Panel product bright spot defect detection method, system and equipment and software product

Abstract

The invention provides a panel product bright spot defect detection method, system and device and a software product, and relates to the field of liquid crystal panel product defect detection.The method comprises the steps that a sample image is input into a target detection model for suspected bright spot detection, and a suspected bright spot defect image is obtained; carrying out pixel distribution statistics on the suspected bright spot defect image to determine a binary segmentation threshold, and carrying out light-emitting unit extraction on the suspected bright spot defect image based on the segmentation threshold to obtain a light-emitting unit image; calculating a brightness difference value and a size difference value of the suspected bright spot and the remaining light-emitting units based on the light-emitting unit image; and carrying out threshold verification on the brightness difference value and the size difference value of the suspected bright spot so as to judge whether the suspected bright spot is a bright spot defect or not. According to the method, the suspected bright spots are preliminarily positioned through the target detection algorithm, and then secondary confirmation is performed on the suspected bright spots by using the traditional CV detection method, so that the detection accuracy can be ensured, and the detection time can be effectively saved.

Description

Technical Field

[0001] The present invention relates to the field of liquid crystal panel product defect detection, and in particular to a panel product bright spot defect detection method, system, equipment and software product. Background Art

[0002] LCD panel products need to light up the screen to detect functional defects before leaving the factory. This process is called lighting inspection. Bright spot defects are a major defect in the lighting inspection. LCD panel products are composed of many periodic light-emitting units. Bright spot defects are when the brightness of some light-emitting units is higher than that of the surrounding light-emitting units. This defect will cause uneven color imaging of the panel and poor user experience.

[0003] The traditional CV detection method will first perform binarization and contour extraction on all light-emitting units on the panel, then locate all light-emitting units, and determine whether each light-emitting unit is a bright spot defect based on card control methods such as brightness and size. However, the traditional CV detection method is relatively cumbersome and requires the detection of all light-emitting units. Summary of the invention

[0004] In order to solve the problem that bright spot defect detection of existing liquid crystal panel products is relatively complicated, embodiments of the present invention provide a method, system, device and software product for bright spot defect detection of panel products.

[0005] In a first aspect, an embodiment of the present invention provides a method for detecting bright spot defects of a panel product, the method comprising the following steps:

[0006] Acquire an original image of a light-emitting unit of a liquid crystal panel, and perform pixel stretching on the original image to obtain a sample image, wherein the light-emitting unit of the liquid crystal panel is in a light-on state;

[0007] The sample image is input into the target detection model to perform suspected bright spot detection to obtain a suspected bright spot defect image;

[0008] Performing pixel distribution statistics on the suspected bright spot defect image to determine a binary segmentation threshold, and extracting luminous units from the suspected bright spot defect image based on the segmentation threshold to obtain a luminous unit image;

[0009] Calculating the brightness difference and size difference of the suspected bright spot and the remaining light-emitting units based on the light-emitting unit image to obtain the brightness difference and size difference of the suspected bright spot;

[0010] The brightness difference and size difference of the suspected bright spot are threshold checked to determine whether the suspected bright spot is a bright spot defect.

[0011] In the above embodiment, the present invention firstly uses the target detection algorithm to preliminarily locate the suspected bright spot, and then uses the traditional CV detection method to perform a second confirmation on the suspected bright spot, which can ensure the accuracy of the detection and effectively save the detection time.

[0012] As some optional implementations of the present application, the brightness value of the light-emitting unit of the liquid crystal panel product is in the range of 15 to 20 nits.

[0013] In the above embodiment, in order to make the characteristics of the bright spot defect more obvious, the present invention lights up the light-emitting unit of the liquid crystal panel with low brightness when detecting the bright spot defect.

[0014] As some optional implementations of the present application, the formula for pixel stretching of the original image is as follows:

[0015]

[0016] Among them, dist represents the pixel value of the sample image, src represents the pixel value of the original image, max(src) represents the maximum pixel value of the original image, and min(src) represents the minimum pixel value of the original image.

[0017] In the above embodiment, the present invention adopts the Normalize method to perform pixel stretching on the original image to achieve contrast enhancement.

[0018] As some optional implementations of the present application, the target detection model adopts Faster RCNN or YOLO.

[0019] In the above embodiment, the present invention preliminarily detects possible suspected bright spots through the trained target detection model, and cuts out the corresponding small picture with the suspected bright spot as the center to obtain the suspected bright spot defect image. Subsequent further confirmation of the suspected bright spot can be performed only on the small picture, without the need to detect all the light-emitting units in the entire large picture.

[0020] As some optional implementation modes of the present application, after performing pixel distribution statistics on the suspected bright spot defect image, it is necessary to perform binarization processing on the suspected bright spot defect image.

[0021] In the above embodiment, the present invention performs binarization processing on the suspected bright spot defect image to facilitate the extraction of all light-emitting units.

[0022] As some optional embodiments of the present application, the formula for calculating the brightness difference and size difference of the suspected bright spot and the remaining light-emitting units based on the light-emitting unit image is as follows:

[0023]

[0024] MB represents the brightness difference between the suspected bright spot and the average brightness of the remaining light-emitting units, and B t Expresses the brightness value of the suspected bright spot, B i represents the brightness value of the remaining i-th light-emitting unit, k represents the number of remaining light-emitting units, MS represents the size difference between the suspected bright spot and the average size of the remaining light-emitting units, S t Expresses the size of the suspected bright spot, S i Represents the size of the remaining i-th light-emitting unit.

[0025] In the above embodiment, the present invention can quantify the abnormality of the suspected bright spot by calculating the brightness difference and size difference between the light-emitting unit of the suspected bright spot and the remaining light-emitting units, so as to facilitate the subsequent determination of the bright spot defect.

[0026] As some optional implementations of the present application, the process of threshold checking the brightness difference and size difference of the suspected bright spot is as follows:

[0027] Obtaining a brightness difference threshold and a size difference threshold of a bright spot defect;

[0028] It is determined whether the brightness difference and size difference of the suspected bright spot are both greater than the brightness difference threshold and the size difference threshold. If so, the suspected bright spot is determined to be a bright spot defect. Otherwise, the suspected bright spot is determined not to be a bright spot defect.

[0029] In the above embodiment, the present invention can obtain the brightness difference threshold and the size difference threshold through sample calculation of historical bright spot defects. When the brightness difference between the suspected bright spot defect and other light-emitting units is greater than the brightness difference threshold, and the size difference is greater than the size difference threshold, the bright spot defect is detected.

[0030] In a second aspect, the present invention provides a panel product bright spot defect detection system, the functions of the system correspond to the steps of the method, and the system comprises:

[0031] An original image acquisition unit, the original image acquisition unit is used to acquire an original image of a light-emitting unit of a liquid crystal panel, and perform pixel stretching on the original image to obtain a sample image, wherein the light-emitting unit of the liquid crystal panel is in a lighted state;

[0032] A suspected bright spot detection unit, which is used to input the sample image into the target detection model to perform suspected bright spot detection to obtain a suspected bright spot defect image;

[0033] A light-emitting unit acquisition unit, the light-emitting unit acquisition unit is used to perform pixel distribution statistics on the suspected bright spot defect image to determine a binary segmentation threshold, and extract light-emitting units from the suspected bright spot defect image based on the segmentation threshold to obtain a light-emitting unit image;

[0034] a difference calculation unit, wherein the difference calculation unit calculates the brightness difference and size difference of the suspected bright spot and the remaining light-emitting units based on the light-emitting unit image to obtain the brightness difference and size difference of the suspected bright spot;

[0035] A threshold determination unit is used to perform a threshold check on the brightness difference and size difference of the suspected bright spot to determine whether the suspected bright spot is a bright spot defect.

[0036] In a third aspect, the present invention provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the method for detecting bright spot defects of panel products.

[0037] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for detecting bright spot defects of a panel product is implemented.

[0038] In a fifth aspect, the present invention provides a computer program product, including a computer program, which implements the method for detecting bright spot defects of panel products when executed by a processor.

[0039] The beneficial effects of the present invention are as follows: The present invention combines the target detection algorithm with the traditional CV detection method, detects the light-emitting units with bright spot defects based on the structural characteristics and light-emitting principles of the light-emitting units on the surface of the liquid crystal panel products, preliminarily locates the suspected bright spots through the target detection algorithm, and then reconfirms the suspected bright spots through the traditional CV detection method, thereby ensuring the accuracy of the detection and effectively saving the detection time. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0041] Figure 1 is a schematic diagram of the computer device structure of the hardware operating environment described in the embodiment of the present invention;

[0042] Figure 2 is a flow chart of a method for detecting bright spot defects of panel products according to an embodiment of the present invention;

[0043] Figure 3 is a comparison diagram of the original image and the sample image according to the embodiment of the present invention;

[0044] Figure 4 is the suspected bright spot defect image described in the embodiment of the present invention;

[0045] Figure 5 is a pixel distribution statistical diagram of the suspected bright spot defect image according to the embodiment of the present invention;

[0046] Figure 6 is a binary image of the light-emitting unit image described in the embodiment of the present invention;

[0047] Figure 7 It is a system block diagram of the panel product bright spot defect detection system described in an embodiment of the present invention. DETAILED DESCRIPTION

[0048] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0049] In order to solve the problem that the existing bright spot defect detection of liquid crystal panel products is relatively cumbersome, this application provides a panel product bright spot defect detection method, system, device and software product. Before introducing the specific technical solution of this application, the hardware operating environment involved in the embodiment of this application is first introduced.

[0050] See also Figure 1 , Figure 1 A schematic diagram of the computer device structure of the hardware operating environment involved in the embodiment of the present application.

[0051] like Figure 1 As shown, the computer device may include: a processor, such as a central processing unit (CPU), a communication bus, a user interface, a network interface, and a memory. Among them, the communication bus is used to realize the connection and communication between these components. The user interface may include a display screen (Display), an input unit such as a keyboard (Keyboard), and optionally, the user interface may also include a standard wired interface and a wireless interface. The network interface may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity interface). The memory may be a high-speed random access memory (Random Access Memory, RAM), or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk storage. The memory may optionally be a storage device independent of the aforementioned processor.

[0052] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the computer device, and may include more or less components than shown in the figure, or combine some components, or arrange the components differently.

[0053] like Figure 1 As shown, the memory as a storage medium may include an operating system module, a network communication module, a user interface module and a data storage module.

[0054] exist Figure 1 In the computer device shown, the network interface is mainly used for data communication with the network server; the user interface is mainly used for data interaction with the user; the processor and memory in the computer device of the present application can be set in the computer device, and the computer device calls the computer program stored in the data storage module in the memory through the processor, and executes the panel product bright spot defect detection method provided in the embodiment of the present application.

[0055] Based on the hardware environment of the aforementioned embodiment, the embodiment of the present application provides a method for detecting bright spot defects of panel products, see Figure 2 , Figure 2 The flowchart of the panel product bright spot defect detection method is as follows:

[0056] (1) Obtaining an original image of a light-emitting unit of a liquid crystal panel, and performing pixel stretching on the original image to obtain a sample image, wherein the light-emitting unit of the liquid crystal panel is in a lit state, see Figure 3 , Figure 3 is a comparison diagram of the original image and the sample image.

[0057] In the embodiment of the present invention, since the bright spot defect is more obvious against a background with lower brightness, the light-emitting unit of the liquid crystal panel is illuminated with low brightness when detecting the bright spot defect. Specifically, the brightness value of the light-emitting unit of the liquid crystal panel product is in the range of 15 to 20 nits; preferably, the brightness value of the light-emitting unit is 16 nits.

[0058] In the embodiment of the present invention, since the original image is invisible to the naked eye and the AI ​​algorithm cannot be used to detect the original image, the Normalize method is used to stretch the pixels of the original image to achieve contrast enhancement.

[0059] In the embodiment of the present invention, the pixel values ​​of the original image can be uniformly stretched to between 0 and 255 by performing pixel stretching on the original image. Specifically, the formula for performing pixel stretching on the original image is as follows:

[0060]

[0061] Among them, dist represents the pixel value of the sample image, src represents the pixel value of the original image, max(src) represents the maximum pixel value of the original image, and min(src) represents the minimum pixel value of the original image.

[0062] (2) Input the sample image into the target detection model to perform suspected bright spot detection to obtain a suspected bright spot defect image. Figure 4 , Figure 4 is the suspected bright spot defect image.

[0063] In an embodiment of the present invention, before inputting a sample image into a target detection model for suspected bright spot detection, it is necessary to train the target detection model, that is, first mark the position of the suspected bright spot of the sample image, and then input the marked sample image into the target detection model, and automatically learn the characteristics of the bright spot through the target detection model, so that the target detection model can identify the suspected bright spot and locate the suspected bright spot, so that the possible suspected bright spot can be preliminarily detected through the trained target detection model, and the small picture corresponding to the suspected bright spot is intercepted with the bright spot as the center to obtain the suspected bright spot defect image. Subsequent further confirmation of the suspected bright spot can be performed only on the small picture, without the need to detect all the light-emitting units of the entire large picture. Specifically, the target detection model includes but is not limited to the use of Faster RCNN or YOLO.

[0064] (3) Performing pixel distribution statistics on the suspected bright spot defect image to determine a binary segmentation threshold, and extracting luminous units from the suspected bright spot defect image based on the segmentation threshold to obtain a luminous unit image.

[0065] In the embodiment of the present invention, after the pixel distribution statistics of the suspected bright spot defect image are performed, the suspected bright spot defect image needs to be binarized to extract all the light-emitting units. Since there are random fluctuations in imaging, the brightness is not fixed, so the fixed grayscale threshold cannot be directly used for the binary segmentation of the suspected bright spot defect image. By performing pixel distribution statistics on the suspected bright spot defect image, the segmentation threshold of the binary segmentation can be determined.

[0066] Specifically, the pixel distribution statistics are to count the frequency of occurrence of the brightness of each pixel value in the image of the suspected bright spot defect image, and determine the binary segmentation threshold according to the frequency of occurrence of the brightness. Figure 5 , Figure 5 This is a statistical diagram of pixel distribution of a suspected bright spot defect image. About 10% of the pixels in the image are in the brightness peak area. This part is the pixel value of the luminous unit. Therefore, the quantile principle can be used to calculate the quantile of the suspected bright spot defect image. The quantile of the gray value of about 90% can be taken as the segmentation threshold. This segmentation threshold can better segment the luminous unit. Please refer to Figure 6 , Figure 6 is the binary image of the luminous unit image.

[0067] (4) Calculating the brightness difference and size difference of the suspected bright spot and the remaining light-emitting units based on the light-emitting unit image to obtain the brightness difference and size difference of the suspected bright spot.

[0068] In the embodiment of the invention, since the bright spot defect is manifested as having higher brightness and larger size than the adjacent light-emitting units, the brightness and size of each light-emitting unit are calculated.

[0069] Specifically, the formula for calculating the brightness difference and size difference of the suspected bright spot and the remaining light-emitting units based on the light-emitting unit image is as follows:

[0070]

[0071] MB represents the brightness difference between the suspected bright spot and the average brightness of the remaining light-emitting units, and B t Expresses the brightness value of the suspected bright spot, B i represents the brightness value of the remaining i-th light-emitting unit, k represents the number of remaining light-emitting units, MS represents the size difference between the suspected bright spot and the average size of the remaining light-emitting units, S t Expresses the size of the suspected bright spot, S i Represents the size of the remaining i-th light-emitting unit.

[0072] (5) Perform threshold verification on the brightness difference and size difference of the suspected bright spot to determine whether the suspected bright spot is a bright spot defect.

[0073] In the embodiment of the present invention, the process of threshold checking the brightness difference and size difference of the suspected bright spot is as follows:

[0074] (5.1) Obtain the brightness difference threshold and size difference threshold of the bright spot defect.

[0075] (5.2) Determine whether the brightness difference and size difference of the suspected bright spot are both greater than the brightness difference threshold and the size difference threshold. If so, determine that the suspected bright spot is a bright spot defect. Otherwise, determine that the suspected bright spot is not a bright spot defect.

[0076] In an embodiment of the present invention, a brightness difference threshold and a size difference threshold can be obtained by calculating sample images of historical bright spot defects. When the brightness difference between the suspected bright spot defect and other light-emitting units is greater than the brightness difference threshold, and the size difference is greater than the size difference threshold, the bright spot defect is detected.

[0077] Specifically, the process of obtaining the brightness difference threshold and size difference threshold of the bright spot defect is as follows:

[0078] (5.11) Acquire several historical sample images, and sequentially acquire the brightness values ​​and sizes of bright spot defects and remaining light-emitting units of the historical sample images;

[0079] (5.12) Calculate the brightness difference and size difference between the bright spot defect and the remaining light-emitting units, and perform mean statistics on the brightness difference and size difference of the brightness defects corresponding to several historical sample images to obtain the mean brightness difference and the mean size difference of several historical sample images, and use the mean brightness difference and the mean size difference as the brightness difference threshold and the size difference threshold of the bright spot defect.

[0080] In summary, the present invention combines the target detection algorithm with the traditional CV detection method, and detects the light-emitting units with bright spot defects based on the structural characteristics and light-emitting principles of the light-emitting units on the surface of the liquid crystal panel products. The suspected bright spots are preliminarily located by the target detection algorithm, and then the suspected bright spots are reconfirmed by the traditional CV detection method, thereby ensuring the accuracy of the detection and effectively saving the detection time.

[0081] In addition, in one embodiment, based on the same inventive concept as the above embodiment, the embodiment of the present invention provides a panel product bright spot defect detection system, and the system corresponds to the method of embodiment 1 one by one, please refer to Figure 7 , Figure 7 The structural block diagram of the panel product bright spot defect detection system is as follows:

[0082] An original image acquisition unit, the original image acquisition unit is used to acquire an original image of a light-emitting unit of a liquid crystal panel, and perform pixel stretching on the original image to obtain a sample image, wherein the light-emitting unit of the liquid crystal panel is in a lighted state;

[0083] A suspected bright spot detection unit, which is used to input the sample image into the target detection model to perform suspected bright spot detection to obtain a suspected bright spot defect image;

[0084] A light-emitting unit acquisition unit, the light-emitting unit acquisition unit is used to perform pixel distribution statistics on the suspected bright spot defect image to determine a binary segmentation threshold, and extract light-emitting units from the suspected bright spot defect image based on the segmentation threshold to obtain a light-emitting unit image;

[0085] a difference calculation unit, wherein the difference calculation unit calculates the brightness difference and size difference of the suspected bright spot and the remaining light-emitting units based on the light-emitting unit image to obtain the brightness difference and size difference of the suspected bright spot;

[0086] A threshold determination unit is used to perform a threshold check on the brightness difference and size difference of the suspected bright spot to determine whether the suspected bright spot is a bright spot defect.

[0087] It should be noted that each unit in the panel product bright spot defect detection system in this embodiment corresponds one-to-one to each step in the panel product bright spot defect detection method in the aforementioned embodiment. Therefore, the specific implementation method and technical effects achieved by this embodiment can refer to the implementation method of the aforementioned panel product bright spot defect detection method, and will not be repeated here.

[0088] In addition, in one embodiment, the present application also provides a computer device, which includes a processor, a memory, and a computer program stored in the memory, and the computer program implements the method in the aforementioned embodiment when executed by the processor.

[0089] In addition, in one embodiment, the present application further provides a computer storage medium, on which a computer program is stored, and the computer program implements the method in the aforementioned embodiment when executed by a processor.

[0090] In some embodiments, the computer readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or various devices including one or any combination of the above memories. The computer may be various computing devices including intelligent terminals and servers.

[0091] In some embodiments, executable instructions may be in the form of a program, software, software module, script or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine or other unit suitable for use in a computing environment.

[0092] As an example, executable instructions may, but need not, correspond to a file in a file system, may be stored as part of a file that stores other programs or data, such as in one or more scripts in a HyperText Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files storing one or more modules, subroutines, or code portions).

[0093] By way of example, executable instructions may be deployed to be executed on one computing device, or on multiple computing devices located at one site, or on multiple computing devices distributed across multiple sites and interconnected by a communication network.

[0094] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0095] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0096] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory / random access memory, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a multimedia terminal device (which can be a mobile phone, a computer, a television receiver, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0097] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for detecting bright spot defects of panel products, characterized in that: The method comprises the following steps: Acquire an original image of a light-emitting unit of a liquid crystal panel, and perform pixel stretching on the original image to obtain a sample image, wherein the light-emitting unit of the liquid crystal panel is in a light-on state; The sample image is input into the target detection model to perform suspected bright spot detection to obtain a suspected bright spot defect image; Performing pixel distribution statistics on the suspected bright spot defect image to determine a binary segmentation threshold, and extracting luminous units from the suspected bright spot defect image based on the segmentation threshold to obtain a luminous unit image; Calculating the brightness difference and size difference of the suspected bright spot and the remaining light-emitting units based on the light-emitting unit image to obtain the brightness difference and size difference of the suspected bright spot; The brightness difference and size difference of the suspected bright spot are threshold checked to determine whether the suspected bright spot is a bright spot defect.

2. A panel product bright spot defect detection method according to claim 1, characterized in that: The brightness value of the light-emitting unit of the liquid crystal panel product when lit is in the range of 15 to 20 nits.

3. The method for detecting bright spot defects of panel products according to claim 1, characterized in that: The formula for pixel stretching of the original image is as follows: Among them, dist represents the pixel value of the sample image, src represents the pixel value of the original image, max(src) represents the maximum pixel value of the original image, and min(src) represents the minimum pixel value of the original image.

4. The method for detecting bright spot defects of panel products according to claim 1, characterized in that: The target detection model uses Faster RCNN or YOLO.

5. The method for detecting bright spot defects of panel products according to claim 1, characterized in that: After performing pixel distribution statistics on the suspected bright spot defect image, the suspected bright spot defect image needs to be binarized.

6. The method for detecting bright spot defects of panel products according to claim 1, characterized in that: The formula for calculating the brightness difference and size difference of the suspected bright spot and the remaining light-emitting units based on the light-emitting unit image is as follows: MB represents the brightness difference between the suspected bright spot and the average brightness of the remaining light-emitting units, and B t Expresses the brightness value of the suspected bright spot, B i represents the brightness value of the remaining i-th light-emitting unit, k represents the number of remaining light-emitting units, MS represents the size difference between the suspected bright spot and the average size of the remaining light-emitting units, S t Expresses the size of the suspected bright spot, S i Represents the size of the remaining i-th light-emitting unit.

7. The method for detecting bright spot defects of panel products according to claim 1, characterized in that: The process of threshold verification for the brightness difference and size difference of suspected bright spots is as follows: Obtaining a brightness difference threshold and a size difference threshold of a bright spot defect; It is determined whether the brightness difference and size difference of the suspected bright spot are both greater than the brightness difference threshold and the size difference threshold. If so, the suspected bright spot is determined to be a bright spot defect. Otherwise, the suspected bright spot is determined not to be a bright spot defect.

8. A panel product bright spot defect detection system, characterized in that: The system comprises: An original image acquisition unit, the original image acquisition unit is used to acquire an original image of a light-emitting unit of a liquid crystal panel, and perform pixel stretching on the original image to obtain a sample image, wherein the light-emitting unit of the liquid crystal panel is in a lighted state; A suspected bright spot detection unit, which is used to input the sample image into the target detection model to perform suspected bright spot detection to obtain a suspected bright spot defect image; A light-emitting unit acquisition unit, the light-emitting unit acquisition unit is used to perform pixel distribution statistics on the suspected bright spot defect image to determine a binary segmentation threshold, and extract light-emitting units from the suspected bright spot defect image based on the segmentation threshold to obtain a light-emitting unit image; a difference calculation unit, wherein the difference calculation unit calculates the brightness difference and the size difference of the suspected bright spot and the remaining light-emitting units based on the light-emitting unit image to obtain the brightness difference and the size difference of the suspected bright spot; A threshold determination unit is used to perform a threshold check on the brightness difference and size difference of the suspected bright spot to determine whether the suspected bright spot is a bright spot defect.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for detecting bright spot defects of panel products as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for detecting bright spot defects of a panel product described in any one of claims 1 to 7 is implemented.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, a method for detecting bright spot defects of a panel product as described in any one of claims 1 to 7 is implemented.

Images