Panel product module section lamination defect detection method and system

Abstract

The invention provides a panel product module segment lamination defect detection method and system, and relates to the technical field of defect detection, and the method comprises the following steps: obtaining a liquid crystal substrate segmentation image and a lamination area segmentation image; inputting the liquid crystal substrate segmentation image and the lamination area segmentation image into a pre-trained target detection model for detection so as to obtain center point coordinates of the liquid crystal substrate and the peripheral driving circuit, center point coordinates of the lamination area and the number and the type of conductive particles; based on the central point coordinates of the liquid crystal substrate and the peripheral driving circuit, the central point coordinates of the press-fit area and the number and the type of the conductive particles, a solder resist deviation measurement result, a press-fit deviation measurement result and a conductive particle counting result are obtained respectively; and performing defect comprehensive judgment based on the resistance welding deviation measurement result, the lamination deviation measurement result and the conductive particle counting result to obtain a module section lamination defect detection result. The problem that existing panel product module section press-fit defect detection accuracy is poor is solved.

Description

Technical Field

[0001] The present invention relates to the field of defect detection technology, and in particular to a method and system for detecting lamination defects of a panel product module segment. Background Art

[0002] During the production of panel products, module lamination is the last processing step of panel products, which is to press and connect the liquid crystal substrate and the peripheral driving circuit. The most important thing in this process is the control of lamination quality. If there are lamination defects in the panel product, it may affect the conductivity of the panel product. Among them, the most common lamination defects are lamination deviation and insufficient conductive particles. The lamination area relies on conductive particles for conductivity, and lamination deviation will also cause the conductive particles to be unable to adhere to the lamination area, resulting in insufficient conductive particles.

[0003] Traditional machine vision methods (CV methods) are easily affected by image quality, resulting in inaccurate measurement of pressing deviation. Conductive particles need to be judged as qualified based on particle size and saturation level. Traditional machine vision methods cannot accurately judge whether particles are qualified. Summary of the invention

[0004] The present invention provides a method and system for detecting lamination defects of module sections of panel products, which solves the problem of poor accuracy in detecting lamination defects of module sections of existing panel products.

[0005] In a first aspect, an embodiment of the present invention provides a method for detecting module section lamination defects of a panel product, the method comprising the following process:

[0006] Acquire a lamination area image of the panel product module, and perform image segmentation processing on the lamination area image to obtain a liquid crystal substrate segmentation image and a lamination area segmentation image;

[0007] Input the segmented image of the liquid crystal substrate and the segmented image of the lamination area into the pre-trained target detection model to perform liquid crystal substrate information detection, lamination area information detection and conductive particle information detection, so as to obtain the center point coordinates of the liquid crystal substrate and the peripheral driving circuit, the center point coordinates of the lamination area, and the number and type of conductive particles;

[0008] Based on the center point coordinates of the liquid crystal substrate and the peripheral driving circuit, the center point coordinates of the lamination area, and the number and type of conductive particles, the solder resist offset measurement results, the lamination offset measurement results, and the conductive particle counting results are respectively obtained;

[0009] Based on the solder mask offset measurement results, the pressing offset measurement results, and the conductive particle counting results, a comprehensive defect judgment is performed to obtain the module section pressing defect detection results.

[0010] In the above embodiment, the present invention adopts a combination of deep learning and machine vision to perform module segment pressing defect detection. First, deep learning technology is used to detect and classify defective objects. Then, machine vision technology is used in combination with the structural characteristics of module segment pressing to obtain solder resist offset measurement results, pressing offset measurement results, and conductive particle counting results. Finally, the solder resist offset measurement results, pressing offset measurement results, and conductive particle counting results are combined with actual abnormality judgment standards to perform a comprehensive defect judgment. The module segment pressing defects can be comprehensively measured, which solves the problem of poor accuracy in module segment pressing defect detection of existing panel products.

[0011] As some optional implementations of the present application, the process of inputting the liquid crystal substrate segmentation image and the lamination area segmentation image into the pre-trained target detection model to perform liquid crystal substrate information detection, lamination area information detection and conductive particle information detection is as follows:

[0012] The segmented image of the liquid crystal substrate is input into the pre-trained target detection model to detect the information of the liquid crystal substrate to obtain the center point coordinates of the liquid crystal substrate (c x1 ,c y1 ) and the center point coordinates of the peripheral drive circuit (c x2 ,c y2 );

[0013] The lamination area segmentation image is input into the pre-trained target detection model to detect the lamination area information to obtain the horizontal coordinates u of the center points at the top of several lamination areas. xi and the horizontal coordinate d of the center point at the bottom of the pressing area xi ;

[0014] The segmented image of the pressed area is input into the pre-trained target detection model to detect the conductive particle information to obtain the number of high-quality conductive particles L h And the number of general conductive particles L l .

[0015] In the above embodiment, the present invention inputs the liquid crystal substrate segmentation image and the pressing area segmentation image into a pre-trained target detection model to perform liquid crystal substrate information detection, pressing area information detection and conductive particle information detection respectively. The target detection model uses deep learning technology to quickly and accurately obtain the coordinate information and particle quantity and category information required for subsequent machine vision technology processing.

[0016] As some optional implementations of the present application, the process of obtaining the solder mask offset measurement result based on the center point coordinates of the liquid crystal substrate and the peripheral driving circuit is as follows:

[0017] Based on the horizontal coordinate c of the center point of the liquid crystal substrate x1 And the horizontal coordinate c of the center point of the peripheral drive circuit x2Calculate the offset distance x in the X-axis direction off ;

[0018] The vertical coordinate c based on the center point of the liquid crystal substrate y1 And the ordinate c of the center point of the peripheral drive circuit y2 Calculate the offset distance y in the Y-axis direction off .

[0019] In the above embodiment, the present invention combines the structural features of the liquid crystal substrate and the peripheral driving circuit of the panel product module segment, and can accurately measure the solder mask deviation by calculating the deviation distance between the two in the X-axis direction and the Y-axis direction.

[0020] As some optional implementations of the present application, the calculation formula for the solder resist offset measurement result is as follows:

[0021] x off =|c x1 -c x2 |

[0022] y off =|c y1 -c y2 |

[0023] Among them, x off Indicates the offset distance x in the X-axis direction off ,y off Indicates the Y-axis deviation distance y off , (c x1 ,c y1 ) represents the center point coordinate of the liquid crystal substrate, (c x2 ,c y2 ) represents the center point coordinates of the peripheral driving circuit.

[0024] As some optional implementations of the present application, the process of obtaining the lamination offset measurement result based on the center point coordinates of the lamination area is as follows:

[0025] Based on the horizontal coordinate u of the center point of the upper part of the pressing area xi and the horizontal coordinate d of the center point at the bottom of the pressing area xi Calculate the offset distance of each lamination area in the X-axis direction

[0026] The offset distance of all lamination areas in the X-axis direction Perform mean processing to obtain the final X-axis deviation distance M off .

[0027] In the above embodiment, the present invention combines the structural characteristics of the lamination area of ​​the panel product module section and can accurately measure the lamination deviation by calculating the average of the deviation distances of all lamination areas in the X-axis direction.

[0028] As some optional implementations of the present application, the calculation formula of the pressing deviation measurement result is as follows:

[0029] Among them, M off Indicates the final X-axis deviation distance. represents the offset distance of the i-th pressing area in the X-axis direction, u xi The horizontal coordinate of the center point of the upper part of the pressing area corresponding to the i-th pressing area, d xi represents the abscissa of the center point of the lower part of the pressing area corresponding to the i-th pressing area, and k represents the total number of pressing areas.

[0030] As some optional implementations of the present application, the process of obtaining the conductive particle counting result based on the number and type of conductive particles is as follows:

[0031] Preset weight coefficient q of high-quality conductive particles 1 And the weight coefficient q of general conductive particles 2 ;

[0032] Based on the weight coefficient q 1 And the number of high-quality conductive particles L h Calculate the count proportion of high-quality conductive particles and based on the weight coefficient q 2 and the number of general conductive particles L l Calculate the count ratio of general conductive particles;

[0033] The count percentage of high-quality conductive particles and the count percentage of general conductive particles are added together to obtain a final conductive particle count L.

[0034] In the above embodiment, the present invention combines the weight coefficients of high-quality conductive particles and general conductive particles to comprehensively convert the number of conductive particles, which can alleviate the problem of inaccurate judgment of conductive particle types by deep learning technology.

[0035] As some optional implementations of the present application, the calculation formula of the conductive particle counting result is as follows:

[0036] L = q 1 *L h +q 2 *L l

[0037] Where, L represents the final conductive particle count, q 1 Represents the weight coefficient corresponding to high-quality conductive particles, q 2 Indicates the weight coefficient corresponding to general conductive particles, L h Indicates the number of high-quality conductive particles, L lIndicates the number of general conductive particles.

[0038] In a second aspect, the present invention provides a panel product module section lamination defect detection system, the system comprising:

[0039] An image acquisition unit, the image acquisition unit is used to acquire a lamination area image of the panel product module, and perform image segmentation processing on the lamination area image to obtain a liquid crystal substrate segmentation image and a lamination area segmentation image;

[0040] A model detection unit, wherein the model detection unit is used to input the liquid crystal substrate segmentation image and the lamination area segmentation image into a pre-trained target detection model to perform liquid crystal substrate information detection, lamination area information detection and conductive particle information detection, so as to obtain the center point coordinates of the liquid crystal substrate and the peripheral driving circuit, the center point coordinates of the lamination area, and the number and type of conductive particles;

[0041] A visual analysis unit, wherein the visual analysis unit obtains solder resist offset measurement results, pressing offset measurement results, and conductive particle counting results based on the center point coordinates of the liquid crystal substrate and the peripheral driving circuit, the center point coordinates of the pressing area, and the number and type of conductive particles;

[0042] A defect determination unit performs comprehensive defect determination based on the solder resist offset measurement result, the pressing offset measurement result, and the conductive particle counting result to obtain a module section pressing defect detection result.

[0043] In a third aspect, the present invention provides a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method for detecting module section lamination defects of a panel product when executing the computer program.

[0044] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for detecting module section lamination defects of a panel product is implemented.

[0045] In a fifth aspect, the present invention provides a computer program product, including a computer program, which, when executed by a processor, implements the method for detecting module section lamination defects of a panel product.

[0046] The beneficial effects of the present invention are as follows: The present invention adopts a combination of deep learning and machine vision to perform module segment pressing defect detection. First, deep learning technology is used to detect and classify defective objects. Then, machine vision technology is used in combination with the structural characteristics of module segment pressing to obtain solder mask deviation measurement results, pressing deviation measurement results, and conductive particle counting results. Finally, the solder mask deviation measurement results, pressing deviation measurement results, and conductive particle counting results are comprehensively judged in combination with actual abnormality judgment standards, so as to comprehensively measure and judge the module segment pressing defects. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0048] Figure 1 is a schematic diagram of the computer device structure of the hardware operating environment described in the embodiment of the present invention;

[0049] Figure 2 It is a flow chart of a method for detecting module section pressing defects of a crystal panel product according to an embodiment of the present invention;

[0050] Figure 3 is a schematic diagram of a lamination area image according to an embodiment of the present invention;

[0051] Figure 4 is a schematic diagram of a lamination area segmentation image according to an embodiment of the present invention;

[0052] Figure 5 is a schematic diagram of a liquid crystal substrate splitting an image on the left and right sides according to an embodiment of the present invention;

[0053] Figure 6 is a schematic diagram of liquid crystal substrate information detection according to an embodiment of the present invention;

[0054] Figure 7 is a schematic diagram of the detection of the lamination area information according to an embodiment of the present invention;

[0055] Figure 8 is a schematic diagram of conductive particle information detection according to an embodiment of the present invention;

[0056] Fig. 9 It is a structural block diagram of a panel product module section pressing defect detection system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0057] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0058] In order to solve the problem of poor accuracy in detecting module section lamination defects of existing panel products, the present application provides a method and system for detecting module section lamination defects of panel products. Before introducing the specific technical solution of the present application, the hardware operating environment involved in the embodiment of the present application is first introduced.

[0059] See also Figure 1 , Figure 1 A schematic diagram of the computer device structure of the hardware operating environment involved in the embodiment of the present application.

[0060] like Figure 1 As shown, the computer device may include: a processor, such as a central processing unit (CPU), a communication bus, a user interface, a network interface, and a memory. Among them, the communication bus is used to realize the connection and communication between these components. The user interface may include a display screen (Display), an input unit such as a keyboard (Keyboard), and optionally, the user interface may also include a standard wired interface and a wireless interface. The network interface may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity interface). The memory may be a high-speed random access memory (Random Access Memory, RAM) memory, or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. The memory may optionally be a storage device independent of the aforementioned processor.

[0061] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the computer device, and may include more or less components than shown in the figure, or combine some components, or arrange the components differently.

[0062] like Figure 1 As shown, the memory as a storage medium may include an operating system, a data storage module, a network communication module, a user interface module and an electronic program module.

[0063] exist Figure 1 In the computer device shown, the network interface is mainly used for data communication with the network server; the user interface is mainly used for data interaction with the user; the processor and memory in the computer device of the present application can be set in the computer device, and the computer device calls the computer program product stored in the electronic program module through the processor, and executes the panel product module segment pressing defect detection method provided in the embodiment of the present application.

[0064] Based on the hardware environment of the aforementioned embodiment, the embodiment of the present application provides a method for detecting module segment lamination defects of a panel product, please refer to Figure 2 , Figure 2 The flowchart of the method for detecting the lamination defects of the module section of the panel product is as follows:

[0065] (1) Acquire a lamination area image of a panel product module, and perform image segmentation processing on the lamination area image to obtain a liquid crystal substrate segmentation image and a lamination area segmentation image.

[0066] In the embodiment of the present invention, during the panel product production process, a line scan camera is used to take a picture of the lamination area of ​​the entire module to obtain an image of the lamination area. However, since the image width of the lamination area image is relatively large, please refer to Figure 3 , Figure 3 The schematic diagram of the lamination area image is as follows. It is not possible to directly use the target detection model for one-time recognition. Therefore, it is necessary to perform image segmentation on the lamination area image. For example, if the height of the lamination area image is 2048, the lamination area image can be segmented into 2048*2048 lamination area segmentation images and liquid crystal substrate segmentation images for subsequent detection. Please refer to Figure 4 , Figure 5 , Figure 4 is a schematic diagram of the segmented image of the lamination area, Figure 5 Schematic diagram of the liquid crystal substrate segmentation image on the left and right sides.

[0067] In an embodiment of the present invention, before inputting the liquid crystal substrate segmentation image and the lamination area segmentation image into the pre-trained target detection model for liquid crystal substrate information detection, lamination area information detection and conductive particle information detection, pre-training is required. The process of model training is as follows:

[0068] (1.1) Obtain the original lamination area image of the panel product module, and perform image segmentation processing on the lamination area image to obtain a liquid crystal substrate segmentation image and a lamination area segmentation image.

[0069] (1.2) Feature marking is performed on the liquid crystal substrate and the peripheral driving circuit on the surface of the liquid crystal substrate segmentation image to obtain solder mask deviation training data; feature marking is performed on the upper part of the pressing area and the lower part of the pressing area on the surface of the pressing area segmentation image (the pressing area is composed of the upper area and the lower area) to obtain pressing deviation training data; feature marking is performed on the conductive particles on the surface of the pressing area segmentation image to obtain conductive particle training data.

[0070] (1.3) Input the solder mask offset training data, the lamination offset training data and the conductive particle training data into the target detection model for model training, so that the target detection model can perform liquid crystal substrate information detection, lamination area information detection and conductive particle information detection. The target detection model includes but is not limited to the FasterRCNN model, the YOLO framework, etc.

[0071] (2) Inputting the segmented image of the liquid crystal substrate and the segmented image of the lamination area into the pre-trained target detection model to perform liquid crystal substrate information detection, lamination area information detection and conductive particle information detection, so as to obtain the center point coordinates of the liquid crystal substrate and the peripheral driving circuit, the center point coordinates of the lamination area and the number and type of conductive particles.

[0072] In an embodiment of the present invention, the process of inputting the liquid crystal substrate segmentation image and the lamination area segmentation image into the pre-trained target detection model to perform liquid crystal substrate information detection, lamination area information detection and conductive particle information detection is as follows:

[0073] (2.1) Input the segmented image of the liquid crystal substrate into the pre-trained target detection model to detect the information of the liquid crystal substrate to obtain the center point coordinates of the liquid crystal substrate (c x1 ,c y1 ) and the center point coordinates of the peripheral drive circuit (c x2 ,c y2 ).

[0074] (2.2) Input the lamination area segmentation image into the pre-trained target detection model to detect the lamination area information to obtain the horizontal coordinates u of the center points at the top of several lamination areas xi and the horizontal coordinate d of the center point at the bottom of the pressing area xi .

[0075] (2.3) Input the segmented image of the pressed area into the pre-trained target detection model to detect the conductive particle information to obtain the number of high-quality conductive particles L h And the number of general conductive particles L l .

[0076] (3) Based on the center point coordinates of the liquid crystal substrate and the peripheral driving circuit, the center point coordinates of the lamination area, and the number and type of conductive particles, the solder resist offset measurement results, the lamination offset measurement results, and the conductive particle counting results are obtained respectively.

[0077] In an embodiment of the present invention, the process of obtaining the solder mask offset measurement result based on the center point coordinates of the liquid crystal substrate and the peripheral driving circuit is as follows:

[0078] (3.1) Based on the horizontal coordinate c of the center point of the liquid crystal substrate x1And the horizontal coordinate c of the center point of the peripheral drive circuit x2 Calculate the offset distance x in the X-axis direction off .

[0079] (3.2) Based on the vertical coordinate c of the center point of the liquid crystal substrate y1 And the ordinate c of the center point of the peripheral drive circuit y2 Calculate the offset distance y in the Y-axis direction off , see Figure 6 , Figure 6 It is a schematic diagram of the liquid crystal substrate information detection.

[0080] Specifically, the calculation formula of the solder resist offset measurement result is as follows:

[0081] x off =|c x1 -c x2 |

[0082] y off =|c y1 -c y2 |

[0083] Among them, x off Indicates the offset distance x in the X-axis direction off ,y off Indicates the Y-axis deviation distance y off , (c x1 ,c y1 ) represents the center point coordinate of the liquid crystal substrate, (c x2 ,c y2 ) represents the center point coordinates of the peripheral driving circuit.

[0084] In an embodiment of the present invention, the process of obtaining the lamination deviation measurement result based on the center point coordinates of the lamination area is as follows:

[0085] (3.3) Based on the horizontal coordinate u of the center point at the top of the pressing area xi and the horizontal coordinate d of the center point at the bottom of the pressing area xi Calculate the offset distance of each lamination area in the X-axis direction

[0086] (3.4) The offset distance of all lamination areas in the X-axis direction Perform mean processing to obtain the final X-axis deviation distance M off , see Figure 7 , Figure 7 It is a schematic diagram of the pressing area information detection.

[0087] Specifically, the calculation formula of the pressing deviation measurement result is as follows:

[0088]

[0089] Among them, M off Indicates the final X-axis deviation distance. represents the offset distance of the i-th pressing area in the X-axis direction, u xi The horizontal coordinate of the center point of the upper part of the pressing area corresponding to the i-th pressing area, d xi represents the abscissa of the center point of the lower part of the pressing area corresponding to the i-th pressing area, and k represents the total number of pressing areas.

[0090] In an embodiment of the present invention, the process of obtaining the conductive particle counting result based on the number and type of conductive particles is as follows:

[0091] (3.5) Preset the weight coefficient q of high-quality conductive particles 1 And the weight coefficient q of general conductive particles 2 , generally, the weight coefficient q of high-quality conductive particles 1 Set to 1, the weight coefficient q of general conductive particles 2 The weight coefficient q of the general conductive particles involved in the embodiment of the present invention is between 0 and 1, and can be adjusted according to the actual situation. 2 Can be set to 0.6.

[0092] (3.6) Based on the weight coefficient q 1 And the number of high-quality conductive particles L h Calculate the count proportion of high-quality conductive particles and based on the weight coefficient q 2 and the number of general conductive particles L l Calculate the count ratio of general conductive particles.

[0093] (3.7) The count percentage of high-quality conductive particles and the count percentage of general conductive particles are added together to obtain the final conductive particle count L. Please refer to Figure 8 , Figure 8 This is a schematic diagram of the conductive particle information detection.

[0094] Specifically, the calculation formula of the conductive particle counting result is as follows:

[0095] L = q 1 *L h +q 2 *L l

[0096] Where, L represents the final conductive particle count, q 1 Represents the weight coefficient corresponding to high-quality conductive particles, q 2 Indicates the weight coefficient corresponding to general conductive particles, Lh Indicates the number of high-quality conductive particles, L l Indicates the number of general conductive particles.

[0097] Specifically, according to the actual situation, the conductive particles with very clear pressing can be defined as high-quality particles, and the remaining conductive particles can be defined as general particles. At the same time, the conductive particles with unclear pressing can also be eliminated from the general particles. The definition of high-quality conductive particles and general particles in the embodiment of the present invention can be set according to the actual situation, and the embodiment of the present invention does not limit this.

[0098] (4) Based on the solder mask offset measurement results, the pressing offset measurement results, and the conductive particle counting results, a comprehensive defect judgment is performed to obtain the module section pressing defect detection results.

[0099] In an embodiment of the present invention, the process of comprehensive defect determination based on the solder resist offset measurement results, the pressing offset measurement results, and the conductive particle counting results is as follows:

[0100] (4.1) Preset solder resist offset measurement result to determine solder resist offset threshold T 1 , the pressing deviation threshold T determined by the pressing deviation measurement result 2 , the conductive particle threshold T for judging the conductive particle counting result 3 .

[0101] (4.2) At the same time, determine whether the solder resist offset measurement result is greater than the solder resist offset threshold T 1 , whether the pressing deviation measurement result is greater than the pressing deviation threshold T 2 , whether the conductive particle counting result is less than the conductive particle threshold T 3 , as long as any judgment is established, it is comprehensively judged that there are defects in the compression of the module segments.

[0102] Specifically, the solder resist offset threshold T 1 , Pressing deviation threshold T 2 and the conductive particle threshold T 3 The configuration is performed according to actual conditions, and the embodiments of the present invention do not limit this.

[0103] In summary, the present invention adopts a combination of deep learning and machine vision to perform module segment pressing defect detection. First, deep learning technology is used to detect and classify defective objects. Then, machine vision technology is used in combination with the structural characteristics of module segment pressing to obtain solder resist offset measurement results, pressing offset measurement results, and conductive particle counting results. Finally, the solder resist offset measurement results, pressing offset measurement results, and conductive particle counting results are comprehensively judged in combination with actual abnormality judgment standards, so as to comprehensively measure and judge the module segment pressing defects.

[0104] In addition, in one embodiment, based on the same inventive concept as the above embodiment, the embodiment of the present invention provides a panel product module section lamination defect detection system, and the system corresponds to the method of embodiment 1 one by one, please refer to Fig. 9 , Fig. 9 The structural block diagram of the panel product module section pressing defect detection system is as follows:

[0105] An image acquisition unit, the image acquisition unit is used to acquire a lamination area image of the panel product module, and perform image segmentation processing on the lamination area image to obtain a liquid crystal substrate segmentation image and a lamination area segmentation image;

[0106] A model detection unit, wherein the model detection unit is used to input the liquid crystal substrate segmentation image and the lamination area segmentation image into a pre-trained target detection model to perform liquid crystal substrate information detection, lamination area information detection and conductive particle information detection, so as to obtain the center point coordinates of the liquid crystal substrate and the peripheral driving circuit, the center point coordinates of the lamination area, and the number and type of conductive particles;

[0107] A visual analysis unit, wherein the visual analysis unit obtains solder resist offset measurement results, pressing offset measurement results, and conductive particle counting results based on the center point coordinates of the liquid crystal substrate and the peripheral driving circuit, the center point coordinates of the pressing area, and the number and type of conductive particles;

[0108] A defect determination unit performs comprehensive defect determination based on the solder resist offset measurement result, the pressing offset measurement result, and the conductive particle counting result to obtain a module section pressing defect detection result.

[0109] It should be noted that each unit in the panel product module section pressing defect detection system in this embodiment corresponds one-to-one to each step in the panel product module section pressing defect detection method in the aforementioned embodiment. Therefore, the specific implementation manner and technical effects achieved by this embodiment can refer to the implementation manner of the aforementioned panel product module section pressing defect detection method, and will not be repeated here.

[0110] In addition, in one embodiment, the present application also provides a computer device, which includes a processor, a memory, and a computer program stored in the memory, and the computer program implements the method in the aforementioned embodiment when executed by the processor.

[0111] In addition, in one embodiment, the present application further provides a computer storage medium, on which a computer program is stored, and the computer program implements the method in the aforementioned embodiment when executed by a processor.

[0112] In some embodiments, the computer readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or various devices including one or any combination of the above memories. The computer may be various computing devices including intelligent terminals and servers.

[0113] In some embodiments, executable instructions may be in the form of a program, software, software module, script or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine or other unit suitable for use in a computing environment.

[0114] As an example, executable instructions may, but need not, correspond to a file in a file system, may be stored as part of a file that stores other programs or data, such as in one or more scripts in a HyperText Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files storing one or more modules, subroutines, or code portions).

[0115] By way of example, executable instructions may be deployed to be executed on one computing device, or on multiple computing devices located at one site, or on multiple computing devices distributed across multiple sites and interconnected by a communication network.

[0116] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0117] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0118] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory / random access memory, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a multimedia terminal device (which can be a mobile phone, a computer, a television receiver, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0119] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for detecting defects in module sections of panel products, characterized in that: The method comprises the following steps: Acquire a lamination area image of the panel product module, and perform image segmentation processing on the lamination area image to obtain a liquid crystal substrate segmentation image and a lamination area segmentation image; Input the segmented image of the liquid crystal substrate and the segmented image of the lamination area into the pre-trained target detection model to perform liquid crystal substrate information detection, lamination area information detection and conductive particle information detection, so as to obtain the center point coordinates of the liquid crystal substrate and the peripheral driving circuit, the center point coordinates of the lamination area, and the number and type of conductive particles; Based on the center point coordinates of the liquid crystal substrate and the peripheral driving circuit, the center point coordinates of the lamination area, and the number and type of conductive particles, the solder resist offset measurement results, the lamination offset measurement results, and the conductive particle counting results are respectively obtained; Based on the solder mask offset measurement results, the pressing offset measurement results, and the conductive particle counting results, a comprehensive defect judgment is performed to obtain the module section pressing defect detection results.

2. A panel product module section lamination defect detection method according to claim 1, characterized in that: The process of inputting the liquid crystal substrate segmentation image and the lamination area segmentation image into the pre-trained target detection model to perform liquid crystal substrate information detection, lamination area information detection and conductive particle information detection is as follows: The segmented image of the liquid crystal substrate is input into the pre-trained target detection model to detect the information of the liquid crystal substrate to obtain the center point coordinates of the liquid crystal substrate (c x1 ,c y1 ) and the center point coordinates of the peripheral drive circuit (c x2 ,c y2 ); The lamination area segmentation image is input into the pre-trained target detection model to detect the lamination area information to obtain the horizontal coordinates u of the center points at the top of several lamination areas. xi and the horizontal coordinate d of the center point at the bottom of the pressing area xi ; The segmented image of the pressed area is input into the pre-trained target detection model to detect the conductive particle information to obtain the number of high-quality conductive particles L h And the number of general conductive particles L l .

3. A panel product module section lamination defect detection method according to claim 2, characterized in that: The process of obtaining the solder mask offset measurement results based on the center point coordinates of the liquid crystal substrate and the peripheral drive circuit is as follows: Based on the horizontal coordinate c of the center point of the liquid crystal substrate x1 And the horizontal coordinate c of the center point of the peripheral drive circuit x2 Calculate the offset distance x in the 1-axis direction off ; The vertical coordinate c based on the center point of the liquid crystal substrate y1 And the ordinate c of the center point of the peripheral drive circuit y2 Calculate the offset distance y in the Y-axis direction off .

4. A panel product module section lamination defect detection method according to claim 3, characterized in that: The calculation formula of the solder resist offset measurement result is as follows: x o f f =|c x1 -c x2 | y off =|c y1 -c y2 | Among them, x off Indicates the offset distance x in the X-axis direction off ,y off Indicates the Y-axis deviation distance y off , (c x1 , c y1 ) represents the center point coordinate of the liquid crystal substrate, (c x2 , c y2 ) represents the center point coordinates of the peripheral driving circuit.

5. A panel product module section lamination defect detection method according to claim 2, characterized in that: The process of obtaining the lamination deviation measurement results based on the center point coordinates of the lamination area is as follows: Based on the horizontal coordinate u of the center point of the upper part of the pressing area xi and the horizontal coordinate d of the center point at the bottom of the pressing area xi Calculate the offset distance of each lamination area in the X-axis direction The offset distance of all lamination areas in the X-axis direction Perform mean processing to obtain the final X-axis deviation distance M off .

6. A panel product module section lamination defect detection method according to claim 5, characterized in that: The calculation formula of the pressing deviation measurement result is as follows: Among them, M off Indicates the final X-axis deviation distance. represents the offset distance of the i-th pressing area in the X-axis direction, u xi The horizontal coordinate of the center point of the upper part of the pressing area corresponding to the i-th pressing area, d xi represents the abscissa of the center point of the lower part of the pressing area corresponding to the i-th pressing area, and k represents the total number of pressing areas.

7. A panel product module section lamination defect detection method according to claim 2, characterized in that: The process for obtaining conductive particle counting results based on the number and type of conductive particles is as follows: Preset the weight coefficient q1 of high-quality conductive particles and the weight coefficient q2 of general conductive particles; Based on the weight coefficient q1 and the number of high-quality conductive particles L h Calculate the count ratio of high-quality conductive particles and based on the weight coefficient q2 and the number of general conductive particles L l Calculate the count ratio of general conductive particles; The count percentage of high-quality conductive particles and the count percentage of general conductive particles are added together to obtain the final conductive particle count. L .

8. A panel product module section lamination defect detection method according to claim 7, characterized in that: The calculation formula of the conductive particle counting result is as follows: <h2 style=";text-align:left;direction:ltr">L = q1 * L<h2 style=";text-align:left;direction:ltr"> h <h2 style=";text-align:left;direction:ltr"> +q2*L<h2 style=";text-align:left;direction:ltr"> l Among them, L represents the final conductive particle count, q1 represents the weight coefficient corresponding to high-quality conductive particles, q2 represents the weight coefficient corresponding to general conductive particles, and L h Indicates the number of high-quality conductive particles, L l Indicates the number of general conductive particles.

9. A panel product module section pressing defect detection system, characterized in that: The system comprises: An image acquisition unit, the image acquisition unit is used to acquire a lamination area image of the panel product module, and perform image segmentation processing on the lamination area image to obtain a liquid crystal substrate segmentation image and a lamination area segmentation image; A model detection unit, wherein the model detection unit is used to input the liquid crystal substrate segmentation image and the lamination area segmentation image into a pre-trained target detection model to perform liquid crystal substrate information detection, lamination area information detection and conductive particle information detection, so as to obtain the center point coordinates of the liquid crystal substrate and the peripheral driving circuit, the center point coordinates of the lamination area, and the number and type of conductive particles; A visual analysis unit, wherein the visual analysis unit obtains solder resist offset measurement results, pressing offset measurement results, and conductive particle counting results based on the center point coordinates of the liquid crystal substrate and the peripheral driving circuit, the center point coordinates of the pressing area, and the number and type of conductive particles; A defect determination unit performs comprehensive defect determination based on the solder resist offset measurement result, the pressing offset measurement result, and the conductive particle counting result to obtain a module section pressing defect detection result.

10. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, it implements the method for detecting module section lamination defects of a panel product as described in any one of claims 1-8.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for detecting module section lamination defects of a panel product as described in any one of claims 1 to 8 is implemented.

12. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, it implements a method for detecting module section lamination defects of a panel product as described in any one of claims 1 to 8.

Images