Panel defect identification method and system, electronic equipment and storage medium

Abstract

The invention provides a panel defect identification method and system, electronic equipment and a storage medium. The method comprises the following steps: acquiring a first panel image corresponding to a display panel; performing defect identification on the first panel image to obtain first defect information of the display panel; and performing defect identification on a second panel image according to the first defect information to obtain second defect information of the display panel. According to the invention, the panel defect can be accurately identified, so that the panel defect repairing precision is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of display panels, and particularly to a method, a system, an electronic device and a computer-readable storage medium for identifying panel defects. Background Art

[0002] Limited by processes and technologies, various defects often exist in the production of semiconductor display panels, and these defects may affect the quality and functions of the final products. Therefore, after each production process of the display panel, a detection device is used to detect the panel, and then the panel with defects is sent to a repair station for defect repair to avoid irreversible effects of the defects on subsequent processes or the final products.

[0003] Currently, panel repair in the industry still mainly relies on manual operations, and relies heavily on manpower during the production process. However, due to the increasingly complex product structure and diverse repair methods, the repair accuracy of the panel is extremely low. Summary of the Invention

[0004] Embodiments of the present invention provide a method and a system for identifying panel defects, aiming to achieve automatic repair of panel defects and thereby improve the accuracy of panel defect identification.

[0005] In a first aspect, embodiments of the present invention provide a method for identifying panel defects, including:

[0006] Obtaining a first panel image corresponding to a display panel;

[0007] Performing defect identification on the first panel image to obtain first defect information of the display panel;

[0008] Performing defect identification on a second panel image according to the first defect information to obtain second defect information of the display panel.

[0009] In a second aspect, embodiments of the present invention provide a system for identifying panel defects, the system including:

[0010] An obtaining module, configured to obtain a first panel image corresponding to a display panel;

[0011] A first identification module, configured to perform defect identification on the first panel image to obtain first defect information of the display panel;

[0012] A second identification module, configured to perform defect identification on a second panel image according to the first defect information to obtain second defect information of the display panel.

[0013] In a third aspect, an embodiment of the present invention provides an electronic device, including a processor and a memory, where the memory stores multiple instructions; the processor loads the instructions from the memory to execute the steps of the above panel defect recognition method.

[0014] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, including a processor and a memory, where the memory stores multiple instructions; the processor loads the instructions from the memory to execute the steps of the above panel defect recognition method.

[0015] Beneficial effects of the embodiments of the present invention:

[0016] Compared with the prior art's panel repair method that relies on manual labor, in the present disclosure, the first panel image of the display panel can be first subjected to defect recognition, and then, based on the defect information in the first panel image, the second panel image can be subjected to defect recognition according to the above defect information to obtain the defect information of the display panel. It can be seen that through two panel image acquisitions and corresponding defect recognition operations, the present disclosure can achieve in-depth recognition of display panel defects, greatly improving the accuracy of panel defect recognition. On this basis, the present disclosure can perform defect repair according to the recognized defect information, thereby being able to ensure the quality of the display panel. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention, and those skilled in the art can obtain other drawings without creative efforts based on these drawings.

[0018] Figure 1 is the first flow diagram provided in the embodiments of the present disclosure;

[0019] Figure 2 is the second flow diagram provided in the embodiments of the present disclosure;

[0020] Figure 3 is the third flow diagram provided in the embodiments of the present disclosure;

[0021] Figure 4 is the fourth flow diagram provided in the embodiments of the present disclosure;

[0022] Figure 5 is the structural diagram of the panel defect recognition system provided in the embodiments of the present disclosure;

[0023] Figure 6 is the structural diagram of the electronic device provided in the embodiments of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present invention. In addition, it should be understood that the specific embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention. In the present invention, unless otherwise stated, the orientation terms such as "upper" and "lower" usually refer to the upper and lower in the actual use or working state of the system, specifically the drawing direction in the accompanying drawings; while "inner" and "outer" refer to the outline of the system. At the same time, in the description of the embodiments of the present disclosure, the terms "first", "second", etc. are only used for distinguishing descriptions, and cannot be understood as indicating or implying relative importance. Thus, the features defined with "first", "second" may explicitly or implicitly include one or more features. In the description of the embodiments of the present disclosure, "a plurality of" means two or more, unless otherwise specifically defined.

[0025] According to the above description of the background art of the present disclosure, at present, the repair of the display array of semiconductor display panels in the industry still mainly relies on manual operations, and more manpower is relied on during the production process. Due to the increasingly complex product structure and diverse repair methods, the difficulties of personnel operation and the learning cost have increased.

[0026] In order to solve the above problems, realize the automatic repair of semiconductor display panels, improve the repair accuracy, and at the same time improve the repair efficiency, the present disclosure proposes a method, system, electronic device, and computer-readable storage medium for repairing defects of semiconductor display panels. The deep learning algorithm is used to identify and analyze the defect morphology, category, and the degree of influence of the defect on the core components of the panel for the collected defect images, and then the best repair plan is given in combination with the business repair method. The control software of the repair machine is automatically operated to replace manual operations of various functions of the software to complete the repair of the defects.

[0027] The panel repair method in the present disclosure is applied to a terminal device, which includes a client and a server.

[0028] Among them, as Figure 2 shown, each client (i.e., Figure 2 the client in Figure 2The operation commands sent by the server in it are used to simulate manual operation. The device control software controls the repair device to perform defect repair actions, and sends the defect images captured by the operating machine to the server. The server is mainly responsible for defect recognition of the defect images sent by the client and formulating repair strategies, parsing the repair strategies into the operation sequences of the operating machine, and then sending the operation sequences to the operating machine. The device control software controls the repair device to perform repair actions.

[0029] The above server side is used for defect detection and repair strategy generation. The server in this disclosure can be a GPU server cluster, and the cluster is managed using K8S and docker. The panel detection method in this disclosure can be deployed as microservices in the above cluster. A separate image is started on the server for each operating machine to execute the panel defect recognition method, and different repair processes are set for each operating machine. Instructions are sent to the operating machine according to the process to execute or algorithms are called for defect detection and generation of repair solutions.

[0030] The device control software on the client side is a lightweight software system that simulates manual operation of the mouse and keyboard to complete the control of the device control software, including functions such as mouse movement, mouse click, keyboard key press, software interface recognition, button area recognition, text recognition, operation feedback, and pop-up recognition. This software is a passive execution software that receives execution instructions sent by the server of the server side, then executes the corresponding instruction operations, checks whether the execution is successful, and feedbacks the execution results and check information.

[0031] In this disclosure, due to the large differences in the machine control software of different manufacturers, the software control system needs to quickly identify and adapt to different machine control software. Therefore, this disclosure can set a multi-layer tree-like structure key function list, which includes the positions, function descriptions, operation actions, operation feedbacks, and interface jump pointers of each function area in the software interface. After receiving the corresponding instructions, the device control software controls the mouse or keyboard to complete the corresponding execution operations according to the function list, and calls the corresponding operation feedback algorithm to check whether the operation is executed successfully. Therefore, the device control software on the client side can include five modules: operation execution / feedback module, function list production and parsing module, image detection operator module, operator execution control flow module, and data network communication module.

[0032] Specifically, for example, the operation execution / feedback module includes functional modules for mouse movement and click, and simulating keyboard key presses. Generally, after a software operation, there will be specific feedback on the corresponding software interface to confirm whether the operation is successful. For example, changes in button color and status, changes in coordinate information recording the camera position, movement of the preview image, etc. Therefore, multiple feedback algorithms are defined, such as image comparison, highlight recognition, template matching, character recognition, etc. When the user makes a function list of the buttons, they need to formulate a method for checking the operation feedback.

[0033] The function list creation and parsing module provides an interactive interface that allows users to conveniently create a tool for the function list of the software interface buttons. The user only needs to draw the position interval of the button or function area on the software interface, and the tool will automatically record the area information. Then, the user inputs the purpose of the area, the operations and call instructions to be executed, such as mouse click, keyboard press, text information extraction, and the jump page after clicking, etc., and configures the corresponding operation feedback check algorithm to complete the production of the button or function. By this method, after defining each area, button, corresponding jump page, and pop-up window of the software, the software records the information, operations, page jump relationships, and the method for checking whether the operations are successful of each button or area in a tree-like structure list. The function list parsing module parses the keywords or instructions input by the user, matches the call instructions specified when the user creates the list, obtains the corresponding function interval, corresponding operation execution method in the data list, and then calls the corresponding operation instruction to execute the operation (for example, mouse click, key press, or call the ocr module for text recognition, etc.). Finally, it also needs to call the corresponding check algorithm according to the defined operation check method to check whether the operation is correctly executed.

[0034] The image detection operator module contains a large number of functional modules for image processing and deep learning. The software provides a visual operation interface for model training and publishing. Users can use this page for rapid model training and test evaluation. The trained model can be directly published to the operator library, and the operator library also includes common functional modules for image processing. Other modules can complete the processing of image data by enabling different networks or traditional image operators through network requests and return the processing results.

[0035] The operator execution control flow module is a software operation process defined by users according to business rules. For example, defect inspection includes a complete process such as obtaining a defect list, moving the camera to the defect location according to the defect location information, taking a picture with the camera, defect detection, intersection broken line analysis, querying repair methods, and performing repair actions. The control flow needs to determine the next step or the operator to be called based on the feedback information of each operator execution. Each operator contains multiple software execution actions. For example, moving the camera to the defect location includes the control software sending camera movement instructions and coordinate information to the client software. After receiving the information, the client software controls the mouse to move to the defect list area, clicks the mouse within the area, and repeatedly calls the click operation feedback check algorithm of this module until the click action is completed. The client software sends the click feedback information to the control flow module through the network. The control flow module performs the operations of the next step according to the feedback information. Others, such as performing repair actions, contain more complex sub-module structures and call more basic communication and execution operators.

[0036] The data network communication module provides different network communication protocols and performs unified structural encapsulation. The upper-layer software control flow module does not need to concern itself with the underlying technical implementation. The communication module provides a unified call module externally. For different platforms and network environments, only the implementation details of the underlying network communication module need to be switched, and no modification is required for other modules of the software.

[0037] The above modules are independent of each other and constitute a device control software with high flexibility and high scalability. Among them, the operation execution / feedback operator module is a basic operator library, which contains a large number of basic function modules for general mouse, keyboard, screen capture, text recognition, and image processing. These modules are independent of the specific software interface and are only related to the operating system. They also provide a unified call method externally, shielding the differences between different operating systems. The function list production and parsing module provides a function for software interface recognition and parsing. It parses and defines different software manually and automatically, parses and arranges the sent request instructions, and then calls the interface of the basic operator library to execute the corresponding operations and perform checks. This module is independent of the specific operating system and hardware environment and is only related to the software interface of the device. The list operator execution control flow module is a specific inspection and repair process defined by users, which is strongly related to business rules but independent of the specific operating software and running hardware environment. The above three modules realize the communication and call of different modules through network communication. Considering the relatively low computing power of the client software, the operation execution / feedback module can be placed on the client for efficient and fast execution, while the function list production and parsing module, the list operator execution control flow, and the specific image detection operator module can be placed on the GPU cluster of the server. Different modules exchange data through network communication to ensure the independence of each module.

[0038] For different device control software, the hardware environment or business rules only need to adapt to and switch the corresponding modules to achieve the pluggability, high availability, and flexible and rapid expansion of the overall software.

[0039] Based on the above device control software, the panel defect recognition method in the present disclosure may specifically include the following steps:

[0040] Step S10: Obtain a first panel image corresponding to the display panel;

[0041] Step S20: Perform defect recognition on the first panel image to obtain first defect information of the display panel;

[0042] It should be noted that in this embodiment, the operating machine of the client can use its acquisition device, such as a camera, to acquire a panel image of the display panel to be repaired (i.e., the first panel image in this embodiment), and the client can send the first panel image to the server.

[0043] The server can obtain the first panel image sent by the client, perform defect recognition on the first panel image to obtain first defect information of the display panel of the first panel image. Among them, the first defect information can be stored in the database of the server. The first defect information can be a defect list, and the defect list at least includes the position information of each panel defect in the display panel to be repaired.

[0044] It can be understood that generally, there are often multiple defects to be repaired on the display panel. Therefore, the server can obtain the position information corresponding to the panel defect one by one, repair the panel defect according to the position information, and then obtain the position information of the next panel defect after the repair is completed.

[0045] In addition, the server can also obtain the position information of all panel defects at the same time and perform repairs one by one.

[0046] Step S30: Perform defect recognition on a second panel image according to the first defect information to obtain second defect information of the display panel.

[0047] After the server obtains the first defect information of the panel to be repaired, it can control the acquisition device of the operating machine to acquire a second panel image according to the first defect information.

[0048] It should be noted that the first panel image in this embodiment is actually a complete image of the display panel to be displayed, while the second panel image is actually a defect local high-definition image of the panel defect for defect detection, recognition, and repair, etc.

[0049] Specifically, for example, the server can obtain the defect position of the panel defect in the above first defect information, and then control the operating machine to move to the above defect position to collect a high-definition second panel image of the panel defect.

[0050] After the operating machine collects the second panel image of the panel defect at the above defect position, it can send the second panel image to the server.

[0051] Furthermore, after the server obtains the second panel image sent by the client, it can perform defect recognition on the second panel image according to the defect position and obtain second defect information, where the second defect information at least includes the target panel defect information and the defect type of the target panel defect in the target panel defect information.

[0052] It should be noted that in this embodiment, the display panel includes multiple functional regions, such as, the display array circuit region (Active area), the fanout peripheral package fanout circuit region, the GOA region (Gate on array array gate drive circuit), etc. For different panel defect regions, the present disclosure can adopt corresponding defect detection and recognition algorithms. Therefore, the server can call the corresponding defect detection and recognition algorithm according to the defect position in the second panel image to perform defect recognition and obtain the second defect information.

[0053] In addition, in this embodiment, whether a panel defect needs to be repaired can depend on whether the defect affects the electrical properties of the circuit device. For example, whether the defect will cause a short circuit or an open circuit, etc. If the defect causes a short circuit or an open circuit, the defect needs to be repaired. Therefore, this embodiment can classify the defect types of panel defects according to whether the panel defect affects the electrical properties, such as, the circuit electrical property defect type (this type of panel defect causes a short circuit or an open circuit in the circuit, etc.) and other circuit electrical property defect types (although this type of panel defect has a short circuit or open circuit relationship with the circuit device in terms of position, it will not cause a short circuit or an open circuit in the circuit).

[0054] For example, even if some of the defects caused are in a short - circuit or open - circuit relationship with the circuit devices in terms of location, the causes of the defects do not affect the actual electrical characteristics of the circuit (that is, although there is a short - circuit or open - circuit in location, it does not actually cause the circuit devices to short - circuit or open - circuit). Such defects usually do not need to be repaired. For example, surface residues, chemical solution residues, water stains, etc. on the display panel will be cleaned during the subsequent cleaning process, so generally these defects do not need to be repaired either. However, some of the defects caused are in a short - circuit or open - circuit relationship with the circuit devices in terms of location and will affect the actual electrical characteristics of the circuit. For example, panel defects such as foreign objects on the panel surface, metal residues, scratches, protective film breakdown, peeling, etc. usually affect the circuit characteristics. Such panel defects that affect the circuit characteristics need to be repaired.

[0055] On this basis, the server can repair the target panel defect according to the defect type of the target panel defect.

[0056] For example, when it is recognized that the defect type of the target panel defect is a circuit electrical defect type, it means that this type of panel defect will cause the circuit device to short - circuit or open - circuit, and the repair device can be controlled to repair the target panel defect. And the device control software of the client can control the repair device to perform the corresponding defect repair operation.

[0057] Therefore, in this embodiment, the server can obtain the first panel image sent by the client, and then can obtain the first defect information corresponding to the first panel image. Furthermore, the server can obtain the defect location of the panel defect in the above - mentioned first defect information, and then control the operating machine to move to the above - mentioned defect location to collect a high - definition second panel image of the panel defect. After the server obtains the second panel image sent by the client, it can identify the defects of the second panel image according to the panel defect area of the second panel image and obtain the second defect information. When the server recognizes that the defect type of the target panel defect is a circuit electrical defect type, it can control the operating machine to repair the target panel defect.

[0058] Compared with the manual panel repair method in the prior art, in the present disclosure, after obtaining the panel image of the display panel to be repaired, the panel defect image of the panel defect can be obtained according to the position information of the panel defect in the panel image, and the panel defect can be defect-identified according to the panel defect image. When the defect type is a circuit electrical defect type, the control operation machine is used to repair the defect. Therefore, in the present disclosure, on the one hand, the panel defect can be automatically repaired, improving the panel repair efficiency and reducing the manual panel quality inspection cost; on the other hand, the present disclosure can determine whether to repair the defect according to the defect type, and only repair the defect when the defect type is a circuit electrical defect type, and does not repair the defect that does not affect the circuit electricity, which can not only ensure the quality of the display panel, but also greatly improve the panel repair efficiency.

[0059] In one embodiment, in the above step S30, "defect-identifying the second panel image according to the first defect information to obtain the second defect information of the display panel" may include:

[0060] Step S301, defect-segmenting the second panel image according to the first defect information to obtain the target panel defect information in the second panel image;

[0061] Step S302, panel-segmenting the second panel image according to the defect region corresponding to the target panel defect information to obtain the first characteristic information corresponding to the target panel defect information;

[0062] Step S303, defect-identifying the second panel image according to the first characteristic information to obtain the second defect information of the display panel.

[0063] In this embodiment, after the server obtains the second panel image collected by the client acquisition device, the second panel image can be defect-segmented to obtain the target panel defect information in the second panel image and the defect region of the target panel defect in the target panel defect information.

[0064] Specifically, for example, the server can perform pixel-level defect segmentation through a deep learning segmentation network according to the defect position of the panel defect in the second panel image.

[0065] Furthermore, the server can also perform circuit device segmentation on the above second panel image to obtain the circuit devices corresponding to the target panel defect in the panel defect region and the first characteristic information of the circuit devices.

[0066] It should be noted that, in this embodiment, the above circuit device is a circuit device affected by the target panel defect (that is, there is a short - circuit or open - circuit relationship between this circuit device and the target panel defect in terms of position), and the above first characteristic information specifically includes circuit short - circuit or circuit open - circuit.

[0067] Furthermore, the server can perform defect recognition on the second panel image according to the above first characteristic information to obtain the second defect information of the display panel.

[0068] The above step S303 may include:

[0069] Step S3031: Obtain the panel parameters corresponding to the target panel defect information in the second panel image;

[0070] Step S3032: Optimize the first characteristic information according to the panel parameters to obtain the second circuit characteristic information;

[0071] Step S3033: Obtain the second defect information of the display panel according to the second characteristic information.

[0072] The server can obtain the panel parameters of the above target panel defect. Among them, the panel parameter can specifically be the morphological parameter of the target panel defect, and optimize the first characteristic information according to this panel parameter. For example, update the first characteristic information of the circuit device to the second characteristic information. Furthermore, when the second characteristic information is circuit open - circuit or circuit short - circuit, determine that the defect type of the target panel defect is an electrical circuit defect.

[0073] It should be noted that, in this embodiment, different types of defects correspond to different physical causes. Common causes include residues, foreign objects, scratches, protective film breakdown, peeling, etc. The defects caused by these different causes falling in different circuit regions have different impacts on electrical characteristics. For example, functional circuits such as data circuits, Gate control circuits, and ITO conductive film electrodes.

[0074] According to the above embodiment description, for some defects in terms of cause, even if there is a short - circuit or open - circuit relationship with the circuit device in terms of position, the cause of the defect does not affect the true electrical characteristics of the circuit. Such defects often do not need to be repaired. For example, surface residues, chemical residues, water stains, etc. on the display panel will be cleaned during the subsequent cleaning process of the manufacturing process, so generally these defects often do not need to be repaired. And for some defects in terms of cause, there is a short - circuit or open - circuit relationship with the circuit device in terms of position, and they will affect the true electrical characteristics of the circuit. For example, foreign objects, metal residues, scratches, protective film breakdown, peeling, etc. on the panel surface usually affect the circuit characteristics. Such panel defects that affect the circuit characteristics need to be repaired.

[0075] Since defects caused by different reasons have very obvious differences in image morphology, therefore, the present disclosure can use a deep learning network to identify the morphological parameters of defects to distinguish whether the cause of the defect in the current morphology affects the circuit characteristics. Only the defects that affect the circuit electrical properties are repaired, and the defects that do not affect the circuit characteristics are directly ignored.

[0076] Specifically, for example, if the first circuit feature of the circuit device in the panel defect area of the second panel image is a circuit short circuit, and according to the morphological parameters of the target panel defect, it is determined that the cause of the target panel defect will not affect the circuit device from having a circuit short circuit, then the above first circuit feature can be updated to the second characteristic information (such as a circuit path). Since the second characteristic information is a circuit path at this time, it can be determined that the defect type of the target panel defect is a non-circuit electrical defect.

[0077] For another example, if it is determined according to the morphological parameters of the target panel defect that the cause of the target panel defect will affect the circuit device from having a circuit short circuit, for example, the cause of the target panel defect is due to metal residue in this area, and the above second characteristic information is a circuit short circuit. At this time, the first characteristic information can be updated to the second characteristic information, and since the second characteristic information is a circuit short circuit, it can be determined that the defect type of the target panel defect is a circuit electrical defect.

[0078] In the above step S302, "performing panel segmentation on the second panel image according to the defect area corresponding to the target panel defect information to obtain the first characteristic information corresponding to the target panel defect information" may include:

[0079] Step S3021, obtaining a mapped image of the standard panel image on the second panel image;

[0080] Step S3022, performing panel segmentation on the second panel image according to the mapped image to obtain the panel device information corresponding to the target panel defect information in the second panel image;

[0081] Step S3023, obtaining the first characteristic information corresponding to the panel device information according to the regional intersection of the defect area and the corresponding area in the preset standard panel image.

[0082] In this embodiment, the server can map a preset standard panel image to the second panel image to segment the second panel image and determine the circuit devices in the panel device information of the second panel image.

[0083] It should be noted that in this embodiment, due to the significant differences and uncertainties in the circuit traces and key components of different panel products, while the circuit traces and key components of the same product are fixed and periodic, the circuit and key components can be finely segmented using a template matching method. For example, a defect-free panel image can be used as a standard template in advance, and pixel-level annotations are made manually in the standard template to give the position areas and category information of different components. Then, it is expanded according to the period of the pattern to form a large template image containing multiple complete periods (i.e., the preset standard panel image in this embodiment), and the positions of different circuits and devices in this image template are known.

[0084] On this basis, the second panel image is subjected to template matching with the standard panel image. After the matching, an affine transformation relationship between the second panel image and the standard panel image is established, and based on this affine transformation relationship, the position information of the circuit devices manually marked in the standard panel image is mapped to the second panel image to obtain the circuit devices at the accurately segmented positions in the second panel image. Moreover, by analyzing the intersection and union of the defective area obtained by defect segmentation and the corresponding area of the standard panel image, the short-circuit and open-circuit relationships (i.e., the first characteristic information) between the target panel defect and the circuit devices in terms of position can be obtained.

[0085] Therefore, in this embodiment, after the panel defect in the panel image is recognized, the panel defect area can be segmented according to the standard panel image to obtain the circuit devices in the panel defect area and the impact of the panel defect on the circuit electrical properties of the circuit devices. When the panel defect affects the circuit electrical properties of the circuit devices, the panel defect is repaired, and when the panel defect does not affect the circuit electrical properties, it is not repaired. Therefore, the piecemeal repair of panel defects is avoided, which can not only improve the panel repair efficiency but also greatly enhance the panel repair quality.

[0086] In one embodiment, after the step S30, "According to the first characteristic information, perform defect recognition on the second panel image to obtain the second defect information of the display panel", it may include:

[0087] Step S40, obtain the target circuit device information corresponding to the target panel defect information;

[0088] Step S50, determine the defect repair information according to the target circuit device information and the defect repair database.

[0089] It should be noted that in this embodiment, according to the above description, different types of defects correspond to different physical causes. Therefore, in the defect repair scheme, defect repair information needs to be determined based on the cause of the defect (i.e., the defect type) and its impact on circuit characteristics. On this basis, a corresponding defect repair strategy can be formulated according to the defect repair information.

[0090] In this embodiment, when the server determines that the circuit electrical defect of the target panel defect is of the circuit electrical defect type, it can determine the target circuit device information corresponding to the target panel defect. Furthermore, the defect repair information corresponding to the target circuit device information can be obtained from the preset database of the server.

[0091] Furthermore, the server can obtain the corresponding defect repair strategy according to the defect repair information.

[0092] Specifically, for example, this embodiment usually adopts three repair strategies: long line, tangent, and grinding to repair defects. Generally, for large foreign objects that do not affect circuit characteristics, the foreign objects can be removed by grinding; for defects causing short circuits, they can be repaired by the tangent method; for open circuit defects in the core circuit, the disconnected circuit can be connected by a long line; for comprehensive defects, the current display pixel circuit can be damaged and isolated by the tangent method to make it a dark point that does not affect the normal pixels around, and then the repair machine can be controlled to perform corresponding repair operations in the corresponding circuit area.

[0093] Furthermore, the target repair strategy can be converted into an operation sequence that can be recognized by the operation machine.

[0094] The device control software of the client can receive the operation sequence and control the repair device to repair the target panel defect according to the device control software.

[0095] It should be noted that in this embodiment, there is a corresponding repair strategy for each circuit device. In this disclosure, the repair strategy can be summarized manually in advance and solidified into the database, and the device control software can call the corresponding repair strategy for the circuit device affected by the target panel defect.

[0096] In another embodiment, according to the above description, since the display panel to be repaired often has multiple defects to be repaired, the server can control the operation machine to check multiple defects one by one, including defect switching, defect list matching to confirm defect information, obtaining defect images (i.e., the second panel image), image clarity inspection, identifying the defect area of the panel defect, calling different region - corresponding defect detection and recognition algorithms for defect detection and recognition, and when the image is not clear, the camera can be moved in the area around the defect or different light sources or a higher - resolution camera can be switched for multi - dimensional confirmation, and the loop list is repeated until all defects are traversed.

[0097] Specifically, for example, as Figure 3 shown, if the server detects that the target panel defect in the second defect information does not include the target panel defect of the circuit electrical defect type, it means that the target panel defect actually does not affect the circuit characteristics. At this time, the second defect information can be ignored, and the camera of the operating machine can be controlled to move to another defect position in the first defect information, and a new second panel image can be collected at the other defect position.

[0098] Furthermore, the image clarity of the second panel image is detected. If the image clarity is greater than or equal to the preset clarity threshold, the new second panel image can be used for defect recognition and repair, etc.; otherwise, the operating machine can be controlled to switch to a new acquisition device and / or switch to a new supplementary light device until the image clarity of the newly collected second panel image is greater than the preset clarity threshold, and then defect recognition and repair, etc. can be performed.

[0099] In the above manner, this embodiment can traverse all the panel defects to be repaired in the defect list for repair.

[0100] Therefore, in this embodiment, when it is detected that the current panel defect does not need to be repaired, the acquisition device can be controlled to collect the panel defect image, and in order to ensure the image quality of the collected defect image, the camera or the light source can be switched to improve the image quality of the collected defect image. Furthermore, when using the image for defect recognition and repair, the defect recognition accuracy can be improved, and thus the defect repair efficiency can be improved.

[0101] In one embodiment, after the above step S50, "repair the target panel defect in the target panel defect information according to the target circuit device information and the defect repair database", the following steps may further be included:

[0102] S60, collect a third panel image of the repaired target panel defect;

[0103] S70, according to the pixel difference between the second panel image and the third panel image;

[0104] S80, if the pixel difference is less than the pixel threshold, collect a new second panel image according to the defect position in the first defect information.

[0105] In this embodiment, after the server repairs the target panel defect, it can obtain a third panel image of the repaired target panel defect.

[0106] Since there are no panel defects in the third panel image of the repaired target panel defects, the number of pixels in the third panel image is significantly less than that in the second panel image. Therefore, the server can calculate the pixel difference between the second panel image and the third panel image. If the pixel difference is less than the preset pixel threshold, it means that the repair of the target panel defects is completed. The server can cycle through other defect positions in the above first defect information, collect panel images at other defect positions, and perform defect identification and repair, etc.

[0107] If the pixel difference is greater than the pixel threshold, it means that the repair of the target panel defects is not successful, and the operating machine needs to be controlled again to repair the target panel defects until the defects are successfully repaired.

[0108] Further, in the above step S20, "performing defect identification on the first panel image to obtain the first defect information of the display panel" may include:

[0109] Step S201, obtaining the text information corresponding to the first panel image;

[0110] Step S202, obtaining the target identifier of the display panel according to the text information;

[0111] Step S203, obtaining the defect library corresponding to the target identifier according to the target identifier;

[0112] Step S204, determining the first defect information of the display panel according to the defect list.

[0113] It should be noted that in this embodiment, as Figure 4 shown, the client can control the display panel to be repaired to enter the operating machine. First, through align positioning, the position of the display panel is calibrated and aligned according to the mark points (mark points) of the display panel, and then the screen information of the device control software is intercepted to obtain the first panel image. Furthermore, the text information corresponding to the first panel image is obtained, and then the target identifier in the first panel image in the above text information is obtained by using the ocr (optical character recognition) method.

[0114] The server can use the target identifier to query the complete information of the current target identifier (such as panel process, test machine, defect detection site, etc.) and the defect library in the database.

[0115] When the defect library is specifically a defect list, the server can obtain the first defect information of the display panel in the defect list, and control the acquisition device of the client to collect a local image (i.e., the second panel image) of the high-definition panel defect at the defect position according to the defect position in the defect list.

[0116] Therefore, in this embodiment, the defect information of the display panel can be automatically obtained, the panel defects can be identified one by one according to the defect information, and the corresponding repair strategies in the database can be called for the circuit devices affected by the panel defects to repair the defects until the repair is successful, realizing automatic panel defect detection, identification and repair, without manual participation, reducing the labor cost, and improving the panel repair quality and repair efficiency at the same time.

[0117] This embodiment also provides a panel defect identification system, which can be specifically integrated in a terminal device. For example, as Figure 5 shown, the panel defect identification system may include:

[0118] An acquisition module 1001, configured to acquire a first panel image corresponding to the display panel;

[0119] A first identification module 1002, configured to perform defect identification on the first panel image to obtain first defect information of the display panel;

[0120] A second identification module 1003, configured to perform defect identification on a second panel image according to the first defect information to obtain second defect information of the display panel.

[0121] For the specific implementation of each of the above operations, reference may be made to the previous embodiments and will not be elaborated here.

[0122] Correspondingly, an embodiment of the present disclosure also provides an electronic device, which may be a terminal, and the terminal may be a smart phone, a tablet computer, a notebook computer, a touch screen, a game console, a personal computer (PC, Personal Computer), a personal digital assistant (Personal Digital Assistant, PDA), and other terminal devices. Alternatively, the electronic device may be a server.

[0123] As Figure 6 shown, Figure 6 is a schematic structural diagram of the electronic device provided by an embodiment of the present disclosure. The electronic device 1100 includes a processor 1101 with one or more processing cores, a memory 1102 with one or more computer-readable storage media, and a computer program stored on the memory 1102 and executable on the processor. Among them, the processor 1101 is electrically connected to the memory 1102. Those skilled in the art can understand that the structure of the electronic device shown in the figure does not constitute a limitation on the electronic device, and it may include more or fewer components than shown, or combine some components, or arrange different components.

[0124] The processor 1101 is the control center of the electronic device 1100, connecting various parts of the entire electronic device 1100 through various interfaces and circuits. By running or loading software programs and / or units stored in the memory 1102, and calling the data stored in the memory 1102, it executes various functions of the electronic device 1100 and processes data, thereby monitoring the entire electronic device 1100. The processor 1101 can be a central processing unit (CPU), a graphics processing unit (GPU), a network processor (NP), etc., and can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present disclosure.

[0125] In the embodiments of the present disclosure, the processor 1101 in the electronic device 1100 will load the instructions corresponding to the processes of one or more application programs into the memory 1102 according to the following steps, and the processor 1101 will run the application programs stored in the memory 1102 to implement various functions, such as:

[0126] Obtain a first panel image corresponding to the display panel, perform defect recognition on the first panel image to obtain first defect information of the display panel;

[0127] Obtain a first panel image corresponding to the display panel;

[0128] Perform defect recognition on the first panel image to obtain first defect information of the display panel;

[0129] According to the first defect information, perform defect recognition on a second panel image to obtain second defect information of the display panel.

[0130] For the specific implementation of each of the above operations, reference can be made to the previous embodiments, which will not be elaborated here.

[0131] Optionally, as Figure 6 shown, the electronic device 1100 further includes: a touch display screen 1103, a radio frequency circuit 1104, an audio circuit 1105, an input unit 1106, and a power supply 1107. Among them, the processor 1101 is electrically connected to the touch display screen 1103, the radio frequency circuit 1104, the audio circuit 1105, the input unit 1106, and the power supply 1107 respectively. Those skilled in the art can understand that Figure 6 the structure of the electronic device shown in

[0132] The touch display screen 1103 can be used to display a graphical user interface and receive operation instructions generated by a user acting on the graphical user interface. The touch display screen 1103 may include a display panel and a touch panel. Among them, the display panel can be used to display information input by the user or information provided to the user, as well as various graphical user interfaces of the electronic device. These graphical user interfaces can be composed of graphics, text, icons, videos, and any combination thereof. Optionally, the display panel can be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), etc. The touch panel can be used to collect touch operations of the user on or near it (such as operations of the user using a finger, a stylus, or any suitable object or accessory on or near the touch panel), and generate corresponding operation instructions, and the operation instructions execute the corresponding program. Optionally, the touch panel can include two parts: a touch detection system and a touch controller. Among them, the touch detection system detects the touch orientation of the user, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection system, converts it into contact coordinates, and then sends it to the processor 1101, and can receive and execute the commands sent by the processor 1101. The touch panel can cover the display panel. After the touch panel detects a touch operation on or near it, it is transmitted to the processor 1101 to determine the type of touch event. Subsequently, the processor 1101 provides a corresponding visual output on the display panel according to the type of touch event. In the embodiments of the present disclosure, the touch panel and the display panel can be integrated into the touch display screen 1103 to implement input and output functions. However, in some embodiments, the touch panel and the touch panel can be implemented as two independent components to implement input and output functions. That is, the touch display screen 1103 can also be used as part of the input unit 1106 to implement the input function.

[0133] The radio frequency circuit 1104 can be used to transmit and receive radio frequency signals to establish wireless communication with a network device or other electronic devices through wireless communication, and transmit and receive signals with the network device or other electronic devices.

[0134] The audio circuit 1105 can be used to provide an audio interface between the user and the electronic device through a speaker and a microphone. The audio circuit 1105 can transmit the electrical signal converted from the received audio data to the speaker, which converts it into a sound signal for output; on the other hand, the microphone converts the collected sound signal into an electrical signal, which is received by the audio circuit 1105 and then converted into audio data. After the audio data is output and processed by the processor 1101, it is sent through the radio frequency circuit 1104 to, for example, another electronic device, or the audio data is output to the memory 1102 for further processing. The audio circuit 1105 may also include an earphone jack to provide communication between the peripheral earphone and the electronic device.

[0135] The input unit 1106 can be used to receive input digital, character information or user characteristic information (such as fingerprint, iris, facial information, etc.), and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function controls.

[0136] The power supply 1107 is used to supply power to each component of the electronic device 1100. Optionally, the power supply 1107 can be logically connected to the processor 1101 through a power management system, so as to realize functions such as management of charging, discharging, and power consumption management through the power management system. The power supply 1107 may also include any components such as one or more DC or AC power supplies, a recharge system, a power failure detection circuit, a power converter or inverter, and a power status indicator.

[0137] Although Figure 6 not shown in the figure, the electronic device 1100 may also include a camera, a sensor, a Wi-Fi module, a Bluetooth module, etc., which will not be elaborated here.

[0138] In the above embodiments, the descriptions of the various embodiments have their own emphases. For parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0139] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructions, or by controlling relevant hardware through instructions. The instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0140] For this reason, the embodiments of the present disclosure provide a computer-readable storage medium, in which multiple computer programs are stored. The computer programs can be loaded by a processor to execute any one of the panel defect recognition methods provided by the embodiments of the present disclosure. The computer programs can execute the steps of the following panel defect recognition method:

[0141] Obtain a first panel image corresponding to the display panel;

[0142] Perform defect identification on the first panel image to obtain first defect information of the display panel;

[0143] According to the first defect information, perform defect identification on the second panel image to obtain second defect information of the display panel.

[0144] For the specific implementation of each of the above operations, reference may be made to the previous embodiments, which will not be elaborated here.

[0145] Among them, the computer-readable storage medium may include: read-only memory (ROM, Read Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disc, etc.

[0146] Since the computer program stored in the computer-readable storage medium can execute any panel defect identification method provided by the embodiments of the present disclosure, the beneficial effects achievable by any panel defect identification method provided by the embodiments of the present disclosure can be realized. For details, reference may be made to the previous embodiments, which will not be elaborated here.

[0147] In the above panel defect identification system, computer-readable storage medium, and electronic device, the descriptions of each embodiment have their own focuses. For parts not elaborated in a certain embodiment, reference may be made to the relevant descriptions of other embodiments. Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes and beneficial effects brought by the above-described panel defect identification system, computer-readable storage medium, computer program product, electronic device, and their corresponding units can refer to the description of the panel defect identification method in the above embodiments, which will not be elaborated here specifically.

[0148] The above has introduced in detail a panel defect identification method, system, electronic device, and computer-readable storage medium provided by the embodiments of the present disclosure. Specific examples are used in this article to elaborate on the principle and implementation manner of the present disclosure. The description of the above embodiments is only used to help understand the method and its core idea of the present disclosure; at the same time, for those skilled in the art, based on the idea of the present disclosure, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present disclosure.

Claims

1. A method for identifying panel defects, characterized in that, including: obtaining a first panel image corresponding to a display panel; performing defect identification on the first panel image to obtain first defect information of the display panel; performing defect identification on a second panel image according to the first defect information to obtain second defect information of the display panel.

2. The panel defect identification method according to claim 1, wherein The performing defect identification on the second panel image according to the first defect information to obtain second defect information of the display panel includes: performing defect segmentation on the second panel image according to the first defect information to obtain target panel defect information in the second panel image; performing panel segmentation on the second panel image according to a defect area corresponding to the target panel defect information to obtain first characteristic information corresponding to the target panel defect information; performing defect identification on the second panel image according to the first characteristic information to obtain second defect information of the display panel.

3. The panel defect recognition method according to claim 2, characterized in that The performing defect identification on the second panel image according to the first characteristic information to obtain second defect information of the display panel includes: obtaining panel parameters corresponding to the target panel defect information in the second panel image; performing optimization processing on the first characteristic information according to the panel parameters to obtain second characteristic information; obtaining second defect information of the display panel according to the second characteristic information.

4. The panel defect recognition method according to claim 2, wherein The performing panel segmentation on the second panel image according to a defect area corresponding to the target panel defect information to obtain first characteristic information corresponding to the target panel defect information includes: obtaining a mapped image of a standard panel image on the second panel image; performing panel segmentation on the second panel image according to the mapped image to obtain panel device information corresponding to the target panel defect information in the second panel image; obtaining the first characteristic information corresponding to the panel device information according to an area intersection of the defect area and a corresponding area in the standard panel image.

5. The panel defect recognition method according to claim 3, wherein After the performing defect identification on the second panel image according to the first characteristic information to obtain second defect information of the display panel, it includes: obtaining target circuit device information corresponding to the target panel defect information; determining defect repair information according to the target circuit device information and a defect repair database.

6. The panel defect identification method according to claim 5, wherein, After the repairing a target panel defect in the target panel defect information according to the target circuit device information and the defect repair database, it further includes: collecting a third panel image of the repaired target panel defect; obtaining a pixel difference between the second panel image and the third panel image; if the pixel difference is less than a pixel threshold, collecting a new second panel image according to a defect position in the first defect information.

7. The panel defect recognition method according to claim 1, characterized in that The performing defect identification on the first panel image to obtain first defect information of the display panel includes: obtaining text information corresponding to the first panel image; obtaining a target identifier of the display panel according to the text information; obtaining a defect library corresponding to the target identifier according to the target identifier; determining first defect information of the display panel according to the defect library.

8. A panel defect recognition system, characterized in that, The system includes: An acquisition module, configured to acquire a first panel image corresponding to a display panel; A first recognition module, configured to perform defect recognition on the first panel image to obtain first defect information of the display panel; A second recognition module, configured to perform defect recognition on a second panel image according to the first defect information to obtain second defect information of the display panel; Preferably, the second recognition module performing defect recognition on the second panel image according to the first defect information to obtain second defect information of the display panel includes: Performing defect segmentation on the second panel image according to the first defect information to obtain target panel defect information in the second panel image; Performing panel segmentation on the second panel image according to a defect region corresponding to the target panel defect information to obtain first characteristic information corresponding to the target panel defect information; Performing defect recognition on the second panel image according to the first characteristic information to obtain second defect information of the display panel. Preferably, the second recognition module performing defect recognition on the second panel image according to the first characteristic information to obtain second defect information of the display panel includes: Obtaining panel parameters corresponding to the target panel defect information in the second panel image; Performing optimization processing on the first characteristic information according to the panel parameters to obtain second characteristic information; Obtaining second defect information of the display panel according to the second characteristic information. Preferably, the second recognition module performing panel segmentation on the second panel image according to a defect region corresponding to the target panel defect information to obtain first characteristic information corresponding to the target panel defect information includes: Obtaining a mapped image of a standard panel image on the second panel image; Performing panel segmentation on the second panel image according to the mapped image to obtain panel device information corresponding to the target panel defect information in the second panel image; Obtaining the first characteristic information corresponding to the panel device information according to an area intersection of the defect region and a corresponding region in the standard panel image. Preferably, after the second recognition module performs defect recognition on the second panel image according to the first characteristic information to obtain second defect information of the display panel, the second recognition module is further configured to: Obtaining target circuit device information corresponding to the target panel defect information; Determining defect repair information according to the target circuit device information and a defect repair database. Preferably, after the second recognition module determines defect repair information according to the target circuit device information and the defect repair database, the second recognition module is further configured to: Collecting a third panel image of the repaired target panel defect; Obtaining a pixel difference between the second panel image and the third panel image; If the pixel difference is less than a pixel threshold, collecting a new second panel image according to a defect position in the first defect information. Preferably, the first recognition module performing defect recognition on the first panel image to obtain first defect information of the display panel includes: Obtain the text information corresponding to the first panel image; Obtain the target identifier of the display panel according to the text information; Obtain the defect library corresponding to the target identifier according to the target identifier; Determine the first defect information of the display panel according to the defect library.

9. An electronic device, characterized in that, It includes a processor and a memory, and the memory stores multiple instructions; the processor loads the instructions from the memory to execute the steps of the panel defect recognition method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores multiple instructions, and the instructions are suitable for being loaded by a processor to execute the steps of the panel defect recognition method according to any one of claims 1 to 7.

Images