Method, device and storage medium for locating foreign matter layers on LCD display screen

Abstract

The present application discloses a method, device and storage medium for locating the foreign matter layer on an LCD display screen. The method of the present application comprises: respectively collecting a first position image, a second position image, a third position image and a fourth position image; respectively identifying defective areas on the first position image and the third position image to obtain the corresponding first defective area and second defective area; determining the final defective area; determining the contrast background area; respectively calculating the pixel value mean of the contrast background area and the final defective area in each image to obtain the pixel value mean corresponding to the three contrast background areas and the pixel value mean corresponding to the three final defective areas; respectively calculating the contrast feature value of the final defective area in each image to obtain the corresponding three contrast feature values; based on the predetermined first boundary value and the second boundary value, comparing the three contrast feature values, and determining the level of the foreign matter according to the comparison result.

Description

Technical Field

[0001] The present application relates to the field of optical detection technology, and in particular to a method, device and storage medium for locating foreign matter layers on an LCD display screen. Background Art

[0002] Liquid Crystal Display (LCD) technology is widely used in electronic devices such as smartphones, tablets, and televisions. As the core component of the display screen, its display quality directly affects the user's visual experience and the market competitiveness of the product. LCD display modules are usually composed of multiple layers, including cover glass (CG layer), optical adhesive (OCA layer), upper polarizer (UPOL layer), pixel layer (PANEL layer), lower polarizer (DPOL layer) and backlight layer (BLU layer) from top to bottom. During the assembly process of the display screen module, despite the fine craftsmanship, foreign matter may inevitably be sandwiched, forming interlayer foreign matter defects. These interlayer foreign matter not only affects the appearance of the product, but may also reduce the display quality, and in severe cases, it will affect the user experience.

[0003] At present, Automatic Optical Inspection (AOI) technology has been widely used in display production lines to automatically detect whether there are foreign objects on the display. However, most of these detection systems are limited to identifying the presence of foreign objects, and do not involve the layered positioning of foreign objects. The multi-layer structure of the display module makes foreign objects in different layers have different effects on the display effect, so accurately determining the specific layer where the foreign objects are located is of great significance for subsequent repair or quality control.

[0004] Existing methods for locating foreign matter layers usually rely on experienced technicians to judge through microscopes or naked eyes. This method is not only costly and inefficient, but also highly subjective and dependent on the skill level of the inspectors, making it difficult to ensure the consistency of the inspection results. Especially in LCD displays, due to their complex layers and strong symmetry, locating foreign matter layers is even more difficult.

[0005] Therefore, in order to solve the problem of layered positioning of foreign objects on LCD screens, there is an urgent need for a new technical solution that can achieve automatic layered positioning, overcome the limitations of existing technologies, and improve the accuracy and efficiency of foreign object detection. Summary of the invention

[0006] In order to solve the above technical problems, the present application provides a method, device and storage medium for locating foreign matter layers on an LCD display screen. The technical solution provided in the present application is described below:

[0007] In a first aspect, the present application provides a method for locating a foreign body layer on an LCD display screen, the method comprising:

[0008] Taking the pixel layer of the LCD screen as a reference, the small field of view camera is controlled to collect images from bottom to top at the BLU layer position, the pixel layer position, the CG layer position and the surface layer position, respectively, to obtain the first position image, the second position image, the third position image and the fourth position image;

[0009] Respectively performing defect area recognition on the first position image and the third position image to obtain corresponding first defect area and second defect area;

[0010] determining a final defect region based on the first defect region and the second defect region;

[0011] determining a contrast background region based on the final defect region;

[0012] Calculating the mean pixel values ​​of the contrast background area and the final defect area in the first position image, the third position image, and the fourth position image respectively, to obtain the mean pixel values ​​corresponding to the three contrast background areas and the mean pixel values ​​corresponding to the three final defect areas;

[0013] Calculating the contrast characteristic value of the final defect area in each image based on the average pixel values ​​corresponding to the three contrast background areas and the average pixel values ​​corresponding to the three final defect areas, respectively, to obtain three corresponding contrast characteristic values;

[0014] Based on the predetermined first boundary value and the second boundary value, the three contrast characteristic values ​​are compared, and the level at which the foreign matter is located is determined according to the comparison result.

[0015] Optionally, comparing the three contrast feature values ​​includes:

[0016] Determine a maximum contrast characteristic value among the three contrast characteristic values, and determine a minimum contrast characteristic value among the contrast characteristic values ​​corresponding to the first position image and the third position image;

[0017] The maximum contrast eigenvalue, the minimum contrast eigenvalue and a first ratio are compared with the first boundary value and the second boundary value, wherein the first ratio is the ratio of the absolute value of the difference between the contrast eigenvalues ​​corresponding to the first position image and the third position image to the minimum contrast eigenvalue.

[0018] Optionally, the first boundary value is smaller than the second boundary value, and determining the level of the foreign matter according to the comparison result includes:

[0019] When the maximum contrast characteristic value is equal to the contrast characteristic value corresponding to the fourth position image, it is determined that the foreign object is located above the screen; otherwise, it is determined that the foreign object is located below the screen.

[0020] Optionally, if it is determined that the foreign object is located below the screen and the first ratio is less than the first boundary value, it is determined that the foreign object is located at the pixel layer.

[0021] Optionally, if it is determined that the foreign object is located below the screen, and the first ratio is greater than the first boundary value, and the contrast characteristic value corresponding to the third position image is equal to the minimum contrast characteristic value, then it is determined that the foreign object is located in the backlight layer.

[0022] Optionally, if it is determined that the foreign object is located below the screen, and the first ratio is greater than the first boundary value, and the contrast characteristic value corresponding to the first position image is equal to the minimum contrast characteristic value, then it is determined that the foreign object is located in the CG layer.

[0023] Optionally, if it is determined that the foreign object is located below the screen, and the first ratio is greater than the first boundary value, and the first ratio is less than the second boundary value, and the contrast characteristic value corresponding to the first position image is equal to the minimum contrast characteristic value, then it is determined that the foreign object is located in the OCA layer.

[0024] Optionally, the calculating the contrast characteristic value of the final defect area in each image based on the average pixel values ​​corresponding to the three contrast background areas and the average pixel values ​​corresponding to the three final defect areas includes:

[0025] The contrast eigenvalue is calculated by the following formula:

[0026]

[0027] Where C represents the contrast eigenvalue, represents the mean pixel value of the defect area in the corresponding image, It represents the mean pixel value of the contrast background area in the corresponding image, and Bias represents the preset bias coefficient;

[0028] The above formula is used to calculate the defect area in image I B ,I C and I S The contrast eigenvalues ​​in C B , C C and C S , where I B ,I C and I S Respectively represent the first position image, the third position image and the fourth position image, C B , C C and CS The contrast feature values ​​corresponding to the three images are represented in turn.

[0029] Optionally, determining the final defect area based on the first defect area and the second defect area includes:

[0030] If the first defect region and the second defect region have an intersection, a region obtained by merging the first defect region and the second defect region is determined as a final defect region.

[0031] Optionally, determining the final defect area based on the first defect area and the second defect area includes:

[0032] If the first defect region and the second defect region do not have an intersection, the region with the largest area between the first defect region and the second defect region is determined as the final defect region.

[0033] Optionally, the performing defect area identification on the first position image and the third position image respectively to obtain the corresponding first defect area and second defect area comprises:

[0034] The first position image and the third position image are processed respectively in the following manners to obtain corresponding defect areas:

[0035] Use a predefined convolution kernel to differentiate the image, and enhance the differentiated image to obtain a differential enhanced image;

[0036] Binarizing the differential enhanced image based on a preset threshold to obtain a binary image;

[0037] Performing Blob analysis on the binary image to determine the initial defect area;

[0038] The initial defect region is expanded using a rectangular structure element to obtain a defect region.

[0039] Optionally, the using a predefined convolution kernel to differentiate the image and enhancing the differentiated image to obtain the differentiated enhanced image includes:

[0040] Differential enhancement is performed using the following formula:

[0041]

[0042] represents the horizontal convolution kernel, represents the convolution kernel in the vertical direction, represents the difference enhanced image, I represents the original image, Represents the preconfigured weight parameters.

[0043] Determining the contrast background area based on the final defect area includes:

[0044] Determining the minimum circumscribed rectangle of the final defect area;

[0045] Expand the left and right sides and the upper and lower sides of the minimum circumscribed rectangle by a first distance and a second distance respectively to obtain an expanded rectangle;

[0046] The difference between the expanded rectangle and the final defect area is calculated to obtain a contrast background area.

[0047] A second aspect of the present application provides a device for positioning foreign matter layers on an LCD display screen, the device comprising:

[0048] An image acquisition unit is used to control the small field of view camera to acquire images at the BLU layer position, the pixel layer position, the CG layer position and the surface layer position from bottom to top based on the pixel layer of the LCD screen, so as to obtain a first position image, a second position image, a third position image and a fourth position image;

[0049] A defect area recognition unit, used to perform defect area recognition on the first position image and the third position image respectively to obtain corresponding first defect area and second defect area;

[0050] a final defect area determining unit, configured to determine a final defect area based on the first defect area and the second defect area;

[0051] A contrast background area determination unit, configured to determine a contrast background area based on the final defect area;

[0052] a pixel value mean calculation unit, used to respectively calculate the pixel value means of the contrast background area and the final defect area in the first position image, the third position image and the fourth position image, to obtain the pixel value means corresponding to the three contrast background areas and the pixel value means corresponding to the three final defect areas;

[0053] A contrast characteristic value calculation unit, used to calculate the contrast characteristic value of the final defect area in each image based on the average pixel values ​​corresponding to the three contrast background areas and the average pixel values ​​corresponding to the three final defect areas, to obtain the corresponding three contrast characteristic values;

[0054] The foreign matter determining unit is used to compare the three contrast characteristic values ​​based on a predetermined first boundary value and a second boundary value, and determine the level of the foreign matter according to the comparison result.

[0055] The third aspect of the present application provides another device for positioning foreign matter layers on an LCD display screen, the device comprising:

[0056] Processor, memory, input-output unit, and bus;

[0057] The processor is connected to the memory, the input and output unit, and the bus;

[0058] The memory stores a program, and the processor calls the program to execute the first aspect and any optional method in the first aspect.

[0059] 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 program executes the first aspect and any optional method in the first aspect.

[0060] It can be seen from the above technical solutions that this application has the following advantages:

[0061] 1. The method of this application can effectively distinguish which layer the foreign matter is located at by collecting images of different layers (BLU layer, pixel layer, CG layer, surface layer) and analyzing their contrast characteristics, and provides an accurate foreign matter layer positioning function. This is of great significance for quality inspection in maintenance and production.

[0062] 2. The method of the present application can not only detect foreign matter in the pixel layer, but also effectively detect foreign matter in the BLU layer and CG layer, which enhances the comprehensiveness of the overall detection and reduces the possibility of missing defects in other layers.

[0063] 3. By calculating the contrast feature value and combining it with the background area pixel value for comparative analysis, the recognition accuracy of foreign objects can be improved, especially for tiny and difficult-to-find defect areas. This method greatly reduces the false detection rate and missed detection rate.

[0064] 4. Since double image contrast (first and third position image contrast) is used in the process of determining the foreign body layer, and the difference between the background area and the defect area is analyzed through contrast, the sub-pixel interference problem in pixel layer imaging is effectively reduced, and the ability to identify defects is improved.

[0065] 5. This method determines the level of foreign matter by setting threshold values ​​(such as the first boundary value and the second boundary value), thereby enhancing the stability and reliability of the detection results under different lighting conditions or different display screen materials.

[0066] 6. This method overcomes the time-consuming and laborious shortcomings of human eye observation or microscope observation, reduces the influence of subjective factors, has low experience requirements for detection technicians, reduces human errors, improves detection efficiency, and is suitable for large-scale automated detection in industrial production.

[0067] 7. It can not only automatically detect whether there are foreign objects in the LCD display screen, but also automatically determine the layer where the foreign objects are located, thus improving the effectiveness and integrity of the detection results. This method has a high degree of automation and reduces human intervention. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] In order to more clearly illustrate the technical solution in the present application, the drawings required for use in the description of the embodiments 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 any creative work.

[0069] Figure 1 A schematic diagram of an embodiment of a method for locating a foreign body layer on an LCD display screen provided in the present application;

[0070] Figure 2 A schematic flow chart of another embodiment of the method for locating foreign matter layers on an LCD display screen provided in the present application;

[0071] Figure 3 A schematic flow chart of another embodiment of the method for locating a foreign body layer on an LCD display screen provided in the present application;

[0072] Figure 4 A schematic diagram of the structure of an embodiment of the device for positioning foreign matter layers on an LCD display screen provided in the present application;

[0073] Figure 5 This is a schematic structural diagram of an embodiment of another device for positioning foreign matter layers on an LCD display screen provided in the present application. DETAILED DESCRIPTION

[0074] It should be noted that the method provided in this application can be applied to a terminal, a system, or a server. For example, the terminal can be a smart phone or a computer, a tablet computer, a smart TV, a smart watch, a portable computer terminal, or a fixed terminal such as a desktop computer. For the convenience of explanation, this application uses the terminal as an example for explanation.

[0075] The following is an explanation of the terms that may be used in this application:

[0076] 1. LCD display

[0077] Liquid Crystal Display (LCD) is an electronic display technology that displays images by changing the propagation direction and intensity of light through liquid crystal materials. LCD displays are usually composed of multiple layers, including a backlight layer (BLU layer), a pixel layer, a cover glass layer (CG layer), and a surface layer.

[0078] 2. BLU layer

[0079] The backlight unit (BLU) is the underlying structure of the LCD display, which is used to provide backlight for the screen. This layer is located below the pixel layer and provides a uniform light source for the liquid crystal pixels through light-emitting diodes (LEDs) or other light sources, making the displayed image clearer.

[0080] 3. Pixel layer

[0081] The pixel layer in an LCD display contains the basic units that form an image. Each pixel is composed of sub-pixels of the three primary colors of red, green, and blue. The pixel layer determines the resolution and image quality of the display and is the core layer of the entire screen display structure.

[0082] 4. CG layer

[0083] The cover glass layer (CG) is the top structure of the LCD display, located above the pixel layer. Its main function is to protect the internal display structure and provide a strong and durable surface.

[0084] 5. Surface layer

[0085] The outermost layer of the LCD display is responsible for protecting the display from external physical damage and contamination. The surface layer usually has anti-reflective and anti-fouling functions to improve the user's viewing experience.

[0086] 6. Optical adhesive layer (OCA layer)

[0087] The optically clear adhesive (OCA) layer is a transparent adhesive layer used to bond different layers of LCD displays (such as the cover glass layer and the display layer) together. The OCA layer has excellent optical transparency and can minimize optical interference while providing reliable adhesion to ensure the stability and durability of the display structure. The OCA layer can also improve the display effect, reduce reflection and bubble generation, and is often used in the bonding process of touch screens and displays.

[0088] See also Figure 1 , Figure 1 This is a flow chart of an embodiment of the method provided in this application. The method of this embodiment includes:

[0089] S101, taking the pixel layer of the LCD screen as a reference, controlling the small field of view camera to collect images from bottom to top at the BLU layer position, the pixel layer position, the CG layer position and the surface layer position, respectively, to obtain a first position image, a second position image, a third position image and a fourth position image;

[0090] The method of this application is applied to LCD screen inspection. Since the depth of field of the lens used with the small field of view layered camera is small, the pixel layer is selected as the layered reference position for positioning in order to ensure the best clarity of the camera. The pixel layer is a very important layer in the LCD display screen. The inspection system ensures the highest quality of the collected image by accurately focusing on the pixel layer, which can provide clear data for subsequent defect analysis.

[0091] If there is no foreign matter in all layers of the LCD display, or if there is foreign matter only at the pixel layer, the contrast of the same area in the images captured at the same distance from the pixel layer on both sides (i.e., BLU layer and CG layer) should be very similar. This is because there is no interference from other layers, resulting in less change in optical properties.

[0092] On the contrary, if there are foreign objects in other layers (such as BLU layer or CG layer), the contrast of the foreign object area will be different in the images collected on both sides at the same distance from the pixel layer because the foreign objects will affect the propagation and scattering of light. By comparing the contrast differences in the images, the specific layer where the foreign objects are located can be inferred.

[0093] The hierarchical structure of LCD display is more complicated than that of OLED. LCD has a BLU layer (backlight layer), which is located below the pixel layer and is responsible for providing the backlight required for display. OLED does not need a backlight layer because its luminescent material can emit light by itself. The existence of the BLU layer increases the difficulty of LCD stratification, so it is necessary to specifically consider the foreign body detection of this layer.

[0094] In contrast, the CG layer (cover glass) is located above the pixel layer and is relatively thick, which means that the attenuation and refraction of light when passing through the CG layer will be different. Therefore, it is necessary to capture images at the location of the CG layer to evaluate the foreign matter situation in this layer.

[0095] Therefore, in this embodiment, the pixel layer of the LCD screen is used as a reference, and a small field of view camera is used to collect images at four different levels (BLU layer, pixel layer, CG layer, and surface layer). The camera shoots from bottom to top, and the specific collection process is as follows:

[0096] BLU layer position: The camera imaging clear position is located below the pixel layer. Take an image of the BLU layer (backlight layer) position to obtain the first position image (I B ).

[0097] Pixel layer position: The camera moves to the pixel layer (PANEL layer) where the image is clear, and collects the image at the second position (I P ).

[0098] CG layer position: The camera continues to move until its clear imaging position is located at the CG layer (cover glass) position, and collects the third position image (I C ).

[0099] Surface layer position: The final clear imaging position of the camera is at the surface layer of the LCD screen, and the fourth position image (I S ).

[0100] S102, performing defect area recognition on the first position image and the third position image respectively to obtain corresponding first defect area and second defect area;

[0101] The defect area is identified for the first position image (BLU layer image) and the third position image (CG layer image). The specific steps are as follows:

[0102] The first position image (I B ) to process the image, identify the defect area in the image through filtering, binarization and other steps, and obtain the first defect area (R B ).

[0103] For the third position image (I C ) performs the same image processing steps to obtain the second defect area (R C ). The goal of this step is to ensure that the presence of foreign matter can be detected by identifying defects in the BLU layer and CG layer images.

[0104] S103, determining a final defect region based on the first defect region and the second defect region;

[0105] In this step, based on the first defect area (R B ) and the second defect area (R C ) Determine the final defect area.

[0106] In an alternative embodiment, R B and R C Two defective regions are used to perform union and intersection operations. If the two regions have an intersection, their union is used as the final defective region; if there is no intersection, the region with a larger area is selected as the final defective region (R F ).

[0107] If R B and R C There is no intersection, which means that the two areas may correspond to foreign matter at different levels. At this time, it is necessary to select which area as the final defect area by comparing the sizes of the two areas.

[0108] In order to ensure that no foreign matter is missed, the larger of the two areas is taken as the final defect area R F This ensures that the system covers potential defect locations as comprehensively as possible.

[0109] S104, determining a contrast background area based on the final defect area;

[0110] In order to further analyze the defect characteristics, it is necessary to determine the contrast background area corresponding to the defect area.

[0111] In an optional embodiment, the minimum bounding rectangle of the final defect area can be obtained, marked as Rs. Rs is expanded horizontally on the left and right sides by a certain distance, called ExpansionH; and vertically on the upper and lower sides, called ExpansionV, to generate the expanded rectangular area R st From R st Subtract the defect area R F , remove the defective parts, and finally get the contrast background area (RBG).

[0112] S105, respectively calculating the mean pixel values ​​of the contrast background area and the final defect area in the first position image, the third position image, and the fourth position image to obtain the mean pixel values ​​corresponding to the three contrast background areas and the mean pixel values ​​corresponding to the three final defect areas;

[0113] Calculate the mean pixel values ​​of the contrast background area and the final defect area in the images at three different positions (the first position image, the third position image, and the fourth position image). The specific steps are as follows:

[0114] In each image, the corresponding contrast background area (R BG ) and the final defect area (R F ) are recorded as:

[0115] In the first position image, the pixel mean G of the background area is obtained BG1 , the pixel mean value G of the defect area F1 .

[0116] In the third position image, the pixel mean G of the background area is obtained BG2 , the pixel mean value G of the defect area F2 .

[0117] In the fourth position image, the pixel mean G of the background area is obtained. BG3 , the pixel mean value G of the defect area F3 .

[0118] S106, respectively calculating the contrast feature value of the final defect area in each image based on the pixel value averages corresponding to the three contrast background areas and the pixel value averages corresponding to the three final defect areas, to obtain three corresponding contrast feature values;

[0119] Based on the mean pixel value obtained in the previous step, the contrast feature value of the defect area in each image is calculated.

[0120] In an optional embodiment, the calculation formula of the contrast characteristic value is:

[0121]

[0122] Where C represents the contrast eigenvalue, represents the mean pixel value of the defect area in the corresponding image, It represents the mean pixel value of the contrast background area in the corresponding image, and Bias represents the preset bias coefficient;

[0123] The above formula is used to calculate the defect area in image I B ,I C and I S The contrast eigenvalues ​​in C B , C C and C S , where I B ,I C and I S Respectively represent the first position image, the third position image and the fourth position image, C B , C C and C S The contrast feature values ​​corresponding to these three images are represented in turn.

[0124] S107 . Based on a predetermined first boundary value and a second boundary value, compare the three contrast feature values, and determine the level at which the foreign matter is located according to the comparison result.

[0125] According to the preset boundary value, the three contrast characteristic values ​​are compared to determine the level where the foreign matter is located. The preset boundary value includes a first boundary value and a second boundary value.

[0126] The method provided in this embodiment can not only automatically detect foreign matter in the LCD display screen, but also can further automatically determine the level at which the foreign matter is located. This automated process improves the accuracy and completeness of the detection and avoids possible omissions and misjudgments during manual detection. By controlling the image acquisition of the small field of view camera at different levels, images of different levels of the display screen can be obtained quickly and accurately, and defective areas can be automatically identified and compared. This greatly improves the detection speed and significantly saves time and labor costs compared to manual observation.

[0127] Traditional manual inspection methods rely on human visual observation or microscopic inspection, which is time-consuming, labor-intensive and easily affected by the experience of the inspector. This method eliminates the influence of human subjective factors on the inspection results through automated analysis, ensuring the consistency and objectivity of the inspection. Through multi-layer image acquisition and calculation of contrast eigenvalues, the level of foreign matter can be accurately determined. Combining union and intersection operations, the area where the foreign matter is located can be captured more comprehensively, reducing the risk of missing foreign matter or misjudging the location of foreign matter. Whether the foreign matter is located in a single layer or multiple layers, the method can find the most suitable final defect area through union and intersection operations. This flexibility enables the system to adapt to different foreign matter distribution situations and improve the reliability of detection.

[0128] In the above-mentioned embodiment, it is mentioned that the level of the foreign matter is determined by comparing the three contrast characteristic values. The present application provides a specific implementation method for determination, and the embodiment is described below:

[0129] S201, taking the pixel layer of the LCD screen as a reference, controlling the small field of view camera to collect images from bottom to top at the BLU layer position, the pixel layer position, the CG layer position and the surface layer position, respectively, to obtain a first position image, a second position image, a third position image and a fourth position image;

[0130] S202, respectively identifying defect regions on the first position image and the third position image to obtain corresponding first defect regions and second defect regions;

[0131] S203, determining a final defect region based on the first defect region and the second defect region;

[0132] S204, determining a contrast background area based on the final defect area;

[0133] S205, respectively calculating the mean pixel values ​​of the contrast background area and the final defect area in the first position image, the third position image, and the fourth position image to obtain the mean pixel values ​​corresponding to the three contrast background areas and the mean pixel values ​​corresponding to the three final defect areas;

[0134] S206, respectively calculating the contrast feature value of the final defect area in each image based on the average pixel values ​​corresponding to the three contrast background areas and the average pixel values ​​corresponding to the three final defect areas, to obtain three corresponding contrast feature values;

[0135] S207, determining a first boundary value and a second boundary value;

[0136] Steps S201 to S207 provided in the present application are similar to steps S101 to S107 provided in the aforementioned embodiment and will not be repeated here.

[0137] S208, determining a maximum contrast feature value among the three contrast feature values, and determining a minimum contrast feature value among the contrast feature values ​​corresponding to the first position image and the third position image;

[0138] In this embodiment, the maximum value is determined among the three detected contrast feature values ​​(i.e., the contrast feature values ​​calculated from the first position image, the third position image, and the fourth position image, respectively). This maximum value indicates that among these layers, a foreign object may exist in a certain layer, and the contrast feature of this layer is the most different from the background area.

[0139] At the same time, the minimum value is determined among the contrast feature values ​​corresponding to the first position image and the third position image. The minimum value reflects the area with the smallest contrast difference among these layers, indicating that foreign matter may exist at this level, but its features are weak or may be located in other layers.

[0140] The purpose of this step is to provide a basis for further determining the layer where the foreign matter is located by identifying the layer with the most obvious contrast difference.

[0141] S209, comparing the maximum contrast eigenvalue, the minimum contrast eigenvalue, and a first ratio with the first boundary value and the second boundary value, wherein the first ratio is a ratio of an absolute value of a difference between contrast eigenvalues ​​corresponding to the first position image and the third position image to the minimum contrast eigenvalue;

[0142] The difference between the contrast feature values ​​corresponding to the first position image and the third position image is calculated, and the absolute value of the ratio of the difference to the minimum contrast feature value is taken as the first ratio. The ratio reflects the contrast difference between the foreign matter at different levels. If the ratio is large, it may mean that the foreign matter spans multiple levels, or the features are more prominent at a certain level.

[0143] The maximum contrast characteristic value, the minimum contrast characteristic value and the first ratio are compared with the first boundary value and the second boundary value respectively. The first boundary value and the second boundary value are used to set the contrast difference thresholds of different levels to determine whether the contrast difference is sufficient to confirm the level where the foreign matter is located.

[0144] This step provides a quantitative standard for determining the location of foreign matter by comparing the relationship between these contrast features and ratios and boundary values.

[0145] S210, determining the level where the foreign matter is located according to the comparison result.

[0146] According to the comparison result in S209, combined with the maximum contrast characteristic value, the minimum contrast characteristic value and the first ratio, the specific layer where the foreign matter is located can be determined. For example, if the contrast characteristic value or the ratio exceeds the first boundary value, it may indicate that the foreign matter exists in a deeper layer (such as the BLU layer); and if the ratio exceeds the second boundary value, it may indicate that the foreign matter exists in a shallower layer (such as the surface layer or the CG layer).

[0147] In the comparison, if the maximum contrast eigenvalue is significantly higher than the boundary value and the minimum contrast eigenvalue is smaller, it can be determined that the foreign matter may be concentrated in a certain layer. If the ratio is larger, it may indicate that the foreign matter is distributed in a multi-layer or cross-layer structure.

[0148] In a more specific embodiment, the present application also provides a more specific embodiment for determining the level of the foreign matter according to the comparison result.

[0149] This embodiment includes five different situations, namely:

[0150] Case 1: When the maximum contrast characteristic value is equal to the contrast characteristic value corresponding to the fourth position image, it is determined that the foreign object is located above the screen; otherwise, it is determined that the foreign object is located below the screen.

[0151] If it is determined that the foreign object is located below the screen, it can be further divided into the following four situations:

[0152] Case 2: If it is determined that the foreign object is located below the screen and the first ratio is less than the first boundary value, it is determined that the foreign object is located at the pixel layer.

[0153] Case three: If it is determined that the foreign object is located below the screen, and the first ratio is greater than the first boundary value, and the contrast characteristic value corresponding to the third position image is equal to the minimum contrast characteristic value, then it is determined that the foreign object is located in the backlight layer.

[0154] Case 4: If it is determined that the foreign object is located below the screen, and the first ratio is greater than the first boundary value, and the contrast characteristic value corresponding to the first position image is equal to the minimum contrast characteristic value, then it is determined that the foreign object is located in the CG layer.

[0155] Case 5: If it is determined that the foreign object is located below the screen, and the first ratio is greater than the first boundary value, and the first ratio is less than the second boundary value, and the contrast feature value corresponding to the first position image is equal to the minimum contrast feature value, then it is determined that the foreign object is located in the OCA layer.

[0156] The following are examples of the above five situations:

[0157] Case 1: The maximum contrast eigenvalue is equal to the contrast eigenvalue corresponding to the image at the fourth position

[0158] Judgment conditions:

[0159] The calculated maximum contrast eigenvalue C max Equal to C S , that is, the contrast characteristic value corresponding to the fourth position image (surface layer image).

[0160] Judgment result:

[0161] Make sure the foreign object is located above the screen, that is, the surface layer (Surface layer) of the display.

[0162] When the foreign matter is located on the surface layer of the display screen, since it is directly exposed to the external environment, the light will be significantly reflected and scattered when passing through this layer, resulting in the most significant contrast difference between the defect area and the background area in the surface layer image. This makes the contrast characteristic value C of the surface layer S Maximum, exceeding the contrast feature value of other levels.

[0163] Therefore, when C max =C S When the foreign object is detected, it can be determined that the foreign object is located on the surface layer of the screen, that is, the top of the display screen.

[0164] Case 2: The foreign object is located below the screen, and the first ratio is less than the first boundary value

[0165] Judgment conditions:

[0166] The foreign object has been determined to be located below the screen, i.e. C max ≠C S .

[0167] The first ratio Ratio_C (i.e. |C B -C C | / C min ) is less than the first boundary value RatioC_th1.

[0168] Judgment result:

[0169] Determine that the foreign matter is located at the pixel layer (PANEL layer).

[0170] When the foreign matter is located at the pixel layer, since the pixel layer is the layer reference position and the small field of view camera collects images at the upper and lower symmetrical positions of the pixel layer (BLU layer and CG layer), the distance between these two layers and the pixel layer is the same.

[0171] If there are no foreign objects in other layers of the display, or if the foreign objects happen to be located at the pixel layer, the contrast of the same area in the images captured at the BLU layer and the CG layer should theoretically be very close.

[0172] Therefore, the first ratio Ratio_C will be very small, less than the preset first boundary value RatioC_th1.

[0173] Since Ratio_C < RatioC_th1, it indicates that the contrast difference between the BLU layer and the CG layer images is very small, and the foreign object is likely to be located in the pixel layer.

[0174] Case 3: The foreign object is located below the screen, the first ratio is greater than the first boundary value, and the contrast feature value corresponding to the image at the third position is equal to the minimum contrast feature value

[0175] Judgment condition:

[0176] The foreign object has been determined to be located below the screen, that is, C max ≠C S .

[0177] The first ratio Ratio_C is greater than the first boundary value RatioC_th1.

[0178] The contrast feature value C corresponding to the image at the third position (CG layer image) C is equal to the minimum contrast feature value C min .

[0179] Judgment result:

[0180] It is determined that the foreign object is located in the backlight layer (BLU layer).

[0181] When the foreign object is located in the BLU layer, since the BLU layer is below the pixel layer, the influence of the foreign object on the light will be more obvious in the BLU layer image.

[0182] Therefore, the contrast feature value CB of the image at the first position (BLU layer image) will be larger, while the contrast feature value C of the image at the third position (CG layer image) C will be smaller, that is, C C =C min .

[0183] The first ratio Ratio_C is greater than RatioC_th1, indicating that the contrast difference between the BLU layer and the CG layer images is large.

[0184] Since Ratio_C > RatioC_th1 and C min =C C , it can be determined that the foreign object is located in the backlight layer.

[0185] Case 4: The foreign object is located below the screen, the first ratio is greater than the first boundary value, and the contrast feature value corresponding to the image at the first position is equal to the minimum contrast feature value

[0186] Judgment condition:

[0187] The foreign object has been determined to be located below the screen, i.e. C max ≠C S .

[0188] The first ratio Ratio_C is greater than the first boundary value RatioC_th1.

[0189] Contrast eigenvalue C corresponding to the first position image (BLU layer image) B Equal to the minimum contrast eigenvalue C min .

[0190] Judgment result:

[0191] It was determined that the foreign matter was located in the CG layer (cover glass layer).

[0192] When foreign matter is located in the CG layer, since the CG layer is located above the pixel layer, the impact of the foreign matter on light in this layer will be more obvious in the CG layer image.

[0193] Therefore, the contrast characteristic value C of the third position image (CG layer image) is C will be larger, while the contrast feature value CB of the first position image (BLU layer image) will be smaller, that is, C B =C min .

[0194] The first ratio Ratio_C is greater than RatioC_th1, indicating that the contrast difference between the BLU layer and the CG layer images is obvious.

[0195] Since Ratio_C>RatioC_th1 and C min =C B , it can be determined that the foreign matter is located in the CG layer.

[0196] Case 5: The foreign object is located below the screen, the first ratio is greater than the first boundary value and less than the second boundary value, and the contrast characteristic value corresponding to the image at the first position is equal to the minimum contrast characteristic value

[0197] Judgment conditions:

[0198] The foreign object has been determined to be located below the screen, i.e. C max ≠C S .

[0199] The first ratio Ratio_C is greater than the first boundary value RatioC_th1 and less than the second boundary value RatioC_th2.

[0200] Contrast eigenvalue C corresponding to the first position image (BLU layer image) B Equal to the minimum contrast eigenvalue C min .

[0201] Judgment result:

[0202] It is determined that the foreign object is located in the optical adhesive layer (OCA layer).

[0203] The OCA layer is located between the pixel layer and the CG layer. A foreign object in this layer will have a greater impact on the CG layer image and a relatively smaller impact on the BLU layer image.

[0204] Therefore, the contrast eigenvalue C of the third position image (CG layer image) C will be relatively large, and the contrast eigenvalue C of the first position image (BLU layer image) B will be relatively small, that is, C B =C min .

[0205] The first ratio Ratio_C is between RatioC_th1 and RatioC_th2, indicating that the contrast difference exists but is not as significant as the previous two cases.

[0206] Since RatioC_th1 < Ratio_C < RatioC_th2 and C min =C B , it can be determined that the foreign object is located in the OCA layer.

[0207] By comparing the contrast eigenvalues of each layer and the differences between them, and using the preset boundary values, the layer where the foreign object is located can be accurately determined. The magnitude and position of the maximum contrast eigenvalue directly affect the preliminary judgment of the foreign object layer. The magnitude of the first ratio Ratio_C is used to refine the judgment and distinguish the position of the foreign object at different under-screen layers.

[0208] The first boundary value (RatioC_th1) is used to determine whether the contrast difference is sufficient to consider that the foreign object is located in other layers outside the pixel layer.

[0209] The second boundary value (RatioC_th2) is used to further distinguish whether the foreign object is located in the OCA layer or the CG layer.

[0210] This determination method utilizes the optical characteristics and positional relationships of each layer of the LCD display screen. Through quantitative analysis, it avoids subjective judgment and improves the accuracy and reliability of detection. By calculating the contrast eigenvalues and ratios and combining the comparison of boundary values, it can carefully analyze the influence range of foreign objects and improve the detection accuracy. The method of this embodiment is not only applicable to detecting the presence of foreign objects, but also can further determine the layer where they are located, especially for layers with different thicknesses, there is a clear distinction.

[0211] Referring to Figure 3 , this application also provides another embodiment, and a specific method for determining the final defect area is provided in this embodiment. This embodiment includes:

[0212] S301, taking the pixel layer of the LCD screen as a reference, controlling the small field of view camera to collect images from bottom to top at the BLU layer position, the pixel layer position, the CG layer position and the surface layer position, respectively, to obtain a first position image, a second position image, a third position image and a fourth position image;

[0213] S302, performing defect area recognition on the first position image and the third position image respectively to obtain corresponding first defect area and second defect area;

[0214] In an optional embodiment, the specific implementation of this step may include the following steps:

[0215] The first position image and the third position image are processed respectively in the following manners to obtain corresponding defect areas:

[0216] Use a predefined convolution kernel to differentiate the image, and enhance the differentiated image to obtain a differential enhanced image;

[0217] Binarizing the differential enhanced image based on a preset threshold to obtain a binary image;

[0218] Performing Blob analysis on the binary image to determine the initial defect area;

[0219] The initial defect region is expanded using a rectangular structure element to obtain a defect region.

[0220] Among them, differential enhancement can be performed by the following formula:

[0221]

[0222] represents the horizontal convolution kernel, represents the convolution kernel in the vertical direction, represents the difference enhanced image, I represents the original image, Represents the preconfigured weight parameters.

[0223] S303, determining whether the first defect region and the second defect region have an intersection;

[0224] If yes, execute step S304; if no, execute step S305.

[0225] In this step, the system first identifies the first defect area and the second defect area in the first position image and the third position image respectively through an image processing algorithm. Then, the spatial positions of the two defect areas are compared to determine whether they overlap in the same or similar image areas, that is, whether there is an intersection. The judgment method can be to determine whether the boundaries of the two areas intersect through geometric calculations.

[0226] For example, a binarization algorithm or other image segmentation method can be used to identify the boundary between two defective areas. The coordinates of the areas are compared to determine whether their boundaries overlap. If there is an intersection, it means there is an intersection.

[0227] By judging the intersection, it can be ensured that the defect areas detected in different image layers are the mapping of the same foreign object, thereby improving the accuracy of subsequent defect positioning. It avoids the incorrect merging of different foreign objects and helps to further accurately determine the final defect area.

[0228] S304: Determine a region formed by merging the first defect region and the second defect region as a final defect region.

[0229] If it is determined in step S303 that the first defect area and the second defect area have an intersection, the system merges the two areas into a larger area as the final defect area. Merging means expanding the boundaries of the two areas to generate a new boundary covering the entire intersection and the original area, ensuring that all defect information is included in the final defect area. The boundaries of the two areas are combined to obtain a new area containing all boundary points of the two areas. The shape of the new area will be determined according to the shape and intersection of the two defect areas, and a minimum closed area covering the original area can be generated.

[0230] The merging operation ensures the integrity of the defect, and all relevant information can be integrated even if the same foreign object is detected in different layers. This method reduces misjudgment, ensures the validity of the inspection results, and avoids the loss of key information.

[0231] 305. Determine the largest area between the first defect area and the second defect area as a final defect area;

[0232] If it is determined in step S303 that the first defect region and the second defect region have no intersection, it means that the two defect regions belong to different defect sources. In this case, the system will select the defect region with a larger area as the final defect region, because a larger defect usually means a more significant foreign matter or problem.

[0233] Specifically, the areas of the two defect regions can be calculated, for example, by the number of pixels or the geometric area of ​​the contour, and the area values ​​of the two regions are compared, and the larger region is selected as the final defect region.

[0234] This step ensures that the inspection system prioritizes more serious or obvious defects by selecting larger areas, reducing the interference of minor defects on the final inspection results. This method can effectively screen out the most important defect areas when there are many foreign objects, improving the inspection efficiency and accuracy of the system.

[0235] S306, determining a contrast background area based on the final defect area;

[0236] S307, respectively calculating the mean pixel values ​​of the contrast background area and the final defect area in the first position image, the third position image, and the fourth position image to obtain the mean pixel values ​​corresponding to the three contrast background areas and the mean pixel values ​​corresponding to the three final defect areas;

[0237] S308, respectively calculating the contrast feature value of the final defect area in each image based on the pixel value mean values ​​corresponding to the three contrast background areas and the pixel value mean values ​​corresponding to the three final defect areas, to obtain three corresponding contrast feature values;

[0238] S309: Based on the predetermined first boundary value and the second boundary value, the three contrast feature values ​​are compared, and the level at which the foreign matter is located is determined according to the comparison result.

[0239] The steps not described in detail in this embodiment are implemented in a similar manner to the related steps in the aforementioned embodiments and will not be described again here.

[0240] In this embodiment, by gradually determining whether the defective areas have intersections, and merging or screening according to the intersections or areas, the final defective area can be located more accurately. Whether a single foreign body (with intersections) or multiple foreign bodies (without intersections) are detected, the system can handle the situation accordingly, with great flexibility. By merging or selecting areas with larger areas, the validity of the final defective area is ensured, and important defect information is retained to the greatest extent, which is helpful for subsequent analysis and processing.

[0241] The above embodiments describe the embodiments of the method provided in the present application in detail. The following describes the embodiments of the device provided in the present application:

[0242] See also Figure 4 The present application provides an embodiment of a device for positioning a foreign body layer on an LCD display screen, the embodiment comprising:

[0243] The image acquisition unit 401 is used to control the small field of view camera to acquire images at the BLU layer position, the pixel layer position, the CG layer position and the surface layer position from bottom to top based on the pixel layer of the LCD screen, so as to obtain a first position image, a second position image, a third position image and a fourth position image;

[0244] A defect area identification unit 402 is used to identify defect areas on the first position image and the third position image respectively to obtain corresponding first defect areas and second defect areas;

[0245] A final defect area determining unit 403, configured to determine a final defect area based on the first defect area and the second defect area;

[0246] A contrast background region determining unit 404, configured to determine a contrast background region based on the final defect region;

[0247] A pixel value mean calculation unit 405 is used to calculate the pixel value means of the contrast background area and the final defect area in the first position image, the third position image and the fourth position image, respectively, to obtain the pixel value means corresponding to the three contrast background areas and the pixel value means corresponding to the three final defect areas;

[0248] A contrast feature value calculation unit 406 is used to calculate the contrast feature value of the final defect area in each image based on the pixel value means corresponding to the three contrast background areas and the pixel value means corresponding to the three final defect areas, to obtain the corresponding three contrast feature values;

[0249] The foreign matter determining unit 407 is used to compare the three contrast feature values ​​based on a predetermined first boundary value and a second boundary value, and determine the level of the foreign matter according to the comparison result.

[0250] Optionally, the foreign matter determining unit 407 is specifically configured to:

[0251] Determine a maximum contrast characteristic value among the three contrast characteristic values, and determine a minimum contrast characteristic value among the contrast characteristic values ​​corresponding to the first position image and the third position image;

[0252] The maximum contrast eigenvalue, the minimum contrast eigenvalue and a first ratio are compared with the first boundary value and the second boundary value, wherein the first ratio is the ratio of the absolute value of the difference between the contrast eigenvalues ​​corresponding to the first position image and the third position image to the minimum contrast eigenvalue.

[0253] Optionally, the foreign matter determining unit 407 is specifically configured to:

[0254] When the maximum contrast characteristic value is equal to the contrast characteristic value corresponding to the fourth position image, it is determined that the foreign object is located above the screen; otherwise, it is determined that the foreign object is located below the screen.

[0255] Optionally, the foreign matter determining unit 407 is specifically configured to:

[0256] If it is determined that the foreign object is located below the screen and the first ratio is less than the first boundary value, it is determined that the foreign object is located at the pixel layer.

[0257] Optionally, the foreign matter determining unit 407 is specifically configured to:

[0258] If it is determined that the foreign object is located below the screen, and the first ratio is greater than the first boundary value, and the contrast characteristic value corresponding to the third position image is equal to the minimum contrast characteristic value, then it is determined that the foreign object is located in the backlight layer.

[0259] Optionally, the foreign matter determining unit 407 is specifically configured to:

[0260] If it is determined that the foreign object is located below the screen, and the first ratio is greater than the first boundary value, and the contrast characteristic value corresponding to the first position image is equal to the minimum contrast characteristic value, then it is determined that the foreign object is located in the CG layer.

[0261] Optionally, the foreign matter determining unit 407 is specifically configured to:

[0262] If it is determined that the foreign object is located below the screen, and the first ratio is greater than the first boundary value, and the first ratio is less than the second boundary value, and the contrast characteristic value corresponding to the first position image is equal to the minimum contrast characteristic value, then it is determined that the foreign object is located in the OCA layer.

[0263] Optionally, the contrast feature value calculation unit 406 is specifically used for:

[0264] The contrast eigenvalue is calculated by the following formula:

[0265]

[0266] Where C represents the contrast eigenvalue, represents the mean pixel value of the defect area in the corresponding image, It represents the mean pixel value of the contrast background area in the corresponding image, and Bias represents the preset bias coefficient;

[0267] The above formula is used to calculate the defect area in image I B ,I C and I S The contrast eigenvalues ​​in C B , C C and CS , where I B ,I C and I S Respectively represent the first position image, the third position image and the fourth position image, C B , C C and C S The contrast feature values ​​corresponding to the three images are represented in turn.

[0268] Optionally, the final defect area determining unit 403 is specifically configured to:

[0269] If the first defect region and the second defect region have an intersection, a region obtained by merging the first defect region and the second defect region is determined as a final defect region.

[0270] If the first defect region and the second defect region do not have an intersection, the region with the largest area between the first defect region and the second defect region is determined as the final defect region.

[0271] Optionally, the defective area identifying unit 402 is specifically configured to:

[0272] The first position image and the third position image are processed respectively in the following manners to obtain corresponding defect areas:

[0273] Use a predefined convolution kernel to differentiate the image, and enhance the differentiated image to obtain a differential enhanced image;

[0274] Binarizing the differential enhanced image based on a preset threshold to obtain a binary image;

[0275] Performing Blob analysis on the binary image to determine the initial defect area;

[0276] The initial defect region is expanded using a rectangular structure element to obtain a defect region.

[0277] Optionally, the defective area identifying unit 402 is specifically configured to:

[0278] Differential enhancement is performed using the following formula:

[0279]

[0280] represents the horizontal convolution kernel, represents the convolution kernel in the vertical direction, represents the difference enhanced image, I represents the original image, Represents the preconfigured weight parameters.

[0281] Optionally, the contrast background area determining unit 404 is specifically configured to:

[0282] Determining the minimum circumscribed rectangle of the final defect area;

[0283] Expand the left and right sides and the upper and lower sides of the minimum circumscribed rectangle by a first distance and a second distance respectively to obtain an expanded rectangle;

[0284] The difference between the expanded rectangle and the final defect area is calculated to obtain a contrast background area.

[0285] The present application also provides a device for positioning foreign matter layers on an LCD display screen, comprising:

[0286] Processor 501, memory 502, input and output unit 503, bus 504;

[0287] The processor 501 is connected to the memory 502, the input and output unit 503 and the bus 504;

[0288] The memory 502 stores a program, and the processor 501 calls the program to execute any of the above-mentioned methods for locating foreign matter layers on an LCD display screen.

[0289] The present application also relates to a computer-readable storage medium, on which a program is stored. When the program is run on a computer, the computer executes any of the above-mentioned methods for locating foreign matter layers on an LCD display screen.

[0290] 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.

[0291] 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.

[0292] 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.

[0293] 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.

[0294] 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 locating foreign matter layers on an LCD display screen, characterized in that: The method comprises: Taking the pixel layer of the LCD screen as a reference, the small field of view camera is controlled to collect images from bottom to top at the BLU layer position, the pixel layer position, the CG layer position and the surface layer position, respectively, to obtain the first position image, the second position image, the third position image and the fourth position image; Respectively performing defect area recognition on the first position image and the third position image to obtain corresponding first defect area and second defect area; determining a final defect region based on the first defect region and the second defect region; determining a contrast background region based on the final defect region; Calculating the mean pixel values ​​of the contrast background area and the final defect area in the first position image, the third position image, and the fourth position image respectively, to obtain the mean pixel values ​​corresponding to the three contrast background areas and the mean pixel values ​​corresponding to the three final defect areas; Calculating the contrast characteristic value of the final defect area in each image based on the average pixel values ​​corresponding to the three contrast background areas and the average pixel values ​​corresponding to the three final defect areas, respectively, to obtain three corresponding contrast characteristic values; Based on a predetermined first boundary value and a second boundary value, the three contrast characteristic values ​​are compared, and the level at which the foreign matter is located is determined according to the comparison result; Comparing the three contrast feature values ​​includes: Determine a maximum contrast characteristic value among the three contrast characteristic values, and determine a minimum contrast characteristic value among the contrast characteristic values ​​corresponding to the first position image and the third position image; Compare the maximum contrast eigenvalue, the minimum contrast eigenvalue, and a first ratio with the first boundary value and the second boundary value, wherein the first ratio is a ratio of an absolute value of a difference between contrast eigenvalues ​​corresponding to the first position image and the third position image to the minimum contrast eigenvalue; The first boundary value is smaller than the second boundary value, and determining the level of the foreign matter according to the comparison result includes: When the maximum contrast characteristic value is equal to the contrast characteristic value corresponding to the fourth position image, it is determined that the foreign object is located above the screen; otherwise, it is determined that the foreign object is located below the screen.

2. The method for locating foreign matter layers on an LCD display screen according to claim 1, characterized in that: If it is determined that the foreign object is located below the screen and the first ratio is less than the first boundary value, it is determined that the foreign object is located at the pixel layer.

3. The method for locating foreign matter layers on an LCD display screen according to claim 1, characterized in that: If it is determined that the foreign object is located below the screen, and the first ratio is greater than the first boundary value, and the contrast characteristic value corresponding to the third position image is equal to the minimum contrast characteristic value, then it is determined that the foreign object is located in the backlight layer.

4. The method for locating foreign matter layers on an LCD display screen according to claim 1, characterized in that: If it is determined that the foreign object is located below the screen, and the first ratio is greater than the first boundary value, and the contrast characteristic value corresponding to the first position image is equal to the minimum contrast characteristic value, then it is determined that the foreign object is located in the CG layer.

5. The method for locating foreign matter layers on an LCD display screen according to claim 1, characterized in that: If it is determined that the foreign object is located below the screen, and the first ratio is greater than the first boundary value, and the first ratio is less than the second boundary value, and the contrast characteristic value corresponding to the first position image is equal to the minimum contrast characteristic value, then it is determined that the foreign object is located in the OCA layer.

6. The method for locating foreign matter layers on an LCD display screen according to claim 1, characterized in that: The step of calculating the contrast characteristic value of the final defect area in each image based on the average pixel values ​​corresponding to the three contrast background areas and the average pixel values ​​corresponding to the three final defect areas comprises: The contrast eigenvalue is calculated by the following formula: Where C represents the contrast eigenvalue, represents the mean pixel value of the defect area in the corresponding image, It represents the mean pixel value of the contrast background area in the corresponding image, and Bias represents the preset bias coefficient; The above formula is used to calculate the contrast characteristic values ​​of the defect area in images IB, IC and IS, respectively, and CB, CC and CS are obtained, where IB, IC and IS represent the first position image, the third position image and the fourth position image, respectively, and CB, CC and CS represent the contrast characteristic values ​​corresponding to the three images, respectively.

7. The method for locating foreign matter layers on an LCD display screen according to claim 1, characterized in that: The determining of the final defect area based on the first defect area and the second defect area comprises: If the first defect region and the second defect region have an intersection, a region obtained by merging the first defect region and the second defect region is determined as a final defect region.

8. The method for locating foreign matter layers on an LCD display screen according to claim 1, characterized in that: The determining of the final defect area based on the first defect area and the second defect area comprises: If the first defect region and the second defect region do not have an intersection, the region with the largest area between the first defect region and the second defect region is determined as the final defect region.

9. The method for locating foreign matter layers on an LCD display screen according to any one of claims 1 to 8, characterized in that: The performing defect area identification on the first position image and the third position image respectively to obtain the corresponding first defect area and second defect area comprises: The first position image and the third position image are processed respectively in the following manners to obtain corresponding defect areas: Use a predefined convolution kernel to differentiate the image, and enhance the differentiated image to obtain a differential enhanced image; Binarizing the differential enhanced image based on a preset threshold to obtain a binary image; Performing Blob analysis on the binary image to determine the initial defect area; The initial defect region is expanded using a rectangular structure element to obtain a defect region.

10. The method for locating foreign matter layers on an LCD display screen according to claim 9, characterized in that: The method of using a predefined convolution kernel to differentiate the image and enhancing the differentiated image to obtain a differentiated enhanced image includes: Differential enhancement is performed using the following formula: represents the horizontal convolution kernel, represents the convolution kernel in the vertical direction, represents the difference enhanced image, I represents the original image, Represents the preconfigured weight parameters.

11. The method for locating foreign matter layers on an LCD display screen according to any one of claims 1 to 8, characterized in that: Determining the contrast background area based on the final defect area includes: Determining the minimum circumscribed rectangle of the final defect area; Expand the left and right sides and the upper and lower sides of the minimum circumscribed rectangle by a first distance and a second distance respectively to obtain an expanded rectangle; The difference between the expanded rectangle and the final defect area is calculated to obtain a contrast background area.

12. A device for positioning foreign matter layers on an LCD display screen, characterized in that: The device comprises: An image acquisition unit is used to control the small field of view camera to acquire images at the BLU layer position, the pixel layer position, the CG layer position and the surface layer position from bottom to top based on the pixel layer of the LCD screen, so as to obtain a first position image, a second position image, a third position image and a fourth position image; A defect area recognition unit, used to perform defect area recognition on the first position image and the third position image respectively to obtain corresponding first defect area and second defect area; a final defect area determining unit, configured to determine a final defect area based on the first defect area and the second defect area; A contrast background area determination unit, configured to determine a contrast background area based on the final defect area; a pixel value mean calculation unit, used to respectively calculate the pixel value means of the contrast background area and the final defect area in the first position image, the third position image and the fourth position image, to obtain the pixel value means corresponding to the three contrast background areas and the pixel value means corresponding to the three final defect areas; A contrast characteristic value calculation unit, used to calculate the contrast characteristic value of the final defect area in each image based on the average pixel values ​​corresponding to the three contrast background areas and the average pixel values ​​corresponding to the three final defect areas, to obtain the corresponding three contrast characteristic values; a foreign matter determination unit, configured to compare the three contrast characteristic values ​​based on a predetermined first boundary value and a second boundary value, and determine a level at which the foreign matter is located according to a result of the comparison; The foreign body determination unit is specifically used for: Determine a maximum contrast characteristic value among the three contrast characteristic values, and determine a minimum contrast characteristic value among the contrast characteristic values ​​corresponding to the first position image and the third position image; Compare the maximum contrast eigenvalue, the minimum contrast eigenvalue, and a first ratio with the first boundary value and the second boundary value, wherein the first ratio is a ratio of an absolute value of a difference between contrast eigenvalues ​​corresponding to the first position image and the third position image to the minimum contrast eigenvalue; The foreign body determination unit is specifically used for: When the maximum contrast characteristic value is equal to the contrast characteristic value corresponding to the fourth position image, it is determined that the foreign object is located above the screen; otherwise, it is determined that the foreign object is located below the screen.

13. A device for positioning foreign matter layers on an LCD display screen, characterized in that: The 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 according to any one of claims 1 to 11.

Images