the linear vectors of other layers are adjusted to a unified length reference W using a bilinear interpolation method. At this time, a strip image with a height of N and a width of W will be obtained. Reference Figure 8 Schematic diagram of defect magnification in the shown bar image. It can be seen that the bar image contains a hemming defect (the area marked by the red rectangular box).

[0046] In the above embodiment, by taking the length W of the intermediate layer linear vector as a reference to adjust the lengths of the linear vectors of other layers, the pixel information loss of the bar image can be minimized as much as possible.

[0047] Figure 4 The flowchart of method 40 for detecting defects in a liquid crystal display screen according to the present application is shown. It can be understood that method 40 for detecting defects in a liquid crystal display screen can be a specific implementation manner in step S105 described above, so the features described above can be similarly applied herein. Figure 1 In step S401, a corresponding filter kernel is constructed for the bar image and morphological processing is performed on the bar image based on the filter kernel to obtain a corresponding target linear vector. In some embodiments, the filter kernels to be constructed include a bar filter kernel and a vertical filter kernel. The bar filter kernel can be understood as a filter that focuses on a specific direction during image processing, which can be horizontal, vertical, diagonal, etc. The width and height of the constructed bar filter kernel are [w, h], where w and h respectively represent the weight ranges in the width and height directions. By adjusting [w, h], hemming defects of different sizes or shapes can be detected. For example, when w≈h, point-like defects can be detected; when w>>h, horizontal defects can be detected; when w<<h, vertical defects can be detected. The vertical filter kernel is a filter that processes in the vertical direction. The vertical filter kernel pays more attention to the features in the vertical direction of the image. During the subsequent processing of the defect response map, it can concentrate the response extreme values of each column of the defect response map in the middle row of the bar image to extract the elements in the middle row to construct a linear vector with a width of W and a height of 1.

[0049] In a feasible embodiment, the constructed bar filter kernel and vertical filter kernel are two different matrices respectively. The width and height of the matrix of the bar filter kernel are [w, h], which are preset according to the specific morphology of the hemming defect. The width and height of the matrix of the vertical filter kernel are [1, N], where N is the height of the bar image, that is, the number of rows.

[0050] ​​​Next, a strip filter kernel is used to perform morphological operations on the strip image. Specifically, if detecting dark defects, the strip filter kernel is closed using the strip filter. This closing operation is used to fill small black spots or shadows (such as holes or cracks) in the strip image. The closed strip image is then subtracted from the original strip image to produce a dark defect response map. If detecting light defects, the strip filter kernel is opened using the strip filter kernel to remove small noise or bright spots. The original strip image is then subtracted from the opened strip image to produce a light defect response map. For ease of explanation, the dark defect response map and the light defect response map are collectively referred to as defect response maps.

[0051] Subsequently, a dilation operation is performed on the above-mentioned defect response image using a vertical filter kernel to expand the bright or dark areas in the defect response image so as to highlight the features in the vertical direction. After the dilation operation, the response extremes of the bright or dark spots in the defect response image will be concentrated in the middle row of the image, and then the elements of the middle row are extracted to construct a target linear vector with a width of W and a height of 1. It should be noted that the reason why only the elements of the middle row are extracted here to construct the target linear vector is because the length of the elements in the middle row has not been adjusted by bilinear interpolation, and each element has a one-to-one corresponding position on the original image (effective display area image), which can ensure the output of accurate defect positions.

[0052] In the above embodiment, by using the filter kernel to perform morphological operations on the strip image, the defect features are enhanced, which makes it easier to detect the edge pressing defect in the subsequent process.

[0053] Furthermore, at step S402, the target linear vector is thresholded and segmented to detect defects and obtain a final linear vector response map and a linear vector result map with defects marked. In some embodiments, the target linear vector obtained through the above processing needs to be thresholded and segmented to complete the detection of edge pressure defects. During this process, the first element of the target linear vector that contains padding is removed. This operation ensures that the output image maintains its original size and prevents invalid data introduced by the padding area from affecting the detection results. After removing the padding elements, the final linear vector response map is obtained.

[0054] The next step is to compare each element of the final linear vector response map with a preset response threshold to flag defects. The preset response threshold can be understood as a defect determination criterion, used to determine which regions of the final linear vector response map have response values ​​that can be considered true defects. Optionally, in one embodiment, the preset response threshold can be set empirically. In another embodiment, the preset response threshold can be set using an adaptive thresholding method based on local statistics. Specifically, the preset response threshold is adjusted based on the local brightness and contrast of the final linear vector response map, allowing it to adapt to varying image conditions.

[0055] When comparing each element of the final linear vector response graph with a preset response threshold, if a preset target number of elements are continuously greater than the preset response threshold, the corresponding elements can be marked as a defect. In one feasible embodiment, the preset target number can be a preset defect length threshold lenThd. If lenThd consecutive elements are greater than the preset response threshold, it is determined to be a defect. This means that the persistence of the defect is confirmed by "length," ensuring that a large, persistent defect is detected, rather than an occasional, localized fluctuation or noise. After traversing every element in the final linear vector response graph, a linear vector result graph is obtained, which, as can be understood, includes all marked defects.

[0056] In the above embodiment, by comparing a continuous preset target number of elements with the response threshold, some occasional noise or single irrelevant abnormal points can be effectively filtered out, effectively avoiding the situation where noise is misjudged as a defect, and improving the accuracy of defect detection.

[0057] Finally, at step S403, the linear vector final response map and the linear vector result map are restored to the effective display area image to display the detected defects in the edge pressure area of ​​the display screen. In some embodiments, the linear vector result map and the linear vector final response map can be mapped to the effective display area image according to the pixel position index to achieve the purpose of restoring the linear vector final response map and the linear vector result map to the effective display area image. The pixel position index refers to the position of each pixel in the image in the two-dimensional coordinate system of the effective display area image. After restoration, the original effective display area image can display the detected defects. Figure 9 , Figure 9 (A) is the final response diagram of the linear vector after position restoration. Figure 9 (B) is the linear vector result diagram after position restoration, where: Figure 9 The detected blank-holding defect in (B) is marked with a red rectangular frame.

[0058] Through the above operations, the position and shape of the defects in the actual image can be intuitively displayed, which can help quality control personnel or inspection system operators to more easily understand the inspection results and quickly determine whether further processing is required.

[0059] Reference Figure 10 , an embodiment of the present application also provides a device 100 for detecting defects in a liquid crystal display screen, comprising: an acquisition module 1001, for acquiring an effective display area image of a display screen; a repair module 1002, for repairing a region of interest mask of the effective display area image, wherein the region of interest mask determines the effective pixel range of the effective display area image for edge pressure defect detection; a removal module 1003, for removing the inner circle image of the repaired region of interest mask from the effective display area image to obtain an outer circle image with a preset number of pixel layers; a splicing module 1004, for expanding and splicing the outer circle image into a strip image; and a detection module 1005, for detecting defects in the edge pressure area of ​​the display screen based on the strip image.

[0060] Figure 11 Schematic diagram of a system for detecting defects in a liquid crystal display according to an embodiment of the present application. Figure 11 As shown, the system 110 may include a device 1101 for detecting defects in a liquid crystal display according to an embodiment of the present application, as well as its peripheral devices and an external network, to achieve the aforementioned combination. Figure 1 - Figure 4 The method for detecting defects of a liquid crystal display screen according to an embodiment of the present application is described.

[0061] like Figure 11 As shown in , a device 1101 for detecting defects in liquid crystal displays may include a CPU 1111, which may be a general-purpose CPU, a dedicated CPU, or other execution unit for information processing and program execution. Furthermore, the device 1101 for detecting defects in liquid crystal displays may also include a mass storage device 1112 and a read-only memory (ROM) 1113. The mass storage device 1112 may be configured to store various types of data. In the embodiment of the present application, this may include an image of the active display area, a stripe image, and the like. Furthermore, the ROM 1113 may be configured to store data required for initializing the various functional modules of the device 1101 for detecting defects in liquid crystal displays, basic input / output (BIO) drivers for the system, and booting the operating system.

[0062] Furthermore, the system 110 may also include other hardware platforms or components, such as the illustrated tensor processing unit (TPU) 1114, graphics processing unit (GPU) 1115, field programmable gate array (FPGA) 1116, and machine learning unit (MLU) 1117. It will be appreciated that although a variety of hardware platforms or components are shown in the system 110, these are merely exemplary and non-limiting, and those skilled in the art may add or remove corresponding hardware as needed.

[0063] The device 1101 for detecting defects in liquid crystal displays further includes a communication interface 1118, which allows it to connect to a local area network / wireless local area network (LAN / WLAN) 1105 via the communication interface 1118, and further connect to a local server 1106 or the Internet 1105 via the LAN / WLAN. Alternatively or additionally, the device 1101 for detecting defects in liquid crystal displays according to embodiments of the present application may also connect directly to the Internet or a cellular network via the communication interface 1118 using wireless communication technology, such as third-generation ("3G"), fourth-generation ("4G"), or fifth-generation ("5G") wireless communication technology. In some application scenarios, the device 1101 for detecting defects in liquid crystal displays may also access a server 1108 on an external network and possibly a database 1109, as needed, to obtain various known data, such as an image of the active display area and a bar image.

[0064] Peripheral devices of the device 1101 for detecting defects in liquid crystal displays may include a display device 1102, an input device 1103, and a data transmission interface 1104. In one embodiment, the display device 1102 may include, for example, one or more speakers and / or one or more visual displays, configured to provide voice prompts and / or display images and videos of the computational process or final results of the device 1101 for detecting defects in liquid crystal displays. The input device 1103 may include, for example, a keyboard, a capture camera, or other input buttons or controls. The data transmission interface 1104 may include, for example, a serial interface, a parallel interface, a universal serial bus (USB), a small computer system interface (SCSI), serial ATA, FireWire, PCI Express, or a high-definition multimedia interface (HDMI), configured for data transmission and interaction with other devices or systems. According to the solution of the present application, the data transmission interface 1104 can transmit coordinate data, etc. The CPU 1111, mass storage 1112, read-only memory 1113, TPU 1114, GPU 1115, FPGA 1116, MLU 1117, and communication interface 1118 of the device 1101 for detecting defects in liquid crystal displays of the present application can be interconnected via a bus 1119, and can exchange data with peripheral devices via this bus. In one embodiment, the CPU 1111 can control the other hardware components and peripheral devices in the device 1101 for detecting defects in liquid crystal displays via this bus 1119.

[0065] It should also be understood that any module, unit, component, server, computer, terminal, or device that executes instructions of the examples of this application may include or otherwise access computer-readable media, such as storage media, computer storage media, or data storage devices (removable and / or non-removable) such as magnetic disks, optical disks, or tapes. Computer storage media may include volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable instructions, data structures, program modules, or other data.

[0066] The present application also discloses a computer-readable storage medium storing program instructions adapted to be loaded and executed by a processor: obtaining an image of an effective display area of ​​a display screen; repairing a region of interest (ROI) mask of the effective display area image, wherein the ROI mask determines the effective pixel range of the effective display area image for edge-pressing defect detection; removing the inner ring image of the repaired ROI mask from the effective display area image to obtain an outer ring image with a preset number of pixel layers; unfolding and splicing the outer ring image into a stripe image; and detecting defects in the edge-pressing area of ​​the display screen based on the stripe image. Therefore, when the solution of the present application is embodied in the form of a software product (computer-readable storage medium), the software product may be stored in a memory and may include instructions for causing a computer device (e.g., a personal computer, server, etc.) to execute some or all of the steps of the method described in the embodiments of the present application. The aforementioned memory may include, but is not limited to, various media capable of storing program code, such as a USB flash drive, a flash drive, a read-only memory (ROM), a random access memory (RAM), a removable hard drive, a magnetic disk, or an optical disk.

[0067] Although multiple embodiments of the present application have been shown and described herein, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art can conceive of many changes, modifications, and alternatives without departing from the thought and spirit of the present application. It should be understood that in the process of practicing the present application, various alternatives to the embodiments of the present application described herein can be adopted. The accompanying claims are intended to define the scope of protection of the present application and therefore cover equivalents or alternatives within the scope of these claims.

Claims

1. A method for detecting defects in a liquid crystal display screen, characterized in that: include: Acquire the effective display area image of the display screen; Repairing the region of interest mask of the effective display area image, wherein the region of interest mask determines the effective pixel range of the effective display area image for edge pressing defect detection; Removing the repaired inner circle image of the interest region mask from the effective display area image to obtain an outer circle image with a preset number of pixel layers; Expanding the outer circle image and splicing it into a strip image; Based on the stripe image, defects in the edge pressing area of ​​the display screen are detected.

2. The method according to claim 1, characterized in that The repairing of the interest region mask of the effective display area image comprises: Obtaining contour points of the region of interest mask; Selecting contour points to be repaired from the contour points; Polygon fitting is performed based on the contour points to be repaired to repair the region of interest mask.

3. The method according to claim 1, characterized in that The step of expanding the outer circle image and splicing the outer circle image into a strip image comprises: Expand the outer circle image into corresponding linear vectors according to pixel layers; Filling the linear vector at the beginning and the end according to half the length of the preset strip filter kernel; The linear vectors after being filled at the head and tail are spliced ​​to obtain the strip image.

4. The method according to claim 3, characterized in that The step of splicing the linear vectors after filling the head and tail to obtain the strip image comprises: Based on the length sorting of the linear vectors, the linear vectors are sequentially spliced ​​together from top to bottom to obtain an initial trapezoidal image; Determining a length reference of the initial trapezoidal image; Based on the length reference, the lengths of the linear vectors of each layer of the initial trapezoidal image are adjusted to be consistent to obtain the strip image.

5. The method according to claim 1, characterized in that The detecting defects of the edge pressing area of ​​the display screen based on the strip image further comprises: Constructing a corresponding filter kernel for the strip image and performing morphological processing on the strip image based on the filter kernel to obtain a corresponding target linear vector; Performing threshold segmentation on the target linear vector to detect the defect and obtain a linear vector final response map and a linear vector result map marked with the defect; The linear vector final response map and the linear vector result map are restored to the effective display area image to display the detected defects in the edge pressing area of ​​the display screen.

6. The method according to claim 5, characterized in that The step of constructing a corresponding filter kernel for the strip image and performing morphological processing on the strip image based on the filter kernel comprises: Constructing a strip filter kernel and a vertical filter kernel for the strip image; Based on the strip filter kernel, performing morphological operation on the strip image to obtain a defect detection response map; Based on the vertical filter kernel, a dilation operation is performed on the defect detection response map to extract the target linear vector.

7. The method according to claim 5, characterized in that The threshold segmentation of the target linear vector comprises: Removing the elements filled at the beginning and the end of the target linear vector to obtain a final response graph of the linear vector; Comparing each element in the linear vector final response map with a preset response threshold; If there are a preset target number of elements that are all greater than the preset response threshold, the corresponding element is marked as a defect; After the comparison of each element in the linear vector final response diagram is completed, the linear vector result diagram marked with the defect is obtained.

8. A device for detecting defects in a liquid crystal display screen, characterized in that: include: An acquisition module, used to acquire an image of an effective display area of ​​a display screen; A repair module, used for repairing the interest region mask of the effective display area image, wherein the interest region mask determines the effective pixel range of the effective display area image for edge pressing defect detection; A removal module, used for removing the repaired inner circle image of the interest region mask from the effective display area image to obtain an outer circle image with a preset number of pixel layers; A splicing module, used for expanding the outer circle image and splicing it into a strip image; The detection module is used to detect defects in the edge pressing area of ​​the display screen based on the strip image.

9. A device for detecting defects in a liquid crystal display screen, characterized in that: include: processor; A memory storing program instructions for detecting defects of a liquid crystal display screen, wherein when the program instructions are executed by the processor, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions for detecting defects of a liquid crystal display screen. When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images