Panel processing system and false defect discrimination method

Abstract

The application relates to a panel processing system and a false defect distinguishing method. The system comprises a camera, a processing device, a judging device and a packaging device. The camera captures a lighting image of a display panel during a lighting test corresponding to a cell process of the display panel. The processing device performs defect detection and defect correction prediction on the lighting image to obtain a defect detection result and a defect correction prediction result corresponding to the display panel. The defect detection result indicates whether the display panel has defects such as Mura. The defect correction prediction result indicates whether the display panel with the Mura defect can be successfully corrected by a stain in a module engineering stage. The judging device obtains a good product judging result based on the defect detection result and the defect correction prediction result corresponding to the display panel. The good product judging result indicates whether the display panel is a good product. The packaging device judges whether to perform a packaging process on the display panel based on the good product judging result corresponding to the display panel, thereby reducing resource waste.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence (AI) technology, and in particular to a panel processing system and a method for distinguishing false defects. Background Technology

[0002] With the high-quality development of display panels, users' quality requirements for display panels are also continuously upgrading, and zero display unevenness (Mura) defects have become a core development trend. Therefore, in the production process of display panels, the requirements for Mura defect detection capabilities and the ability to improve product quality through demura correction technology are becoming increasingly stringent.

[0003] Currently, after the display panel undergoes the cell assembly process, the next steps involve inspecting the panel for Mura defects and proceeding with subsequent packaging and module engineering. Module engineering involves assembling components such as polarizers, chip-on-flex (COF) films, and printed board assemblies (PBAs) on the display panel. Following module engineering, further contamination correction is performed to remove Mura defects and improve the overall quality of the display panel.

[0004] However, there may be cases where stain correction fails, leading to unnecessary packaging and module engineering of the display panel, resulting in a waste of resources. Summary of the Invention

[0005] This application provides a panel processing system and a method for distinguishing false defects, avoiding unnecessary processes, reducing resource waste, and at least partially solving the above-mentioned technical problems.

[0006] To achieve the above objectives, according to a first aspect of this application, a panel processing system is provided, the system comprising a camera, a processing device, a determination device, and a packaging device; The camera is used to capture images of the display panel during the cell assembly process, to obtain an image of the display panel under illumination, and to send the image of the display panel under illumination to the processing device. The processing device is used to perform defect detection on the lamp image, obtain a defect detection result corresponding to the display panel, and send the defect detection result corresponding to the display panel to the judgment device; wherein, the defect detection result indicates whether there is a defect in the display panel, and the defect includes uneven display Mura defect; The system performs defect correction prediction on the illumination image to obtain a defect correction prediction result corresponding to the display panel, and sends the defect correction prediction result corresponding to the display panel to the determination device; wherein, the defect correction prediction result indicates whether the display panel with Mura defects can be successfully corrected for smudges during the module engineering stage; The judging device is used to obtain a good product judgment result for the display panel based on the defect detection result and defect correction prediction result corresponding to the display panel, and send the good product judgment result for the display panel to the packaging equipment; wherein, the good product judgment result indicates whether the display panel is a good product; The packaging equipment is used to determine whether to package the display panel based on the good product judgment result corresponding to the display panel.

[0007] In some embodiments, the processing apparatus is specifically used for: The target AI model is used to predict whether the Mura defects can be successfully corrected. The target AI model is trained on a training set, which includes display panel images of Mura defects that have been successfully corrected and display panel images of Mura defects that have not been corrected.

[0008] In some embodiments, the display panel image is further labeled with a defect type, and the processing device is specifically used for: Based on the target AI model, defect detection is performed on the lighting image.

[0009] In some embodiments, the processing apparatus is specifically used for: If the defect detection result corresponding to the display panel indicates that only Mura defects exist, defect correction prediction is performed on the lamp image corresponding to the display panel. If the defect detection result corresponding to the display panel indicates the presence of defects other than the Mura defect, no defect correction prediction will be performed on the lamp image corresponding to the display panel.

[0010] In some embodiments, the determining device is specifically used for: If the defect detection result corresponding to the display panel indicates that only Mura defects exist, the good product determination result corresponding to the display panel is obtained based on the defect detection result and defect correction prediction result corresponding to the display panel. If the defect detection result corresponding to the display panel indicates the presence of defects other than the Mura defect, a good product determination result corresponding to the display panel is obtained based on the defect detection result corresponding to the display panel.

[0011] In some embodiments, if the defect detection result corresponding to the display panel indicates that only Mura defects exist, and the defect correction prediction result indicates that the stain correction is successful, the good product determination result corresponding to the display panel indicates that the display panel is a good product; If the defect detection result corresponding to the display panel indicates that only Mura defects exist, and the defect correction prediction result indicates that stain correction has failed, the good product judgment result corresponding to the display panel indicates that the display panel is not a good product. If the defect detection result corresponding to the display panel indicates the presence of defects other than the Mura defect, the good product determination result corresponding to the display panel indicates that the display panel is not a good product.

[0012] In some embodiments, the packaging device is specifically configured to send a result acquisition request to the determination device when the display panel arrives; The determination device is specifically used to respond to the result acquisition request by sending the good product determination result corresponding to the display panel to the packaging device.

[0013] According to a second aspect of this application, a method for distinguishing false defects is provided, the method comprising: Obtain the defect detection result corresponding to the display panel that has undergone the cell process; wherein, the defect detection result indicates whether there is a defect in the display panel, and the defect includes uneven display Mura defect; the defect detection result is obtained by performing defect detection on the lamp image captured during the lamp test corresponding to the cell process of the display panel; Obtain the defect correction prediction result corresponding to the display panel; wherein, the defect correction prediction result indicates whether the display panel with Mura defects can be successfully corrected for smudges during the module engineering stage; Based on the defect detection results and defect correction prediction results corresponding to the display panel, the good product determination result corresponding to the display panel is obtained; wherein, the good product determination result indicates whether the display panel is a good product.

[0014] In some embodiments, obtaining the good product determination result corresponding to the display panel based on the defect detection result and defect correction prediction result corresponding to the display panel includes: If the defect detection result corresponding to the display panel indicates that only Mura defects exist, the good product determination result corresponding to the display panel is obtained based on the defect detection result and defect correction prediction result corresponding to the display panel.

[0015] According to a third aspect of this application, a chip is provided, including a memory storing a plurality of instructions; a processor loads instructions from the memory to execute steps in any of the false defect differentiation methods provided in the embodiments of this application.

[0016] According to a fourth aspect of this application, a computer-readable storage medium is provided having a computer program or instructions stored thereon, which, when executed by a processor, implement the steps in the false defect discrimination method described above.

[0017] According to a fifth aspect of this application, a computer program product is provided, comprising a computer program or instructions that, when executed by a processor, implement the steps of any of the false defect discrimination methods provided in this application.

[0018] The panel processing system provided in this application includes a camera, a processing unit, a judging unit, and a packaging device. The camera captures images of the display panel during the lamp-on testing stage of the cell assembly process to obtain lamp-on images. The processing unit uses these lamp-on images to perform defect detection to determine if the display panel has defects such as Mura defects, and uses these images to predict defect correction to determine if the Mura defects can be successfully corrected during the module engineering stage. Then, the judging unit determines the yield judgment result of the display panel based on the defect detection results and the defect correction prediction results, thus determining whether display panels with Mura defects can be made into yield products, achieving early screening of non-yieldable display panels. Finally, the packaging device determines whether to continue packaging the display panel based on whether it is a yield product, avoiding packaging and module engineering processes on non-yieldable display panels, thereby avoiding unnecessary processes, resource waste, and improving the overall yield and resource utilization efficiency of panel production.

[0019] Other features and advantages of this application will be described in detail in the following detailed description section. Attached Figure Description

[0020] Figure 1 This is a schematic diagram of a panel processing procedure provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of a panel processing system provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of a display panel image provided in an embodiment of the present invention. Figure 1 ; Figure 4 This is a schematic diagram of a display panel image provided in an embodiment of the present invention. Figure 2 ; Figure 5 This is a flowchart illustrating a method for distinguishing false defects provided in an embodiment of the present invention. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0022] With the high-quality development of display panels, users' quality requirements for display panels are also continuously upgrading, and zero Mura defects have become a core development trend. Therefore, in the production process of display panels, the requirements for Mura defect detection capabilities and the ability to improve product quality through stain correction (or optical correction) technology are becoming increasingly stringent.

[0023] In the display industry, during the cell process of the FAB stage, lamp-lighting testing primarily involves driving the display panel to display a test image. A camera automatically captures images (i.e., lamp-lighting images), and then traditional image processing algorithms are used to detect fixed-form Mura defects. This is essentially automatic picture inspection (API) of the lamp-lighting images. Specifically, lamp-lighting testing uses a display panel lamp-lighting machine. Through a shortening bar method, a full-screen image (e.g., white, red, green, blue, black, and grayscale) is displayed on the display panel. The camera then captures an image of the display panel displaying this image, obtaining the corresponding lamp-lighting image.

[0024] However, for the Mura defects detected in the display panels, it is impossible to predict in advance the repair effect of the Mura defects after the module engineering process using contamination correction (i.e., Mura correction). In other words, it is impossible to predict whether the contamination correction technology in the module engineering stage can bring the display panels with Mura defects to a good product state. Therefore, all display panels with Mura defects need to be sent to the packaging equipment for packaging as if they can be made into good products. Then, the packaged display panels undergo module engineering (or module process). During the module engineering of the display panels that have passed the cell process, components such as polarizing plates and COFs are assembled on the display panels.

[0025] After assembly, display panels with Mura defects undergo a Demura process to repair them. For example, for areas with uneven brightness caused by electrical characteristic defects, different driving voltages are applied to adjust the brightness. Only after the display panels with Mura defects complete the Demura process in the module engineering can they be determined as good products. Defective products that cannot be repaired are scrapped, resulting in waste of components such as module polarizers and COFs, thus wasting resources.

[0026] For example, such as Figure 1 As shown, automatic image detection is performed on the illumination images of N display panels to determine whether each display panel has defects. Display panels with Mura defects are directly sent to the packaging equipment as good products for subsequent processes such as packaging and module engineering. Display panels with other defects (such as dot defects, line defects, etc.) are directly treated as non-good products and do not require further processing.

[0027] Therefore, to address the aforementioned issues, this application provides a false defect differentiation scheme. Based on AI technology, it detects whether a display panel has Mura defects and predicts the result of Mura correction after the detected Mura defects are corrected during the module engineering stage. This determines whether the stain correction can make the display panel with Mura defects a good product, thereby scrapping the display panels that cannot be made good before module engineering, avoiding unnecessary processes and reducing resource waste.

[0028] The following section will describe in detail the false defect differentiation scheme provided in this application, using the panel processing system as an example. Figure 2 As shown, the panel processing system includes a camera, a processing unit, a judgment unit, and a packaging device.

[0029] A camera is used to capture images of the display panel during the cell assembly process to obtain an image of the display panel being illuminated, and to send the image of the display panel being illuminated to a processing device. The processing unit performs defect detection on the illuminated image, obtains the defect detection result corresponding to the display panel, and sends the defect detection result to the judgment unit. The defect detection result indicates whether the display panel has defects, including uneven display (Mura) defects.

[0030] The processing device is also used to perform defect correction prediction on the lamp image, obtain the defect correction prediction result corresponding to the display panel, and send the defect correction prediction result corresponding to the display panel to the judgment device; wherein, the defect correction prediction result indicates whether the display panel with Mura defects can be successfully corrected for smudges during the module engineering stage.

[0031] The judgment device is used to obtain the good product judgment result of the display panel based on the defect detection result and defect correction prediction result of the display panel, and send the good product judgment result of the display panel to the packaging equipment; wherein, the good product judgment result indicates whether the display panel is a good product.

[0032] Packaging equipment is used to determine whether to package the display panel based on the good product judgment result corresponding to the display panel.

[0033] Optionally, when a defect exists in the display panel, the defect detection result corresponding to the display panel indicates the type of defect in the display panel.

[0034] In this embodiment, before the display panel undergoes packaging and module engineering, the processing device performs defect detection on the LED image of the display panel to determine whether the display panel has defects such as Mura. When a defect exists in the display panel, the processing device can also perform defect correction prediction on the LED image of the display panel to determine whether the display panel with Mura defects can be successfully corrected during the module engineering stage, that is, to determine whether the display panel with Mura defects can be made into a good product. In other words, Mura defects that can be made into good products are false defects, thereby achieving the differentiation of false Mura defects.

[0035] Then, the judgment device can use the defect detection results and defect correction prediction results corresponding to the display panel to obtain the good product judgment result corresponding to the display panel, thereby realizing the prediction of the good product status of the display panel.

[0036] If the product acceptance result for the display panel indicates that the display panel is defective, the packaging equipment does not need to package the display panel. The display panel will not undergo module engineering or other processes and will instead be scrapped.

[0037] If the product quality assessment result for the display panel indicates that the display panel is a good product, the packaging equipment does not need to package the display panel. After packaging, the display panel can continue with module engineering and stain correction.

[0038] Alternatively, the aforementioned processing device may be a server, such as an AI server.

[0039] Optionally, the aforementioned determination device may be a data matching and distribution system.

[0040] Optionally, the aforementioned processing device and determining device may be the same device or different devices, and this application does not limit them.

[0041] In some embodiments, the processing apparatus is specifically used to: predict defects in the illumination image based on a target AI model. The target AI model is used to predict whether Mura defects can be successfully corrected, that is, to predict whether a display panel with Mura defects can be made into a good product after the defects are corrected. Specifically, the processing apparatus inputs the illumination image of the display panel into the target AI model, the target AI model performs defect correction prediction on the illumination image of the display panel, and obtains and outputs the corresponding defect correction prediction result for the display panel. Based on this, the accuracy of the defect correction prediction is ensured.

[0042] The aforementioned target AI model was trained using a training set. The training set included images of Mura defective display panels (e.g., those with successfully repaired blemishes) Figure 3 As shown in the image, the Mura defect in the display panel corresponding to the image on the display panel can be successfully repaired.

[0043] In addition, the training set also includes images of display panels with poor Mura quality where stain correction failed (e.g., Figure 4 As shown in the image, the Mura defect on the display panel corresponding to this image cannot be successfully repaired. It is understandable that by comparing... Figure 3 The image shown is of a Mura display panel with successfully repaired stains. Figure 4 As can be seen from the display panel images of Mura defects with failed smudge correction shown, the differences between the two images are small, and there are many types of Mura defects. Therefore, the training set includes a large number of display panel images of Mura defects with failed smudge correction and display panel images of Mura defects with successful smudge correction to ensure the accuracy of defect correction prediction of the trained target AI model.

[0044] Optionally, the aforementioned display panel images (such as the display panel image with successfully corrected Mura defects and the display panel image with unsuccessfully corrected Mura defects) are also labeled with defect types, i.e., defect data. Defect types include Mura defects. Additionally, defect types may include other defects, such as dot defects and line defects. Therefore, the target AI model can also detect defects in the lighting image. Accordingly, the processing device is specifically used to: perform defect detection on the lighting image based on the target AI model. Specifically, the processing device inputs the lighting image of the display panel into the target AI model, which performs defect detection and defect correction prediction on the lighting image of the display panel, obtaining and outputting the corresponding defect detection results and defect correction prediction results for the display panel. In this way, the processing device can not only use the target AI model for defect detection but also for defect correction prediction, improving the efficiency of defect detection and defect correction prediction while ensuring accuracy.

[0045] Alternatively, the processing device can also employ other methods to perform defect detection on the lighting images, such as using traditional image detection algorithms. Furthermore, the processing device can utilize both traditional image detection algorithms and a target AI model to perform defect detection on the lighting images.

[0046] Traditional image detection algorithms can detect muraking defects and other defects on display panels. However, these algorithms have limitations. While APIs can accurately detect muraking defects with fixed shapes, they cannot accurately detect muraking defects with irregular shapes, leading to missed detections. Therefore, a combination of traditional image detection algorithms and a target AI model can be used for defect detection.

[0047] For example, the processing device can first use a conventional image detection algorithm to perform defect detection on the lamp image corresponding to the display panel. If it is determined that there are other defects in the display panel, the defect detection result corresponding to the display panel can be directly determined to indicate that the display panel has defects other than Mura defects.

[0048] When it is determined that the display panel only has a Mura defect, the corresponding defect detection result of the display panel can be directly determined to indicate that the display panel has a Mura defect.

[0049] If it is determined that there are no defects in the display panel, in order to avoid missing defects in Mura, the target AI model can be used to perform defect detection on the LED image of the display panel to obtain the corresponding defect detection results of the display panel.

[0050] In some embodiments, it can be determined whether the display panel can be predicted to be of good quality based on the defects present in the display panel. If the defect detection result for the display panel indicates that only Mura defects exist, it indicates that the display panel may be of good quality, and the processing device performs defect correction prediction on the lamp image corresponding to the display panel.

[0051] If the defect detection result for the display panel indicates a defect other than a Mura defect, it means that the display panel has other defects such as dot defects or line defects. In other words, the display panel is not a good product. Therefore, the processing device does not perform defect correction prediction on the lamp image corresponding to the display panel, thereby avoiding further unnecessary defect correction prediction.

[0052] In some embodiments, the determination device can determine whether to use the corresponding defect detection results and defect correction prediction results or only the corresponding defect detection results to accurately predict whether the display panel is a good product, based on the defects present in the display panel. If the corresponding defect detection results indicate only Mura defects, the determination device obtains a good product determination result for the display panel based on the corresponding defect detection results and defect correction prediction results. If the defect detection result for the display panel indicates a defect other than a Mura defect (i.e., the display panel has a non-Mura defect), the judgment device determines the good product status of the display panel based on the defect detection result. This allows for accurate determination of whether the display panel can be considered a good product.

[0053] Optionally, as shown in Table 1, if the defect detection result corresponding to the display panel indicates that there is only a Mura defect (i.e., OK), and the defect correction prediction result indicates that the stain correction is successful (i.e., OK), the good product judgment result corresponding to the display panel indicates that the display panel is a good product (i.e., OK).

[0054] If the defect detection result for the display panel indicates only a Mura defect, and the defect correction prediction result indicates that the stain correction has failed, the good product judgment result for the display panel indicates that the display panel is not a good product (i.e., NG).

[0055] If the defect detection result corresponding to the display panel indicates that there is a defect other than the Mura defect (i.e., NG), the good product judgment result corresponding to the display panel indicates that the display panel is not a good product.

[0056] Optionally, as shown in Table 1 above, the above-mentioned good product determination results may also include defects present in the display panel.

[0057] Table 1

[0058] It should be noted that when the defect detection result of the display panel indicates that there is no defect in the display panel, the judgment device can directly determine that the good product judgment result of the display panel indicates that the display panel is a good product.

[0059] In some embodiments, after determining the good product judgment result corresponding to the display panel, the judging device can directly send the good product judgment result to the packaging device. Alternatively, when the display panel arrives at the packaging device, the packaging device sends a result retrieval request to the judging device. After receiving the result retrieval request, the judging device, in response to the request, sends the good product judgment result corresponding to the display panel to the packaging device, avoiding the unnecessary issuance of good product judgment results.

[0060] To achieve the differentiation of correctable false Mura defects, this embodiment also provides a method for distinguishing false defects performed by the aforementioned determination device, such as... Figure 5 As shown, the method includes S501-S503.

[0061] S501. Obtain the defect detection results corresponding to the display panel that has undergone the cell process.

[0062] The defect detection results indicate whether the display panel has defects, including Mura defects. These results are obtained by detecting defects through illumination images captured during the illumination test corresponding to the cell process of the display panel.

[0063] S502. Obtain the defect correction prediction results corresponding to the display panel.

[0064] Among them, the defect correction prediction results indicate whether the display panel with Mura defects can be successfully corrected for smudges during the module engineering stage.

[0065] S503. Based on the defect detection results and defect correction prediction results corresponding to the display panel, obtain the good product judgment result corresponding to the display panel.

[0066] The product quality assessment result indicator panel shows whether the product is a good product.

[0067] Optionally, based on the defect detection results and defect correction prediction results corresponding to the display panel, a good product determination result for the display panel is obtained, including: If the defect detection result for the display panel indicates only a Mura defect, the good product determination result for the display panel is obtained based on the defect detection result and defect correction prediction result for the display panel.

[0068] The implementation process of S501-S503 can be found in the previous text, and will not be repeated here.

[0069] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be performed by instructions, or by instructions controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor (such as the timing controller described above).

[0070] Therefore, embodiments of this application provide a computer-readable storage medium storing a computer program thereon, which is loaded by a processor to execute the steps described in the above-described method embodiments of this application. For example, the computer program loaded by the processor can execute the false defect differentiation method as described above.

[0071] For details on the implementation of each of the above operations / steps, please refer to the previous examples, which will not be repeated here.

[0072] The computer-readable storage medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0073] Since the computer program stored in the computer-readable storage medium can execute the steps in any of the above method embodiments provided in the embodiments of this application, the beneficial effects that the methods described in any of the above method embodiments can achieve can be realized, as detailed in the preceding embodiments, and will not be repeated here.

[0074] This application also provides a chip, including a memory storing multiple instructions; a processor loads instructions from the memory to execute the steps in any of the false defect differentiation methods provided in this application.

[0075] This application also provides a computer program product or computer program that includes computer instructions stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the electronic device to perform the methods provided in the various optional implementations of the above embodiments.

[0076] Alternatively, the aforementioned electronic device may also be referred to as a determination device.

[0077] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more features. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0078] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0079] The embodiments, implementation methods, and related technical features of this application can be combined and substituted for each other without conflict.

[0080] The above are merely preferred embodiments of this application and are not intended to limit this application in any way. Any simple modifications, equivalent changes, and alterations made to the above embodiments based on the technical essence of this application without departing from the scope of the technical solution of this application shall still fall within the scope of the technical solution of this application.

Claims

1. A panel processing system, characterized in that, The system includes a camera, a processing device, a judgment device, and a packaging device; The camera is used to capture images of the display panel during the cell assembly process, to obtain an image of the display panel under illumination, and to send the image of the display panel under illumination to the processing device. The processing device is used to perform defect detection on the lamp image, obtain a defect detection result corresponding to the display panel, and send the defect detection result corresponding to the display panel to the judgment device; wherein, the defect detection result indicates whether there is a defect in the display panel, and the defect includes uneven display Mura defect; The system performs defect correction prediction on the illumination image to obtain a defect correction prediction result corresponding to the display panel, and sends the defect correction prediction result corresponding to the display panel to the determination device; wherein, the defect correction prediction result indicates whether the display panel with Mura defects can be successfully corrected for smudges during the module engineering stage; The judging device is used to obtain a good product judgment result for the display panel based on the defect detection result and defect correction prediction result corresponding to the display panel, and send the good product judgment result for the display panel to the packaging equipment; wherein, the good product judgment result indicates whether the display panel is a good product; The packaging equipment is used to determine whether to package the display panel based on the good product judgment result corresponding to the display panel.

2. The system according to claim 1, characterized in that, The processing device is specifically used for: The target AI model is used to predict whether the Mura defects can be successfully corrected. The target AI model is trained on a training set, which includes display panel images of Mura defects that have been successfully corrected and display panel images of Mura defects that have not been corrected.

3. The system according to claim 2, characterized in that, The display panel image is also labeled with the defect type, and the processing device is specifically used for: Based on the target AI model, defect detection is performed on the lighting image.

4. The system according to any one of claims 1 to 3, characterized in that, The processing device is specifically used for: If the defect detection result corresponding to the display panel indicates that only Mura defects exist, defect correction prediction is performed on the lamp image corresponding to the display panel. If the defect detection result corresponding to the display panel indicates the presence of defects other than the Mura defect, no defect correction prediction will be performed on the lamp image corresponding to the display panel.

5. The system according to claim 4, characterized in that, The determining device is specifically used for: If the defect detection result corresponding to the display panel indicates that only Mura defects exist, the good product determination result corresponding to the display panel is obtained based on the defect detection result and defect correction prediction result corresponding to the display panel. If the defect detection result corresponding to the display panel indicates the presence of defects other than the Mura defect, a good product determination result corresponding to the display panel is obtained based on the defect detection result corresponding to the display panel.

6. The system according to claim 5, characterized in that, If the defect detection result corresponding to the display panel indicates that only Mura defects exist, and the defect correction prediction result indicates that the stain correction is successful, the good product judgment result corresponding to the display panel indicates that the display panel is a good product; If the defect detection result corresponding to the display panel indicates that only Mura defects exist, and the defect correction prediction result indicates that stain correction has failed, the good product judgment result corresponding to the display panel indicates that the display panel is not a good product. If the defect detection result corresponding to the display panel indicates the presence of defects other than the Mura defect, the good product determination result corresponding to the display panel indicates that the display panel is not a good product.

7. The system according to any one of claims 1 to 3, characterized in that, The packaging device is specifically used to send a result acquisition request to the determination device when the display panel arrives; The determination device is specifically used to respond to the result acquisition request by sending the good product determination result corresponding to the display panel to the packaging device.

8. A method for distinguishing false defects, characterized in that, A determination device applied to a panel processing system as described in any one of claims 1 to 7; the method includes: Obtain the defect detection result corresponding to the display panel that has undergone the cell process; wherein, the defect detection result indicates whether the display panel has defects, and the defects include Mura defects; the defect detection result is obtained by detecting defects through the lamp images taken during the lamp testing corresponding to the cell process of the display panel; Obtain the defect correction prediction result corresponding to the display panel; wherein, the defect correction prediction result indicates whether the display panel with Mura defects can be successfully corrected for smudges during the module engineering stage; Based on the defect detection results and defect correction prediction results corresponding to the display panel, the good product determination result corresponding to the display panel is obtained; wherein, the good product determination result indicates whether the display panel is a good product.

9. The method according to claim 8, characterized in that, The process of obtaining a good product determination result for the display panel based on the defect detection results and defect correction prediction results corresponding to the display panel includes: If the defect detection result corresponding to the display panel indicates that only Mura defects exist, the good product determination result corresponding to the display panel is obtained based on the defect detection result and defect correction prediction result corresponding to the display panel.

10. A computer-readable storage medium, characterized in that, It stores a computer program or instructions that, when executed by a processor, implement the steps in the false defect differentiation method as described in claim 8 or 9.

Images