A method and system for producing an automated display panel
By segmenting the grayscale image of the display panel and calculating the probability of bright spots, bright spot areas are identified and repaired, solving the problem of missed detection in the existing technology and improving the accuracy of detection and production efficiency.
Patent Information
- Application Number
- CN202410881399.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-03
- Publication Date
- 2024-11-01
- Estimated Expiration
- 2044-07-03
AI Technical Summary
Existing technologies are prone to missing defects in display panel defect detection and cannot effectively repair defects caused by external factors, affecting panel quality and reliability.
By segmenting the grayscale image of the display panel into blocks, calculating the impact of image segmentation and the probability of bright spots, and combining the change vector and the degree of interference, the bright spot areas are identified, and the defective panels are automatically transferred to the repair area for repair.
It improves the accuracy of defect detection, reduces missed and false detections, ensures timely panel repair, and improves production efficiency and panel quality.
Smart Images

Figure CN118429338B_ABST
Abstract
Description
Technical Field
[0001] The present invention generally relates to the field of image processing. The present invention relates to an automated display panel production method and system. Background Art
[0002] An automation display panel is an interface used to monitor and control automation systems. It is usually composed of software and hardware, and is used to display real-time data, execute control commands, and configure parameters. In the production and processing of automated display panels, the automated display panels need to be tested after the completed circuit boards are assembled with the display panels and various components. Through testing, problems with the display panels during the production process are promptly discovered and corrected to ensure that they operate normally and meet specification requirements.
[0003] The patent application document with publication number CN109636778A discloses a display panel defect detection method and a display panel defect detection device. The method obtains an image of the display panel, grayscales the image of the display panel, and then binarizes the image after grayscale processing. When the binarized image grayscale of all regions of the binarized image is 0, the binarized image is judged to be defective. When the middle region and the peripheral region of the binarized image have different binarized image grayscales, the binarized image is judged to be non-defective. Non-defects such as water droplets have black surroundings and bright middle regions. Thus, the panel defects and / or non-defects can be correctly detected to avoid the problem of waste of production capacity caused by false detection.
[0004] The above-mentioned defect detection of the display panel has limitations. It only determines whether the display panel has defects based on external influencing factors such as water droplets. This limitation may lead to missed detection during the detection process and fail to repair the defects of the display panel well, thereby affecting the overall quality and reliability of the display panel. Summary of the invention
[0005] In order to solve the technical problem that in defect detection of display panels, only external influencing factors may easily lead to missed detection during the detection process, and the defects of the display panels cannot be repaired well, thereby affecting the overall quality and reliability of the display panels, the present invention provides solutions in the following aspects.
[0006] In a first aspect, an automated display panel production method includes: acquiring an image of each display panel;
[0007] Converting the image into a grayscale image, and obtaining position information of defects in the grayscale image;
[0008] According to the location information of the defect, the corresponding display panel is transferred to a maintenance area so as to repair the defective area;
[0009] The process of obtaining the position information of the defect is as follows:
[0010] Divide the grayscale image into a plurality of image blocks, and calculate the influence degree of each image block, wherein the influence degree is obtained by a first difference and a second difference; wherein the first difference is the grayscale difference between any pixel point and its adjacent pixel point in the grayscale change direction, and the second difference is the grayscale difference between any pixel point and its adjacent pixel point in the grayscale change direction in the adjacent image blocks;
[0011] Calculate the probability that the pixel is a bright spot, the probability being the first product minus the second product; the first product being the product of the change vector of the pixel and the degree of influence of the image block where the pixel is located, and the second product being the product of the change vector of the pixel's neighborhood pixels and the degree of influence of the image block where the neighborhood pixels are located;
[0012] Update the grayscale value of the grayscale image according to the probability and find the bright spot area in the grayscale image.
[0013] Beneficial effect: The present invention divides the grayscale image of the display panel into blocks and calculates the influence of the image blocks to identify the bright spot area in the image, and further uses the probability calculation method of the pixel point being a bright spot, combined with the product of the change vector and the influence degree, to reduce missed detection and false detection, thereby accurately locating the position of the defect on the display panel, and automatically transferring the defective display panel to the maintenance area for repair based on the defect location information. This automated transfer and repair process not only improves production efficiency, but also ensures that defects are handled in a timely and appropriate manner.
[0014] In one embodiment, before acquiring the position information of the defect in the grayscale image, the method includes:
[0015] Dividing the grayscale image into a plurality of image blocks;
[0016] Calculating the ratio of the grayscale mean of the image block to the grayscale variance of the pixels in the image block, and using the ratio as the interference degree of the image block, wherein the interference degree is used to evaluate the influence of the grayscale change caused by the bright spot on the internal consistency of the image block;
[0017] When the variance is not 0, the image block is marked as defective; otherwise, it is marked as normal.
[0018] Beneficial effect: By calculating the ratio of the grayscale mean to the variance of each image block, this ratio reflects the size of the central tendency of the pixel grayscale value in the image block relative to the discrete tendency. It is an important indicator for evaluating whether the image block is affected by interference such as bright spots. Among them, by distinguishing between normal display panels and defective display panels, it helps to simplify subsequent operations.
[0019] In one embodiment, the grayscale change direction is a line connecting a pixel point with the maximum grayscale value and a pixel point with the minimum grayscale value in the image block.
[0020] Beneficial effect: By determining the line connecting the maximum and minimum grayscale values in an image block, the grayscale range in the area can be intuitively seen.
[0021] In one embodiment, the degree of influence is:
[0022] ; In the formula, For the degree of impact, For the In the image block The pixel point is in the grayscale change direction. The grayscale difference of the pixels adjacent to the pixel, is the first The neighboring blocks of the image block The grayscale difference between a pixel and its adjacent pixels, For the said The interference degree of each image block, For the said The interference degree of the image block where the pixel point is located.
[0023] Beneficial effect: The corresponding interference degree factor is introduced, which takes into account both the grayscale change within the image block and the grayscale change when the line segment in the grayscale change direction passes through the adjacent block, and these differences are weighted to more accurately evaluate the impact of bright spots.
[0024] In one embodiment, the step of obtaining the change vector of the pixel point is:
[0025] Obtaining a change direction of the pixel point; the change direction is a direction from a low grayscale value to a high grayscale value between the pixel point in the grayscale image and a pixel point in its neighborhood with the largest grayscale difference;
[0026] The change direction is taken as the vector direction, and the maximum grayscale difference between the pixel point and the pixels in its neighborhood is taken as the magnitude of the vector, so as to obtain the change vector of the pixel point.
[0027] In one embodiment, the step of obtaining the change vector of the image block is:
[0028] The grayscale change direction is used as the vector direction of the image block, and the difference between the maximum grayscale value and the minimum grayscale value in the image block is used as the size of the vector to obtain the change vector of the image block.
[0029] In one embodiment, the probability that the pixel is a bright spot is:
[0030] ; In the formula, is the grayscale image The probability that a pixel is a bright spot, For the said The change vector of the pixel point, For the said The change vector of the image block where the pixel point is located, For the The influence of the image block where the pixel point is located, For the The magnitude of the change vector of pixels, For the The pixel in the neighborhood The influence of the image block where the pixel point is located, For the The pixel in the neighborhood The magnitude of the change vector of pixels, is the normalization function, Represents weight.
[0031] In one embodiment, the step of updating the grayscale value of the grayscale image according to the probability is:
[0032] The probability that the pixel is a bright spot is normalized, and the normalized probability is multiplied by the original grayscale value of the corresponding pixel to obtain a new grayscale value of the pixel, thereby obtaining an updated grayscale image.
[0033] Beneficial effects: By updating the grayscale value of the grayscale image, a clear defect map is further provided to maintenance personnel, making the repair work more targeted and efficient.
[0034] In a second aspect, an automated display panel production system includes: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the automated display panel production method described above is implemented. BRIEF DESCRIPTION OF THE DRAWINGS
[0035] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:
[0036] Figure 1It is a schematic diagram showing color distortion of a display panel in an automated display panel production method according to an embodiment of the present invention.
[0037] Figure 2 It is a schematic diagram of bright spots existing on a display panel in an automated display panel production method according to an embodiment of the present invention.
[0038] Figure 3 It is a method flow chart of steps S1-S3 in an automated display panel production method according to an embodiment of the present invention. DETAILED DESCRIPTION
[0039] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.
[0040] During the production and processing of display panels, it is necessary to perform defect detection on the display panels to meet the quality requirements of the display panels. Among the defects of the display panels themselves, there are color distortion and bright spots. Among them:
[0041] Color distortion refers to the deviation of the color performance of the display panel from the expected or standard color, which may include color oversaturation, hue deviation, reduced contrast, etc. (such as Figure 1 Color distortion is usually caused by improper color calibration, the wrong color profile of the monitor, incorrect settings of the graphics card or driver software, and in some cases, such as monitor aging or hardware failure.
[0042] Bright spots are spots on the display panel that are brighter than the surrounding area. They are usually easier to see against a black or dark background (such as Figure 2 ). These spots may affect the uniformity of the screen and the viewing experience. The formation of bright spots may be caused by a variety of factors, including local damage to the backlight module, irregularities in the arrangement of liquid crystals, changes in internal reflection or refraction, etc. For example, partial damage to the LED strip in the backlight panel may cause local brightness abnormalities.
[0043] It should be noted that the area affected by bright spots is small, and the grayscale mutation caused by it is usually limited to a small range. Color distortion usually manifests as unnatural transitions between colors. These transitions should be smooth and continuous without external interference. In the area of color distortion, the grayscale value of the pixel point usually changes slowly and gradually. This gradient visually presents a smooth color transition. When the display panel has color distortion, the local color changes are approximate, and the appearance of bright spots may break this approximation, making the color changes in the affected area differ greatly from the surrounding area.
[0044] The reasons for color distortion and bright spots are different, so the inspection and repair methods are different for different defects, so it is necessary to distinguish between the two defects.
[0045] The embodiment of the present invention discloses an automated display panel production method, referring to Figure 3 , including steps S1-S3, as follows
[0046] S1: Collect images of each display panel.
[0047] In the embodiment of the present invention, a high-definition industrial camera is used to capture multiple display panel images.
[0048] S2: Convert the image into a grayscale image, and obtain position information of defects in the grayscale image.
[0049] In an embodiment of the present invention, the image of each display panel is preprocessed. First, semantic segmentation is performed, usually using a deep learning model such as a convolutional neural network to distinguish the display panel and the background in the display panel image. Then, a grayscale algorithm is applied to the display panel area to obtain a grayscale image containing only the display panel.
[0050] The grayscale image is divided into multiple image blocks of size 5×5. Any image block is selected as an example to obtain the grayscale values of all pixels in the image block, thereby calculating the grayscale variance of the pixels in the image block and the grayscale mean of the image block. According to the grayscale variance and the grayscale mean, the interference degree of the image block is calculated to evaluate the influence of the grayscale change caused by the bright spot on the internal consistency of the image block.
[0051] Then the interference degree of the above image block is:
[0052]
[0053] In the formula, is the interference degree of the image block, is the grayscale variance of the pixels in the image block, The first The gray value of a pixel, is the grayscale mean of the image block, is the normalization function.
[0054] The greater the interference degree of the image block, the greater the influence of the bright spot on the block. Among them, there is a grayscale change at the center of the bright spot, but the change at the position of the bright spot is very small, and the color of the normal screen is relatively uniform. Therefore, when the grayscale variance of the pixel point in the image block is 0, the corresponding display panel is recorded as a normal display panel, otherwise, it is recorded as a defective display panel.
[0055] Based on the defective display panel, identify the location information of the defect. The specific steps are as follows:
[0056] First, the grayscale image is divided into multiple image blocks, and the influence degree of the bright spot of each image block is calculated.
[0057] Specifically, the Take the image block as an example, and take the image block as the center to obtain eight domain image blocks. In the image block, the direction of the line connecting the pixel with the largest gray value and the pixel with the smallest gray value is taken as the first The grayscale change direction of an image block represents the main grayscale change direction in the image block.
[0058] Get the In the image block The pixel point is in the grayscale change direction. The grayscale difference of the pixel points adjacent to the pixel point, and obtain the grayscale change direction of the first pixel point The neighboring blocks of the image block The grayscale difference between a pixel and its adjacent pixels is then calculated. The influence of each image block.
[0059] Then the expression of the above influence degree is:
[0060] ; In the formula, For the degree of impact, For the In the image block The pixel point is in the grayscale change direction. The grayscale difference of the pixels adjacent to the pixel, is the first The neighboring blocks of the image block The grayscale difference between a pixel and its adjacent pixels, For the said The interference degree of each image block, For the said The interference degree of the image block where the pixel point is located.
[0061] Among them, the interference degree factor is introduced to consider both the grayscale changes within the image block and the grayscale changes when the line segment corresponding to the grayscale change direction passes through other blocks. These differences are weighted by the interference degree to more accurately evaluate the impact of bright spots.
[0062] The larger the value, the greater the degree to which the block is affected by the bright spot.
[0063] Secondly, when the display panel only has color distortion, the local changes of the display panel are very similar. When the display panel is affected by bright spots, the location of the bright spots will be different from the local changes of other color distortion locations. At the same time, the area affected by the bright spots is small, so by comparing the block range with the pixel area range, the greater the difference between the local pixel point and its existence, the greater the impact of the bright spot on the pixel point.
[0064] Specifically, the grayscale image Take a pixel point as an example, obtain the pixel points in the eight neighborhoods of the pixel point, and determine the The pixel with the largest grayscale value difference is used to determine the first pixel. The change direction of each pixel point, and the grayscale difference between them is taken as the change amplitude, so that The direction and magnitude of the change vector of the pixel point are determined. Similarly, the grayscale change direction is used as the first The vector direction of the image block where the pixel point is located, the difference between the maximum grayscale value and the minimum grayscale value in the image block is taken as the size of the vector, and the The fastest change vector of the image where the pixel is located.
[0065] According to The difference between the change vector of the pixel point and the change vector of the corresponding image block is obtained. The probability that a pixel is a bright spot is expressed as follows:
[0066] ; In the formula, is the grayscale image The probability that a pixel is a bright spot, For the said The change vector of the pixel point, For the said The change vector of the image block where the pixel point is located, For the The influence of the image block where the pixel point is located, For the The magnitude of the change vector of pixels, For the The pixel in the neighborhood The influence of the image block where the pixel point is located, For the The pixel in the neighborhood The magnitude of the change vector of pixels, is the normalization function, Represents weight.
[0067] Among them, through It represents the span weight of the acute angle between two vectors. The larger the angle, the greater the local change, and the greater the impact of the bright spot.
[0068] Considering the The product difference between the change amplitude of a pixel and its neighboring pixels and their corresponding influence degree further emphasizes the discontinuity of changes in the local area caused by the bright spot.
[0069] Finally, the grayscale value of the grayscale image is updated according to the probability obtained above, the probability that the pixel is a bright spot is normalized, and the normalized probability is multiplied by the original grayscale value of the corresponding pixel to obtain a new grayscale value of the pixel to enhance the pixel affected by the light spot. The updated grayscale image is processed by the Otsu threshold segmentation method to find the bright spot area in the grayscale image.
[0070] S3: According to the location information of the defect, the corresponding display panel is transferred to a maintenance area to repair the defective area.
[0071] Based on the bright spot area obtained in step S2, the display panels with bright spot problems and the display panels with only color distortion are distinguished, and the display panels with bright spot problems are transferred to the bright spot repair area, which can be compensated by replacing the backlight module or using software algorithms; the display panels with only color distortion are transferred to the color distortion repair area, and professional color calibration tools and software can be used to adjust the color settings of the display to ensure color accuracy and consistency.
[0072] An embodiment of the present invention further discloses an automated display panel production system, including a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the automated display panel production method according to the present invention is implemented.
[0073] The system also includes other components familiar to those skilled in the art, such as a communication bus and a communication interface. The configuration and functions of these components are known in the art and will not be described in detail here.
[0074] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, apparatus or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module or both. Any such computer storage medium may be part of a device or accessible or connectable to a device.
[0075] In the description of this specification, "plurality" or "several" means at least two, such as two, three or more, etc., unless otherwise clearly and specifically defined.
[0076] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.
Claims
1. An automated display panel production method, It is characterized in that include: collecting images of each display panel; Converting the image into a grayscale image, and dividing the grayscale image into a plurality of image blocks; Calculating the ratio of the grayscale mean of the image block to the grayscale variance of the pixels in the image block, and taking the ratio as the interference degree of the image block, the interference degree is used to evaluate the influence of the grayscale change caused by the bright spot on the internal consistency of the image block; wherein, when the variance is not 0, the image block is marked as defective; otherwise, it is marked as normal; obtaining the position information of the defect in the grayscale image; and according to the position information of the defect, transferring the corresponding display panel to the maintenance area to repair the defective area; The process of obtaining the position information of the defect is as follows: Divide the grayscale image into a plurality of image blocks, and calculate the influence degree of each image block, wherein the influence degree is obtained by a first difference and a second difference; wherein the first difference is the grayscale difference between any pixel point and its adjacent pixel point in the grayscale change direction, and the second difference is the grayscale difference between any pixel point and its adjacent pixel point in the grayscale change direction in the adjacent image blocks; The impact levels are: ; In the formula, For the degree of impact, For the In the image block The pixel point is in the grayscale change direction. The grayscale difference of the pixels adjacent to the pixel, is the first The neighboring blocks of the image block The grayscale difference between a pixel and its adjacent pixels, For the The degree of interference of each image block, For the The degree of interference of the image block where the pixel point is located; Calculate the probability that the pixel is a bright spot, the probability being the first product minus the second product; the first product being the product of the change vector of the pixel and the degree of influence of the image block where the pixel is located, and the second product being the product of the change vector of the pixel's neighborhood pixels and the degree of influence of the image block where the neighborhood pixels are located; The probability that the pixel is a bright spot is: ; In the formula, is the grayscale image The probability that a pixel is a bright spot, For the The change vector of the pixel point, For the The change vector of the image block where the pixel point is located, For the The influence of the image block where the pixel point is located, For the The magnitude of the change vector of pixels, For the The pixel in the neighborhood The influence of the image block where the pixel point is located, For the The pixel in the neighborhood The magnitude of the change vector of pixels, is the normalization function, represents weight; Update the grayscale value of the grayscale image according to the probability and find the bright spot area in the grayscale image.
2. The method for producing an automated display panel according to claim 1, It is characterized in that The grayscale change direction is the line connecting the pixel with the largest grayscale value and the pixel with the smallest grayscale value in the image block.
3. The method for producing an automated display panel according to claim 1, It is characterized in that The steps for obtaining the change vector of the pixel point are: Obtaining a change direction of the pixel point; the change direction is a direction from a low grayscale value to a high grayscale value between the pixel point in the grayscale image and a pixel point in its neighborhood with the largest grayscale difference; The change direction is taken as the vector direction, and the maximum grayscale difference between the pixel point and the pixels in its neighborhood is taken as the magnitude of the vector, so as to obtain the change vector of the pixel point.
4. The method for producing an automated display panel according to claim 3, It is characterized in that The steps for obtaining the change vector of the image block are: The grayscale change direction is used as the vector direction of the image block, and the difference between the maximum grayscale value and the minimum grayscale value in the image block is used as the size of the vector to obtain the change vector of the image block.
5. The method for producing an automated display panel according to claim 1, It is characterized in that The steps to update the grayscale value of the grayscale image according to the probability are: The probability that the pixel is a bright spot is normalized, and the normalized probability is multiplied by the original grayscale value of the corresponding pixel to obtain a new grayscale value of the pixel, thereby obtaining an updated grayscale image.
6. An automated display panel production system, It is characterized in that include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the automated display panel production method according to any one of claims 1 to 5 is implemented.
