A method and related device for detecting multi-layer foreign matter on a display screen

Abstract

The present application discloses a method and related device for detecting multi-layer foreign matter on a display screen, which is used to improve the efficiency and quality of screen defect detection. The method for detecting multi-layer foreign matter on a display screen of the present application includes: respectively obtaining target positioning heights of multiple levels of an LCD screen; respectively obtaining image information of multiple levels through a camera; respectively performing differential processing on the image information of multiple levels to obtain multiple contrast enhancement maps; respectively obtaining multiple morphological features according to the multiple contrast enhancement maps; respectively calculating the multiple morphological features to obtain multiple defect feature values, the defect feature values ​​representing the difference between the defect and the background; comparing the numerical values ​​of multiple defect feature values ​​to obtain the maximum defect feature value; determining the level corresponding to the maximum defect feature value as the level corresponding to the defect; and calculating the size of the defect according to the contrast enhancement map of the level corresponding to the defect and the physical size of the LCD screen.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of screen defect detection, and in particular to a method and related device for detecting multi-layer foreign matter on a display screen. Background Art

[0002] In the field of display technology, the manufacturing process of display screens is extremely complex, involving the superposition and integration of multiple precision layers. These layers include CG layer (cover glass), OCA layer (optical adhesive), upper POL layer (polarizer), PANEL layer (pixel layer), lower POL layer (polarizer) and BLU (backlight layer). During the manufacturing process of the display screen, due to various factors such as material properties, processing environment, operating technology, etc., stains may remain on different layers. Although these stains are small, they have a crucial impact on the clarity and overall quality of the display screen. They may cause blur, bright spots, dark spots and other problems on the display screen, thereby affecting the user's visual experience. In order to solve this problem, the existing processing method is to observe the various layers of the display screen with the human eye to find and locate the stains.

[0003] However, although the manual inspection method can visually see the presence and location of stains, its limitations are also very obvious. Due to the limited resolution and accuracy of the human eye, manual inspection is prone to misjudgment, resulting in incorrect determination of the level of the stain and large calculation errors of the corresponding defect size, which in turn reduces the efficiency of display manufacturing and the quality of the display. Summary of the invention

[0004] The present application discloses a method and a related device for detecting multi-layer foreign matter on a display screen, which are used to improve the efficiency and quality of screen defect detection.

[0005] The first aspect of the present application discloses a method for detecting multi-layer foreign matter on a display screen, comprising:

[0006] Taking the target positioning height of the pixel layer of the LCD screen as a reference, respectively obtaining the target positioning heights of multiple levels of the LCD screen;

[0007] According to the target positioning heights of the multiple levels, respectively obtain image information of the multiple levels through cameras;

[0008] Performing differential processing on the image information of the multiple levels respectively to obtain multiple contrast enhancement images;

[0009] Obtaining a plurality of morphological features according to the plurality of contrast enhancement images respectively, wherein the morphological features are morphological features corresponding to the defects on the LCD screen displayed at the plurality of levels respectively;

[0010] Calculating the multiple morphological features respectively to obtain multiple defect feature values, wherein the defect feature values ​​represent the difference between the defect and the background;

[0011] Comparing the numerical values ​​of the plurality of defect characteristic quantities to obtain the maximum defect characteristic quantity value;

[0012] Determining the level corresponding to the maximum defect characteristic value as the level corresponding to the defect;

[0013] The size of the defect is calculated according to the contrast enhancement map of the level corresponding to the defect and the physical size of the LCD screen.

[0014] Optionally, before respectively acquiring the target positioning heights of multiple levels of the LCD screen based on the target positioning height of the pixel layer of the LCD screen, the method further includes:

[0015] Acquire a first height by using a laser ranging sensor, where the first height is a vertical distance between the laser ranging sensor at an initial point and the surface of the LCD screen;

[0016] Acquire an initial positioning height of a pixel layer of the LCD screen, wherein a measurement reference point of the initial positioning height is the initial point position;

[0017] Acquire a second height, where the second height is a vertical distance between the laser ranging sensor at a target test point and the surface of the LCD screen;

[0018] Calculate a relative offset height according to the first height and the second height;

[0019] The target positioning height of the pixel layer is obtained by calculation according to the relative offset height and the initial positioning height.

[0020] Optionally, taking the target positioning height of the pixel layer of the LCD screen as a reference, respectively acquiring the target positioning heights of multiple levels of the LCD screen includes:

[0021] respectively acquiring a plurality of height differences between the pixel layer and the plurality of levels by means of the laser ranging sensor;

[0022] Calculate and obtain target positioning heights of multiple levels according to the multiple height differences and the target positioning heights of the pixel layers respectively.

[0023] Optionally, performing differential processing on the image information of the multiple levels respectively to obtain multiple contrast enhancement images includes:

[0024] Performing grayscale transformation on the image information of the multiple levels respectively to obtain grayscale images of the multiple levels;

[0025] Respectively performing noise reduction and background interference reduction processing on the grayscale images of the multiple levels to obtain pre-processed images of the multiple levels;

[0026] Convolution calculations are performed on the preprocessed images of the multiple levels respectively to obtain multiple contrast enhancement images.

[0027] Optionally, performing convolution calculations on the preprocessed images of the multiple levels respectively to obtain multiple contrast enhancement images includes:

[0028] Get the target convolution formula, which is as follows:

[0029] ;

[0030] Among them, the I DF is a contrast enhancement image, I is a preprocessing image, and k x1 , the k x2 are two convolution kernels in the horizontal direction corresponding to the preprocessed image, and the k y1 , the k y2 are two convolution kernels in the vertical direction corresponding to the preprocessing image, and weight is a weight enhancement coefficient;

[0031] According to the target convolution formula, the preprocessed images of the multiple levels are calculated respectively to obtain multiple contrast enhancement images.

[0032] Optionally, obtaining a plurality of morphological features according to the plurality of contrast enhancement images respectively comprises:

[0033] According to the adaptive threshold algorithm, defect area detection is performed on the multiple contrast enhancement images respectively to obtain multiple morphological features.

[0034] Optionally, calculating the size of the defect according to the contrast enhancement map of the level corresponding to the defect and the physical size of the LCD screen includes:

[0035] Obtaining the physical size of the LCD screen;

[0036] According to the physical size, obtaining a pixel equivalent of the contrast enhancement image;

[0037] According to the defect area on the contrast enhancement image, obtaining the long side value and the wide side value of the minimum circumscribed rectangle of the defect area;

[0038] The size of the defect is calculated based on the long side value and the wide side value.

[0039] The second aspect of the present application discloses a system for detecting multi-layer foreign matter on a display screen, comprising:

[0040] A target maximum definition unit, used to obtain target positioning heights of multiple levels of the LCD screen respectively based on the target positioning height of the pixel layer of the LCD screen;

[0041] An image information unit, configured to obtain image information of the multiple levels through cameras respectively according to target positioning heights of the multiple levels;

[0042] A differential processing unit, used to perform differential processing on the image information of the multiple levels respectively to obtain multiple contrast enhancement maps;

[0043] A morphological feature unit, used to obtain a plurality of morphological features according to a plurality of contrast enhancement images, wherein the morphological features are morphological features corresponding to the defects on the LCD screen displayed at a plurality of levels;

[0044] A defect feature value unit, used to calculate the multiple morphological features respectively to obtain multiple defect feature values, wherein the defect feature values ​​represent the difference between the defect and the background;

[0045] A comparing unit, used to compare the numerical values ​​of the plurality of defect characteristic values ​​to obtain a maximum defect characteristic value;

[0046] A determining unit, configured to determine the level corresponding to the maximum defect characteristic value as the level corresponding to the defect;

[0047] The defect size unit is used to calculate the size of the defect according to the contrast enhancement map of the level corresponding to the defect and the physical size of the LCD screen.

[0048] A third aspect of the present application provides an electronic device, including:

[0049] Processor, memory, input-output unit, and bus;

[0050] The processor is connected to the memory, the input and output unit, and the bus;

[0051] The memory stores a program, and the processor calls the program to execute the method for detecting multi-layer foreign matter on a display screen according to the first aspect and any optional method according to the first aspect.

[0052] A fourth aspect of the present application provides a computer-readable storage medium, on which a program is stored. When the program is executed on a computer, the method for detecting multi-layer foreign matter on a display screen according to the first aspect and any optional method according to the first aspect is executed.

[0053] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0054] The method for detecting multi-layer foreign matter on a display screen provided by the present application takes the target positioning height of the pixel layer of the LCD screen as a reference, and obtains the target positioning heights of multiple levels of the LCD screen respectively; obtains the image information of the multiple levels through a camera respectively according to the target positioning heights of the multiple levels; performs differential processing on the image information of the multiple levels respectively to obtain multiple contrast enhancement maps; obtains multiple morphological features respectively according to the multiple contrast enhancement maps, and the morphological features are morphological features corresponding to the defects on the LCD screen displayed at the multiple levels respectively; calculates the multiple morphological features respectively to obtain multiple defect feature values, and the defect feature values ​​represent the difference between the defect and the background; compares the numerical values ​​of the multiple defect feature values ​​to obtain the maximum defect feature value; determines the level corresponding to the maximum defect feature value as the level corresponding to the defect; and calculates the size of the defect according to the contrast enhancement map of the level corresponding to the defect and the physical size of the LCD screen. The method of the present application takes the pixel layer of the LCD screen as the benchmark, takes images according to the target positioning heights of multiple layers, and distinguishes the defects by using the characteristics of the corresponding layers; then, by processing and analyzing each layer of the image, the contrast enhancement map corresponding to the image is obtained, and the defect feature quantity is calculated according to the contrast enhancement map, and the size is compared to further find the actual level of the defect, and the size of the defect is calculated at the same time, and finally the level of the defect and the size of the defect can be accurately output. Thus, the automated screen defect layer positioning and size measurement are realized, and the contrast enhancement map ensures the accuracy of data and judgment, and improves the efficiency and quality of production and manufacturing work. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0056] Figure 1 A schematic diagram of an embodiment of a method for detecting multi-layer foreign matter on a display screen of the present application;

[0057] Figure 2 A schematic diagram of an embodiment of a method for obtaining a target positioning height of a pixel layer in the present application;

[0058] Figure 3 A schematic diagram of an embodiment of a method for obtaining target positioning heights at multiple levels in the present application;

[0059] Figure 4 A schematic diagram of an embodiment of a method for differentially processing image information of the present application;

[0060] Figure 5A schematic diagram of an embodiment of a method for calculating defect size in the present application;

[0061] Figure 6 A schematic diagram of an embodiment of a system for detecting multi-layer foreign matter on a display screen of the present application;

[0062] Figure 7 This is a schematic diagram of an embodiment of an electronic device of the present application. DETAILED DESCRIPTION

[0063] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0064] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0065] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0066] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" 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 "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0067] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0068] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0069] In the field of display technology, especially in the process of making display screens, due to the complexity of the manufacturing process, stains may exist at different levels. These stains may appear at different levels such as CG layer (cover glass), OCA layer (optical adhesive), upper POL layer (polarizer), PANEL layer (pixel layer), lower POL layer (polarizer), BLU (backlight layer). The presence of these stains may affect the clarity and quality of the display screen, so they need to be detected and processed. First, observe the various levels of the display screen with the human eye to find the presence of stains. If stains are found, further observe at which level the stains appear and measure the size of the stains. The advantage of this method is that the presence and location of the stains can be intuitively seen, but the disadvantage is that it is inefficient, the accuracy is not high, and it is easily affected by human factors. Since manual observation is required, the speed is slow and cannot meet the needs of large-scale production. Secondly, due to the limited resolution and accuracy of the human eye, it is easy to make misjudgments, resulting in incorrect determination of the level of the defect and large errors in the calculation of the corresponding defect size. Thirdly, due to the manual defect size check, the size detection is inaccurate and the error is large, which makes it impossible to classify according to the size of the defect. Therefore, accurate size judgment is extremely important. These problems limit the application of existing technologies in display screen stain detection and classification, and cannot effectively improve the product yield.

[0070] Based on this, the present application discloses a method and related device for detecting multi-layer foreign matter in a display screen, which are used to improve the efficiency and quality of screen defect detection.

[0071] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0072] The method of the present application can be applied to a server, a device, a terminal or other devices with logic processing capabilities, and the present application does not limit this. For the convenience of description, the following description is made by taking the execution subject as an example of a terminal.

[0073] See also Figure 1 The present application provides an embodiment of a method for detecting multi-layer foreign matter in a display screen, comprising:

[0074] 101, taking the target positioning height of the pixel layer of the LCD screen as a reference, respectively obtaining target positioning heights of multiple layers of the LCD screen;

[0075] In this embodiment, in the hierarchical structure of the LCD screen, the pixel layer is usually located at the top layer and directly contacts the user. Other layers such as the backlight layer, liquid crystal layer, filter layer, etc. are all located below the pixel layer, which affects the picture clarity of the pixel layer. Therefore, taking the target positioning height of the pixel layer as a reference, the target positioning height of other layers of the LCD screen (for example: cover glass layer, optical adhesive layer, upper polarizer layer, lower polarizer layer and backlight layer, etc.) is obtained through the height position relationship between the pixel layer and other layers, and through subsequent steps, we can accurately determine the layer where the defect is located. The target positioning height of the pixel layer is confirmed by moving the camera device, that is, on a pre-selected Z axis (the Z axis passes through the LCD screen), the camera device is moved up and down. When the camera device can capture the clearest image, the position of the camera device is fixed, and then the distance between the current camera device and the pixel layer is obtained, and this distance is determined as the target positioning height of the pixel layer.

[0076] 102, acquiring image information of multiple levels through cameras according to target positioning heights of multiple levels;

[0077] In this embodiment, in order to accurately locate the specific location of the defect, that is, to find the specific level where the defect occurs in the LCD screen, each level should be analyzed and eliminated to screen out the level where the defect occurs. According to all the target positioning heights in step 101, adjust the camera (in this embodiment, the camera can use a high-resolution camera or a small-field camera to ensure that the image information captured is the clearest, which is not limited here), capture each level of the LCD screen, and obtain image information of each level.

[0078] 103, performing differential processing on the image information of the multiple levels respectively to obtain multiple contrast enhancement images;

[0079] In this embodiment, the image information of multiple levels is differentiated to distinguish the defect from the background as much as possible, that is, to increase the difference between the defect and the background, so as to ensure that the specific location of the defect can be accurately found. Each pixel in the image can be compared one by one, and the difference between it and the adjacent pixels in terms of brightness, color, etc. can be calculated. This method can accurately identify tiny defects; the image can also be divided into multiple small areas, and then the difference between each area and the adjacent area is compared. This method can reduce the computational complexity while retaining the overall structure of the image. The image after differentiation processing will highlight the difference part in the image, that is, the potential defect area. Then, the brightness value of the image can be linearly mapped to a new range to expand the brightness difference and obtain a contrast enhancement map; the brightness value of the image information can also be transformed using a nonlinear function (such as a logarithmic function, an exponential function, etc.) to obtain a contrast enhancement map with a more significant contrast enhancement effect.

[0080] 104, obtaining a plurality of morphological features according to the plurality of contrast enhancement images, wherein the morphological features are morphological features corresponding to the defects on the LCD screen displayed at a plurality of levels;

[0081] In this embodiment, the morphological features refer to the shape, size, color and other features of the defect in the image. Due to the multi-layer structure of the LCD screen, the defect may present different morphological features at different levels. Morphological analysis is performed on the contrast enhancement image of each layer to extract the morphological features of the defect. Specifically, defect area detection can be performed on multiple contrast enhancement images according to an adaptive threshold algorithm to obtain multiple morphological features, and then the morphological features of the defect at each level are recorded for subsequent analysis.

[0082] 105, respectively calculating the plurality of morphological features to obtain a plurality of defect feature values, wherein the defect feature values ​​represent the difference between the defect and the background;

[0083] In this embodiment, the defect characteristic value is a quantitative index used to measure the difference between the defect and the background. The defect characteristic value can be obtained by calculating the contrast, brightness difference, color difference and other parameters between the defect and the background. Specifically, image processing software can be used to calculate the morphological features of each layer to obtain the defect characteristic value, and then record the characteristic value of the defect on each layer for subsequent comparison.

[0084] 106, comparing the numerical values ​​of the plurality of defect characteristic quantities to obtain the maximum defect characteristic quantity value;

[0085] In this embodiment, the maximum defect characteristic value indicates that the defect is most obvious on a certain layer, that is, the layer is the level where the defect is located. According to the defect characteristic values ​​corresponding to different levels obtained in step 105, the size is compared to find the maximum defect characteristic value. Since the captured image information is the clearest image, the defect is also the clearest at this time, and the grayscale value of the corresponding defect area is the lowest, while the background is composed of R, G, and B sub-pixels, and the corresponding grayscale image appears white. Therefore, when a defect exists at a certain level, it can be known that when the defect at a certain level is the clearest, the corresponding defect characteristic value is the largest, that is, the image information corresponding to the maximum defect characteristic value is the image information of the level where the defect is located, thereby locating the level where the defect is located. It should be noted that since the surface defects may move due to human factors during detection, the defect characteristic value corresponding to each level will be empty, and the corresponding level is defined as the surface layer.

[0086] Specifically, the defect feature values ​​at all levels can be sorted to form a feature value list, each feature value corresponding to a specific level. The feature value list is traversed, each feature value is compared, and the maximum value in the list is found, that is, the maximum defect feature value.

[0087] 107, determining the level corresponding to the maximum defect characteristic value as the level corresponding to the defect;

[0088] In this embodiment, the corresponding level is found according to the maximum defect feature value, and then the relevant information of the level where the defect is located, including the level number, name, defect feature value, etc., is recorded for subsequent defect classification, statistics and analysis. When comparing feature values, the accuracy and reliability of the data must be ensured. Avoid incorrect level judgments due to data errors or improper processing.

[0089] 108 , calculating the size of the defect according to the contrast enhancement map of the level corresponding to the defect and the physical size of the LCD screen.

[0090] In this embodiment, the size of the defect is an important parameter for evaluating the severity of the defect. The actual size of the defect can be calculated by measuring the pixel size of the defect in the contrast enhancement image and combining it with the physical size of the LCD screen. Specifically, in the contrast enhancement image, the pixel size of the defect is measured using image processing software. According to the physical size of the LCD screen and the pixel resolution of the camera, the pixel size is converted to the actual size, and then the actual size of the defect is recorded for subsequent analysis and processing.

[0091] The method for detecting multi-layer foreign matter on a display screen provided by the present application takes the target positioning height of the pixel layer of the LCD screen as a reference, and obtains the target positioning heights of multiple levels of the LCD screen respectively; obtains the image information of the multiple levels through a camera respectively according to the target positioning heights of the multiple levels; performs differential processing on the image information of the multiple levels respectively to obtain multiple contrast enhancement maps; obtains multiple morphological features respectively according to the multiple contrast enhancement maps, and the morphological features are morphological features corresponding to the defects on the LCD screen displayed at the multiple levels respectively; calculates the multiple morphological features respectively to obtain multiple defect feature values, and the defect feature values ​​represent the difference between the defect and the background; compares the numerical values ​​of the multiple defect feature values ​​to obtain the maximum defect feature value; determines the level corresponding to the maximum defect feature value as the level corresponding to the defect; and calculates the size of the defect according to the contrast enhancement map of the level corresponding to the defect and the physical size of the LCD screen. The method of the present application takes the pixel layer of the LCD screen as the benchmark, takes images according to the target positioning heights of multiple layers, and distinguishes the defects by using the characteristics of the corresponding layers; then, by processing and analyzing each layer of the image, the contrast enhancement map corresponding to the image is obtained, and the defect feature quantity is calculated according to the contrast enhancement map, and the size is compared to further find the actual level of the defect, and the size of the defect is calculated at the same time, and finally the level of the defect and the size of the defect can be accurately output. Thus, the automated screen defect layer positioning and size measurement are realized, and the contrast enhancement map ensures the accuracy of data and judgment, and improves the efficiency and quality of production and manufacturing work.

[0092] See also Figure 2 The present application provides an embodiment of a method for obtaining a target positioning height at a pixel layer, including:

[0093] 201, obtaining a first height through a laser ranging sensor, where the first height is a vertical distance between the laser ranging sensor at an initial point and the surface of the LCD screen;

[0094] In this embodiment, a point below the LCD screen is taken as the initial point, the laser distance sensor is set at the initial point, and the Z axis is set so that the laser distance sensor moves up and down along the Z axis to measure the relevant distance. At the initial point, the laser distance sensor will emit a laser beam to the surface of the LCD screen, and measure the time from the laser emission to the reflection back, and calculate the vertical distance between the sensor and the LCD screen surface according to the speed of light and time, that is, the first height H1.

[0095] 202, obtaining an initial positioning height of a pixel layer of the LCD screen, wherein a measurement reference point of the initial positioning height is an initial point position;

[0096] In this embodiment, the camera is set on the same Z axis as the laser distance sensor. At this time, the Z axis still passes through the initial point position. The camera is moved up and down. When the camera can capture the clearest image of the pixel layer, the camera position is fixed, and the laser distance sensor is moved to the camera position. At this time, the travel distance of the laser distance sensor is the initial positioning height H2 of the pixel layer of the LCD screen. The initial positioning height H2 is used as a reference value for the subsequent acquisition of the target positioning height of the pixel layer.

[0097] 203, obtaining a second height, where the second height is a vertical distance between the laser ranging sensor at the target test point and the surface of the LCD screen;

[0098] In this embodiment, a target test point is taken on the same horizontal plane as the initial point, and the target test point is still below the LCD screen. The laser distance sensor is moved to the target test point, and the vertical distance between the laser distance sensor and the LCD screen surface is collected again, that is, the second height H3.

[0099] 204, calculating and obtaining a relative offset height according to the first height and the second height;

[0100] In this embodiment, in general, the surface height of the LCD screen is usually not on the same horizontal plane, so there is a difference between the first height H1 and the second height H3, that is, a relative offset height ΔH, and ΔH is calculated by the following formula: .

[0101] 205 , calculating and obtaining a target positioning height of the pixel layer according to the relative offset height and the initial positioning height.

[0102] In this embodiment, in order to determine the height at which the pixel layer of the LCD screen presents the clearest image at the target test point position, after obtaining the relative offset height ΔH and the initial positioning height, the target positioning height D corresponding to each target test point of the pixel layer can be calculated according to the following formula: .

[0103] See also Figure 3 The present application provides an embodiment of a method for obtaining target positioning heights at multiple levels, including:

[0104] 301, respectively acquiring a plurality of height differences between a pixel layer and a plurality of layers through a laser ranging sensor;

[0105] In this embodiment, at the target test point position, the height difference between the pixel layer and the other multiple layers of the LCD screen is obtained by a laser ranging sensor. Specifically, the laser ranging sensor can emit laser pulses to each layer and receive the reflected laser pulses. By measuring the time difference of the laser pulses reflected from each layer, the distance between the sensor and the reflective surface of each layer is calculated using the laser ranging formula. Then, by comparing the distances between different layers, multiple height differences between the pixel layer and multiple layers can be obtained.

[0106] 302 , calculate and obtain target positioning heights of multiple levels according to multiple height differences and target positioning heights of pixel layers respectively.

[0107] In this embodiment, after obtaining the target positioning height of the pixel layer in step 205 and the multiple height differences in step 301, the target positioning height of the pixel layer is added or subtracted from the multiple height differences to obtain the target positioning height corresponding to each level at the target test point. The target positioning height of each level is used for subsequent placement of cameras to capture the clearest image of each level and improve the accuracy of the data.

[0108] See also Figure 4 The present application provides an embodiment of a method for differentially processing image information, comprising:

[0109] 401, performing grayscale transformation on image information of multiple levels respectively to obtain grayscale images of multiple levels;

[0110] In this embodiment, grayscale transformation is to convert a color image into a grayscale image, or to transform an existing grayscale image, so as to improve the display effect of the image or enhance certain features of the image. Specific grayscale transformation methods include: grayscale transformation formula conversion method, image black and white inversion method, logarithmic transformation method, power law (gamma) transformation method, and piecewise linear transformation method. By applying at least one of the above grayscale transformation methods to image information at multiple levels, grayscale images at multiple levels can be obtained.

[0111] 402, performing noise reduction and background interference reduction processing on the grayscale images of multiple levels respectively to obtain pre-processed images of multiple levels;

[0112] In this embodiment, in order to improve the clarity and quality of the image, and to improve the recognition accuracy of the target object, the grayscale images of multiple levels can be subjected to noise reduction and background interference reduction processing. Filter-based methods (such as median filtering, Wiener filtering, etc.) and model-based methods (such as low-rank matrix approximation, graph regularization, etc.) are commonly used noise reduction methods. In addition, deep learning technologies such as convolutional neural networks (CNNs) can also be used for noise reduction processing. Specifically, applying noise reduction processing methods to grayscale images of multiple levels can effectively remove noise from the image. Background subtraction, threshold segmentation, morphological processing, etc. are commonly used background interference reduction methods. These methods can be selected and applied according to the characteristics of the background and grayscale images. Specifically, by further applying the background interference reduction processing method to the grayscale image after noise reduction processing, a clearer pre-processed image of multiple levels can be obtained.

[0113] 403 , performing convolution calculations on the preprocessed images of multiple levels respectively to obtain multiple contrast enhanced images.

[0114] In this embodiment, the convolution operation is a basic operation in image processing, which is based on the process of multiplying and summing a kernel (or convolution kernel, filter) with an image. The purpose of the convolution operation is to perform various processes such as smoothing, sharpening, and edge detection on the image, thereby enhancing the contrast or other features of the image. Specifically, according to the following target convolution formula, convolution operations are performed on pre-processed images of multiple levels respectively:

[0115] ;

[0116] Among them, I DF is the contrast enhancement image, I is the preprocessing image, k x1 , k x2 are two convolution kernels in the horizontal direction corresponding to the preprocessed image, k y1 , k y2 are two convolution kernels in the vertical direction corresponding to the preprocessed image, and weight is the weight enhancement coefficient. It should be noted that when performing convolution operations on preprocessed images at different levels, the parameters should be kept consistent.

[0117] See also Figure 5 The present application provides an embodiment of a method for calculating defect size, comprising:

[0118] 501, obtaining the physical size of the LCD screen;

[0119] In this embodiment, the actual physical size of the LCD screen is obtained so as to subsequently calculate the pixel equivalent and defect size. The physical size of the LCD screen is obtained by referring to the specification information built into the LCD screen.

[0120] 502, obtaining a pixel equivalent of the contrast enhancement image according to the physical size;

[0121] In this embodiment, pixel equivalent refers to the actual physical size represented by each pixel in the image. Obtaining the pixel equivalent of the contrast enhancement image helps to convert the defect size in the image into the actual physical size later. Specifically, first obtain the resolution of the contrast enhancement image (that is, the number of pixels in the horizontal and vertical directions of the image). Then calculate according to the following pixel equivalent calculation formula: pixel equivalent = (image size / picture resolution) × device resolution. Among them, image size refers to the physical size of the LCD screen, picture resolution refers to the resolution of the contrast enhancement image, and device resolution refers to the resolution of the LCD screen. It should be noted that if the contrast enhancement image is automatically generated on the system and there is no clear device resolution information, it can be assumed that the device resolution is 1 (that is, each pixel corresponds to 1 unit length). At this time, the pixel equivalent is simplified to the image size divided by the picture resolution.

[0122] 503, according to the defect area on the contrast enhancement image, obtaining the long side value and the wide side value of the minimum circumscribed rectangle of the defect area;

[0123] In this embodiment, an image processing algorithm is used to identify the defect area on the contrast enhancement image. Then, the minimum bounding rectangle of the defect area is calculated. The minimum bounding rectangle refers to a rectangle that can completely contain the defect area and has the smallest area. Then, the long side value and the wide side value of the minimum bounding rectangle are extracted.

[0124] 504, the size of the defect is calculated based on the long side value and the wide side value.

[0125] In this embodiment, in order to convert the defect size in the image into the actual physical size, the pixel equivalent calculated in step 502 can be used to convert the long side value and the wide side value of the minimum circumscribed rectangle from the pixel unit to the actual physical size unit (such as centimeters or inches). The specific calculation formula is: the size of the actual long side of the defect = the long side value of the minimum circumscribed rectangle × pixel equivalent; the size of the actual wide side of the defect = the wide side value of the minimum circumscribed rectangle × pixel equivalent. In summary, the defect size is composed of the size of the actual long side of the defect and the size of the actual wide side of the defect, and the above steps 501 to 504 can ensure the accuracy of the data.

[0126] The above embodiment describes the method for detecting multi-layer foreign matter on a display screen provided by the present application. The following describes the system, electronic device, and storage medium for detecting multi-layer foreign matter on a display screen provided by the present application:

[0127] See also Figure 6 The present application provides an embodiment of a system for detecting multi-layer foreign matter on a display screen, including:

[0128] The target positioning height unit 601 is used to obtain the target positioning heights of multiple levels of the LCD screen respectively based on the target positioning height of the pixel layer of the LCD screen;

[0129] An image information unit 602 is used to obtain image information of multiple levels through cameras according to target positioning heights of multiple levels;

[0130] A difference processing unit 603 is used to perform difference processing on the image information of multiple levels respectively to obtain multiple contrast enhancement maps;

[0131] A morphological feature unit 604 is used to obtain a plurality of morphological features according to the plurality of contrast enhancement images, wherein the morphological features are morphological features corresponding to the defects on the LCD screen displayed at a plurality of levels;

[0132] The defect feature value unit 605 is used to calculate the multiple morphological features respectively to obtain multiple defect feature values, where the defect feature values ​​represent the difference between the defect and the background;

[0133] A comparison unit 606 is used to compare the numerical values ​​of multiple defect characteristic values ​​to obtain the maximum defect characteristic value;

[0134] A determining unit 607, configured to determine the level corresponding to the maximum defect characteristic value as the level corresponding to the defect;

[0135] The defect size unit 608 is used to calculate the size of the defect according to the contrast enhancement map of the level corresponding to the defect and the physical size of the LCD screen.

[0136] Optionally, before the target highest definition unit 601, the following is further included:

[0137] A first height unit 609 is used to obtain a first height through a laser distance measuring sensor, where the first height is a vertical distance between the laser distance measuring sensor at an initial point and the surface of the LCD screen;

[0138] An initial positioning height unit 610 is used to obtain an initial positioning height of a pixel layer of the LCD screen, wherein a measurement reference point of the initial positioning height is an initial point position;

[0139] A second height unit 611 is used to obtain a second height, where the second height is a vertical distance between the laser ranging sensor at the target test point and the LCD screen surface;

[0140] A relative offset height unit 612, configured to calculate a relative offset height according to the first height and the second height;

[0141] The pixel layer target height unit 613 is used to calculate the target positioning height of the pixel layer according to the relative offset height and the initial positioning height.

[0142] Optionally, the target maximum definition unit 601 is specifically used for:

[0143] Acquire multiple height differences between the pixel layer and multiple levels respectively through a laser ranging sensor;

[0144] Target positioning heights of multiple levels are calculated based on multiple height differences and target positioning heights of pixel layers.

[0145] Optionally, the differentiation processing unit 603 is specifically configured to:

[0146] Performing grayscale transformation on image information of multiple levels respectively to obtain grayscale images of multiple levels;

[0147] Perform noise reduction and background interference reduction processing on grayscale images of multiple levels respectively to obtain pre-processed images of multiple levels;

[0148] Convolution calculations are performed on preprocessed images of multiple levels respectively to obtain multiple contrast enhanced images.

[0149] Optionally, the differentiation processing unit 603 is specifically configured to:

[0150] Get the target convolution formula, which is as follows:

[0151] ;

[0152] Among them, I DF is the contrast enhancement image, I is the preprocessing image, k x1 , k x2 are two convolution kernels in the horizontal direction corresponding to the preprocessed image, k y1 , k y2 are two convolution kernels in the vertical direction corresponding to the preprocessed image, and weight is the weight enhancement coefficient;

[0153] According to the target convolution formula, the preprocessed images of multiple levels are calculated respectively to obtain multiple contrast enhanced images.

[0154] Optionally, the morphological feature unit 604 is specifically used for:

[0155] According to the adaptive threshold algorithm, defect area detection is performed on multiple contrast-enhanced images respectively to obtain multiple morphological features.

[0156] Optionally, the defect size unit 608 is specifically used for:

[0157] Get the physical size of the LCD screen;

[0158] According to the physical size, the pixel equivalent of the contrast enhancement image is obtained;

[0159] According to the defect area on the contrast enhancement image, the long side value and the wide side value of the minimum circumscribed rectangle of the defect area are obtained;

[0160] The defect size is calculated based on the long side and wide side values.

[0161] See also Figure 7 , the present application provides an electronic device, including:

[0162] Processor 701 , memory 702 , input / output unit 703 , and bus 704 .

[0163] The processor 701 is connected to the memory 702 , the input and output unit 703 , and the bus 704 .

[0164] The memory 702 stores a program, and the processor 701 calls the program to execute the following steps: Figures 1 to 5 The method described in any one of the embodiments.

[0165] The present application provides a computer-readable storage medium, on which a program is stored, and when the program is executed on a computer, the program performs the following steps: Figures 1 to 5 The method described in any one of the embodiments.

[0166] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0167] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0168] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0169] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0170] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, read-only memory), random access memory (RAM, random access memory), disk or optical disk and other media that can store program code.

Claims

1. A method for detecting multi-layer foreign matter on a display screen, characterized in that: include: Taking the target positioning height of the pixel layer of the LCD screen as a reference, respectively obtaining the target positioning heights of multiple levels of the LCD screen; According to the target positioning heights of the multiple levels, respectively obtain image information of the multiple levels through cameras; Perform grayscale transformation on the image information of the multiple levels respectively to obtain grayscale images of the multiple levels; perform noise reduction and background interference reduction processing on the grayscale images of the multiple levels respectively to obtain pre-processed images of the multiple levels; obtain a target convolution formula, and the target convolution formula is as follows: ； Among them, the I DF is a contrast enhancement image, I is a preprocessing image, and k x1 , the k x2 are two convolution kernels in the horizontal direction corresponding to the preprocessed image, and the k y1 , the k y2 are two convolution kernels in the vertical direction corresponding to the preprocessed image, and weight is a weight enhancement coefficient; according to the target convolution formula, the preprocessed images of the multiple levels are calculated respectively to obtain multiple contrast enhanced images; According to an adaptive threshold algorithm, defect area detection is performed on the multiple contrast enhancement images respectively to obtain multiple morphological features, where the morphological features are morphological features corresponding to the defects on the LCD screen displayed at the multiple levels respectively; Calculating the multiple morphological features respectively to obtain multiple defect feature values, wherein the defect feature values ​​represent the difference between the defect and the background; Comparing the numerical values ​​of the plurality of defect characteristic quantities to obtain the maximum defect characteristic quantity value; Determining the level corresponding to the maximum defect characteristic value as the level corresponding to the defect; The size of the defect is calculated according to the contrast enhancement map of the level corresponding to the defect and the physical size of the LCD screen.

2. The method according to claim 1, characterized in that Before respectively acquiring the target positioning heights of multiple levels of the LCD screen based on the target positioning height of the pixel layer of the LCD screen, the method further includes: Acquire a first height by using a laser ranging sensor, where the first height is a vertical distance between the laser ranging sensor at an initial point and the surface of the LCD screen; Acquire an initial positioning height of a pixel layer of the LCD screen, wherein a measurement reference point of the initial positioning height is the initial point position; Acquire a second height, where the second height is a vertical distance between the laser ranging sensor at a target test point and the surface of the LCD screen; Calculate a relative offset height according to the first height and the second height; The target positioning height of the pixel layer is obtained by calculation according to the relative offset height and the initial positioning height.

3. The method according to claim 2, characterized in that The step of respectively obtaining target positioning heights of multiple levels of the LCD screen based on the target positioning height of the pixel layer of the LCD screen includes: respectively acquiring a plurality of height differences between the pixel layer and the plurality of levels by means of the laser ranging sensor; Calculate and obtain target positioning heights of multiple levels according to the multiple height differences and the target positioning heights of the pixel layers respectively.

4. The method according to claim 1, characterized in that: Calculating the size of the defect according to the contrast enhancement map of the level corresponding to the defect and the physical size of the LCD screen includes: Obtaining the physical size of the LCD screen; According to the physical size, obtaining a pixel equivalent of the contrast enhancement image; According to the defect area on the contrast enhancement image, obtaining the long side value and the wide side value of the minimum circumscribed rectangle of the defect area; The size of the defect is calculated based on the long side value and the wide side value.

5. A system for detecting multi-layer foreign matter on a display screen, characterized in that: include: A target maximum definition unit, used to obtain target positioning heights of multiple levels of the LCD screen respectively based on the target positioning height of the pixel layer of the LCD screen; An image information unit, configured to obtain image information of the multiple levels through cameras respectively according to target positioning heights of the multiple levels; The difference processing unit is used to perform grayscale transformation on the image information of the multiple levels respectively to obtain grayscale images of the multiple levels; perform noise reduction and background interference reduction processing on the grayscale images of the multiple levels respectively to obtain pre-processed images of the multiple levels; and obtain a target convolution formula, which is as follows: ； Among them, the I DF is a contrast enhancement image, I is a preprocessing image, and k x1 , the k x2 are two convolution kernels in the horizontal direction corresponding to the preprocessed image, and the k y1 , the k y2 are two convolution kernels in the vertical direction corresponding to the preprocessed image, and weight is a weight enhancement coefficient; according to the target convolution formula, the preprocessed images of the multiple levels are calculated respectively to obtain multiple contrast enhanced images; A morphological feature unit, configured to perform defect area detection on the plurality of contrast enhancement images respectively according to an adaptive threshold algorithm to obtain a plurality of morphological features, wherein the morphological features are morphological features corresponding to the defects on the LCD screen displayed at a plurality of levels; A defect feature value unit, used to calculate the multiple morphological features respectively to obtain multiple defect feature values, wherein the defect feature values ​​represent the difference between the defect and the background; A comparing unit, used to compare the numerical values ​​of the plurality of defect characteristic quantities to obtain a maximum defect characteristic quantity value; A determining unit, configured to determine the level corresponding to the maximum defect characteristic value as the level corresponding to the defect; The defect size unit is used to calculate the size of the defect according to the contrast enhancement map of the level corresponding to the defect and the physical size of the LCD screen.

6. An electronic device, characterized in that: The electronic device comprises: Processor, memory, input-output unit, and bus; The processor is connected to the memory, the input and output unit, and the bus; The memory stores a program, and the processor calls the program to execute the method for detecting multi-layer foreign matter on a display screen as claimed in any one of claims 1 to 4.

7. A computer-readable storage medium having a program stored thereon, wherein when the program is executed on a computer, the method for detecting multi-layer foreign matter on a display screen according to any one of claims 1 to 4 is executed.

Images