Substrate detection method and device, terminal equipment and computer readable storage medium

Abstract

The invention is suitable for the technical field of substrate detection, and particularly relates to a substrate detection method and device, terminal equipment and a computer readable storage medium. The method comprises the following steps: acquiring a first image of a to-be-detected substrate, and performing image acquisition on the to-be-detected substrate through an image acquisition device according to an image acquisition strategy corresponding to size information of the to-be-detected substrate to obtain one or more second images in the to-be-detected substrate; and performing image recognition processing on the one or more second images in the to-be-detected substrate to obtain pad information corresponding to one or more pads in the to-be-detected substrate, and further detecting the to-be-detected substrate according to the pad information corresponding to one or more pads in the to-be-detected substrate and the pad information in one or more standard substrates, so as to detect the to-be-detected substrate according to the pad information corresponding to one or more pads in the to-be-detected substrate and the pad information in one or more standard substrates. And determining a detection result of the to-be-detected substrate. According to the invention, real expansion and contraction can be determined more accurately, the expansion and contraction condition of the to-be-detected substrate can be determined more reliably, and the stability and reliability of substrate detection are ensured.

Description

Technical Field

[0001] The present application belongs to the technical field of substrate detection, and in particular, relates to a substrate detection method, apparatus, terminal equipment and computer-readable storage medium. Background Art

[0002] LED (Light Emitting Diode) display modules are usually formed by transferring and soldering LED light-emitting chips to pads on the surface of the substrate using PCB (Printed Circuit Board) or transparent glass as substrates. Due to its material properties, PCBs are prone to expansion and contraction during the production and manufacturing of LED modules, such as during the soldering of LED light-emitting chips, which can affect product quality and may even cause product scrapping. Therefore, the rational control of abnormal expansion and contraction of PCB boards at different temperatures has become one of the most complex problems facing manufacturers. In addition, with the development of PCB boards towards multi-layer high-density types and the miniaturization of substrate-mounted devices, how to ensure their stable operation under various temperature environments and require the expansion and contraction performance of PCB boards to be within the specified range has also become a problem that must be solved in the industry.

[0003] The patent with publication number CN118293796A discloses a substrate detection method, device, electronic device and storage medium, which compares the substrate to be detected with each standard substrate in the standard substrate library, determines the closest target standard pad by the offset of the first pad, and then determines the expansion and contraction ratio and offset distance of each first pad of the substrate to be detected based on the target standard pad, and finally obtains the target standard substrate by matching first and then determines the expansion and contraction ratio and offset distance, thereby detecting the expansion and contraction information of the substrate to be detected. However, this method can only roughly detect the overall expansion and contraction information of the substrate, and the accuracy is low.

[0004] In summary, a more accurate and reliable PCB expansion and shrinkage detection method is needed to ensure the stability and reliability of PCB boards, while solving the modern PCB board detection needs that other detection methods cannot meet. Summary of the invention

[0005] The embodiments of the present application provide a substrate detection method, an apparatus, a terminal device, and a computer-readable storage medium, which can solve the technical problem of low substrate detection accuracy.

[0006] In a first aspect, an embodiment of the present application provides a substrate detection method, comprising: Acquire a first image of a substrate to be inspected; According to the image acquisition strategy corresponding to the size information of the substrate to be inspected, an image acquisition device is used to acquire an image of the substrate to be inspected, so as to obtain one or more second images of the substrate to be inspected, wherein the size information of the substrate to be inspected is determined according to the coordinate information of multiple marking points in the first image of the substrate to be inspected; Performing image recognition processing on one or more second images of the substrate to be inspected to obtain pad information corresponding to one or more pads in the substrate to be inspected; The inspection result of the substrate to be inspected is determined according to the pad information respectively corresponding to one or more pads in the substrate to be inspected and the pad information in one or more standard substrates.

[0007] In a possible implementation manner of the first aspect, the image acquisition strategy corresponding to the size information of the substrate to be inspected is used to acquire the image of the substrate to be inspected by an image acquisition device to obtain one or more second images of the substrate to be inspected, including: Determining an image acquisition strategy according to the size information of the substrate to be inspected and the field of view information of the image acquisition device; Based on the image acquisition strategy, an image acquisition device is used to acquire images of the substrate to be inspected, so as to obtain one or more second images of the substrate to be inspected.

[0008] In a possible implementation manner of the first aspect, the size information of the substrate to be inspected includes length information and width information of the substrate to be inspected, the field of view information of the image acquisition device includes length information and width information of the image acquisition device, and determining the image acquisition strategy according to the size information of the substrate to be inspected and the field of view information of the image acquisition device includes: Determining the number of times the image acquisition device moves in the length direction according to the length information of the substrate to be inspected and the length information of the image acquisition device; Determining the number of times the image acquisition device moves in the width direction according to the width information of the substrate to be inspected and the width information of the image acquisition device; An image acquisition strategy is determined according to the number of times the image acquisition device moves in the length direction and the number of times the image acquisition device moves in the width direction.

[0009] In a possible implementation manner of the first aspect, determining the image acquisition strategy according to the size information of the substrate to be inspected and the field of view information of the image acquisition device further includes: An image acquisition strategy is determined according to the size information of the substrate to be inspected, the field of view information of the image acquisition device and the pad arrangement information.

[0010] In a possible implementation manner of the first aspect, the size information of the substrate to be inspected is determined based on the following steps: Performing image recognition processing on the first image of the substrate to be inspected to obtain coordinate information of a plurality of marking points in the first image of the substrate to be inspected, wherein the first image of the substrate to be inspected includes a plurality of marking points; The size information of the substrate to be inspected is determined according to the coordinate information of a plurality of marking points in the first image of the substrate to be inspected.

[0011] In a possible implementation manner of the first aspect, determining the size information of the substrate to be inspected according to the coordinate information of a plurality of marking points in the first image of the substrate to be inspected includes: Determine size information of a range of the marking points according to coordinate information of a plurality of marking points in the first image of the substrate to be inspected; The size information of the marking point range is reduced to obtain the size information of the substrate to be inspected.

[0012] In a possible implementation manner of the first aspect, determining the inspection result of the substrate to be inspected according to pad information corresponding to one or more pads in the substrate to be inspected and pad information in one or more standard substrates includes: According to the offset of each pad in the substrate to be inspected corresponding to each pad in each standard substrate, the inspection result of each area of ​​the substrate to be inspected is determined, wherein the inspection result of each area of ​​the substrate to be inspected includes the comprehensive offset of the pad information of multiple pads in each area of ​​the substrate to be inspected relative to the pad information of corresponding multiple pads in the corresponding area of ​​each standard substrate.

[0013] In a second aspect, an embodiment of the present application provides a substrate detection device, comprising: A first image acquisition module, used to acquire a first image of the substrate to be inspected; a second image acquisition module, configured to acquire an image of the substrate to be inspected by an image acquisition device according to an image acquisition strategy corresponding to the size information of the substrate to be inspected, so as to acquire one or more second images of the substrate to be inspected, wherein the size information of the substrate to be inspected is determined according to the coordinate information of a plurality of marking points in the first image of the substrate to be inspected; A pad information acquisition module, used to perform image recognition processing on one or more second images of the substrate to be detected, and obtain pad information corresponding to one or more pads in the substrate to be detected; The detection result determination module is used to determine the detection result of the substrate to be detected according to the pad information corresponding to one or more pads in the substrate to be detected and the pad information in one or more standard substrates.

[0014] In a third aspect, an embodiment of the present application provides a terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the substrate detection method as described in the first aspect above is implemented.

[0015] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the substrate detection method as described in the first aspect above is implemented.

[0016] In a fifth aspect, an embodiment of the present application provides a computer program product. When the computer program product is run on a terminal device, the terminal device executes the substrate detection method described in any one of the above-mentioned first aspects.

[0017] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here.

[0018] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: The present application acquires a first image of a substrate to be detected, and according to an image acquisition strategy corresponding to the size information of the substrate to be detected, performs image acquisition on the substrate to be detected through an image acquisition device, obtains one or more second images of the substrate to be detected, performs image recognition processing on the one or more second images of the substrate to be detected, obtains pad information corresponding to one or more pads in the substrate to be detected, and then determines the detection result of the substrate to be detected according to the pad information corresponding to one or more pads in the substrate to be detected and the pad information in one or more standard substrates. The present application determines the detection result of the substrate to be detected based on multiple pad information at different positions of the substrate to be detected and the pad information of the standard substrate, which can more accurately determine the real expansion and contraction, more reliably determine the expansion and contraction of the substrate to be detected, ensure the stability and reliability of substrate detection, and the result is more valuable for reference. In addition, the present application solves the technical problem that other detection methods cannot meet the detection requirements of modern PCB boards. The present application can be applied to the sub-pixel light point arrangement application scenario of chip on board (COB), which can greatly reduce the cost for panel manufacturers in the industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0020] Figure 1 It is a schematic diagram of a process of a substrate detection method provided in an embodiment of the present application; Figure 2 is a schematic diagram of a marking point in a substrate to be detected; Figure 3 It is a schematic diagram of image acquisition of a substrate to be inspected according to an embodiment of the present application; Figure 4 A schematic diagram of capturing an image of a substrate to be inspected according to another embodiment of the present application; Figure 5 It is a schematic diagram of collecting images of a substrate to be inspected according to another embodiment of the present application; Figure 6 It is a flow chart of a substrate detection method provided by an application embodiment of the present application; Figure 7 is a structural schematic diagram of a substrate detection device provided in one embodiment of the present application; Figure 8 It is a schematic diagram of the structure of the terminal device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0021] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0022] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0023] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0024] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0025] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0026] The substrate detection method provided in the embodiment of the present application can be applied to terminal devices such as mobile phones, tablet computers, wearable devices, vehicle-mounted devices, augmented reality (AR) / virtual reality (VR) devices, laptop computers, ultra-mobile personal computers (UMPC), netbooks, personal digital assistants (PDA), etc. The embodiment of the present application does not impose any restrictions on the specific type of the terminal device.

[0027] For example, the terminal device can be a station (STAION, ST) in a WLAN, a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA) device, a handheld device with wireless communication function, a computing device or other processing device connected to a wireless modem, a vehicle-mounted device, a vehicle networking terminal, a computer, a laptop computer, a handheld communication device, a handheld computing device, a satellite wireless device, a wireless modem card, a TV set top box (STB), a customer premises equipment (CPE) and / or other devices for communicating on a wireless system and a next-generation communication system, such as a mobile terminal in a 5G network or a mobile terminal in a future evolved Public Land Mobile Network (PLMN) network, etc.

[0028] As an example but not limitation, when the terminal device is a wearable device, the wearable device can also be a general term for wearable devices that are intelligently designed and developed using wearable technology for daily wear, such as glasses, gloves, watches, clothing and shoes. A wearable device is a portable device that is worn directly on the body or integrated into the user's clothes or accessories. Wearable devices are not just hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are fully functional, large in size, and can achieve complete or partial functions without relying on smartphones, such as smart watches or smart glasses, as well as those that only focus on a certain type of application function and need to be used in conjunction with other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.

[0029] The present application provides a more accurate and reliable substrate detection method to ensure the stability and reliability of PCB boards, while solving modern PCB board detection needs that cannot be met by other detection methods.

[0030] Figure 1 It is a flow chart of a substrate detection method provided in one embodiment of the present application.

[0031] S11, acquiring a first image of a substrate to be inspected.

[0032] Here, the first image of the substrate to be inspected is an image whose image content includes the entire substrate to be inspected. The substrate can also be called a light board. The substrate to be inspected can also be called a light board to be inspected.

[0033] The first image of the substrate to be inspected can be acquired by an image acquisition device, which includes but is not limited to a camera, a webcam, or other devices that can be used to capture images.

[0034] In addition, the first image of the substrate to be inspected that is collected in advance may also be acquired from other devices by means of file transmission.

[0035] S12, according to the image acquisition strategy corresponding to the size information of the substrate to be inspected, the image acquisition device is used to acquire an image of the substrate to be inspected, so as to obtain one or more second images of the substrate to be inspected, wherein the size information of the substrate to be inspected is determined according to the coordinate information of multiple marking points in the first image of the substrate to be inspected.

[0036] Among them, the image acquisition strategy refers to the movement strategy executed by the image acquisition device when the mobile image acquisition device is performing image acquisition on the substrate to be inspected. Usually, the size of the substrate to be inspected is larger than the image acquisition field of view of the image acquisition device. Therefore, it is necessary to move the image acquisition device to comprehensively acquire the second image of each position in the substrate to be inspected. Since the pads are distributed in various areas and positions in the substrate to be inspected. Therefore, it is usually necessary to obtain one or more second images of the substrate to be inspected by performing image acquisition on the entire substrate to be inspected by the image acquisition device according to the image acquisition strategy corresponding to the size information of the substrate to be inspected, so as to comprehensively perform image acquisition on the substrate to be inspected. The second image refers to the image within the field of view of the image acquisition device obtained by the image acquisition device after capturing the substrate to be inspected once. The content of the second image usually includes one or more pads contained in a certain position in the substrate to be inspected.

[0037] The size information of the substrate to be inspected is determined based on the coordinate information of multiple marking points in the first image of the substrate to be inspected. The size information of the substrate to be inspected can be determined in the following two ways, including but not limited to.

[0038] 1) Performing image recognition processing on a first image of a substrate to be inspected, obtaining coordinate information of a plurality of marking points in the first image of the substrate to be inspected, wherein the first image of the substrate to be inspected includes a plurality of marking points. Determining size information of the substrate to be inspected based on the coordinate information of the plurality of marking points in the first image of the substrate to be inspected.

[0039] A marking point is a point used to mark the edge position of the substrate to be inspected. A marking point is also called a mark point. The number of marking points in the substrate to be inspected is usually 2 or more, such as 2, 3, 4, or 8. Figure 2 FIG. 4 is a schematic diagram of a substrate to be inspected including four marking points. Figure 2 As shown, the substrate to be inspected includes four marking points, namely, marking point 0, marking point 1, marking point 2, and marking point 3.

[0040] For example, the first image of the substrate to be inspected includes 4 marking points. By performing image recognition processing on the first image of the substrate to be inspected, the coordinate information of the 4 marking points in the first image of the substrate to be inspected can be obtained, for example, the coordinates of mark0 are (x=0, y=1000), the coordinates of mark1 are (x=1000, y=1000), the coordinates of mark2 are (x=1000, y=0), and the coordinates of mark3 are (x=0, y=0).

[0041] After determining the coordinate information of multiple marking points in the first image of the substrate to be inspected, the size information of the substrate to be inspected can be directly determined based on the coordinate information of the multiple marking points. For example, based on the coordinates of mark0 being (x=0, y=1000), the coordinates of mark1 being (x=1000, y=1000), the coordinates of mark2 being (x=1000, y=0), and the coordinates of mark3 being (x=0, y=0), it can be determined that the length of the substrate to be inspected is 1000 and the width is 1000.

[0042] The image recognition processing method for the first image of the substrate to be inspected may be, for example, various artificial intelligence image recognition processing methods, including but not limited to YOLO (You Only Look Once), R-CNN (Region-Convolutional Neural Networks), SSD (Single Shot MultiBox Detector) and other image recognition processing methods. Among them, the full name of YOLO is You Only Look Once, which is a deep learning algorithm for target detection. Its core idea is to solve the target detection task as a regression problem, and predict the bounding box and target category directly from the input image through a single convolutional neural network. The YOLO algorithm divides the input image into multiple grids, each of which is responsible for detecting the target falling within it. The full name of R-CNN is Region-Convolutional Neural Networks, which is the first algorithm that successfully applies deep learning to target detection. R-CNN implements target detection technology based on algorithms such as convolutional neural networks, linear regression and support vector machines. The full name of the SSD algorithm is Single ShotMultiBox Detector. Single Shot indicates that the SSD algorithm is a one-stage method, and MultiBox indicates that SSD is a multi-box prediction. The characteristics of SSD are: SSD extracts feature maps of different scales for detection. Large-scale feature maps can be used to detect small objects, while small feature maps are used to detect large objects. And SSD uses prior boxes of different scales and aspect ratios.

[0043] 2) Performing image recognition processing on the first image of the substrate to be inspected, and obtaining coordinate information of multiple marking points in the first image of the substrate to be inspected, wherein the first image of the substrate to be inspected includes multiple marking points. Determining size information of a range of marking points based on the coordinate information of the multiple marking points in the first image of the substrate to be inspected. Performing reduction processing on the size information of the range of marking points to obtain size information of the substrate to be inspected.

[0044] Following the previous example, take the example that the first image of the substrate to be inspected includes 4 marking points. By performing image recognition processing on the first image of the substrate to be inspected, the coordinate information of the 4 marking points in the first image of the substrate to be inspected can be obtained, for example, the coordinates of mark0 are (x=0, y=1000), the coordinates of mark1 are (x=1000, y=1000), the coordinates of mark2 are (x=1000, y=0), and the coordinates of mark3 are (x=0, y=0).

[0045] Since the location of the mark point is usually outside the pad area, the size information of the substrate to be inspected is usually smaller than the size information of the mark point range formed by the coordinate information of multiple mark points. For example, the size information of the mark point range formed by mark0 to mark3 is 1000 in length and 1000 in width. The size information of the mark point range is reduced, for example, the length of the substrate to be inspected can be 900 and the width can be 900.

[0046] In one embodiment, according to the image acquisition strategy corresponding to the size information of the substrate to be inspected, an image acquisition device is used to acquire an image of the substrate to be inspected to obtain one or more second images of the substrate to be inspected, including: An image acquisition strategy is determined according to the size information of the substrate to be inspected and the field of view information of the image acquisition device. Based on the image acquisition strategy, the image acquisition device is used to acquire images of the substrate to be inspected to obtain one or more second images of the substrate to be inspected.

[0047] Generally, the size of the substrate to be inspected is larger than the image acquisition field of view of the image acquisition device. Therefore, it is necessary to move the image acquisition device to comprehensively acquire the second image of each position in the substrate to be inspected. The field of view information of the image acquisition device generally includes the area information that can be covered by the image acquisition device in a single acquisition. The field of view information of the image acquisition device, for example, includes the area information of the image acquisition device. Continuing with the previous example, the length of the substrate to be inspected is 1000 and the width is 1000. It can be determined that the area information of the substrate to be inspected is 1000000. If the area information of the image acquisition device is 10000, it can be determined that the image acquisition strategy is to move the image acquisition device 100 times, so as to acquire images of the substrate to be inspected by the image acquisition device. The image acquisition strategy can also include the moving mode of the image acquisition device, and the moving mode of the image acquisition device includes but is not limited to the following two modes a and b. a. The image acquisition is performed step by step from the outside to the inside in a clockwise direction, with the side length of the image acquisition device as the moving distance each time. In the case where the field of view information of the image acquisition device is a square, the side length of the image acquisition device can be used as the distance of each movement. The image acquisition is performed step by step from the outside to the inside, specifically in a clockwise direction or a counterclockwise direction. The image acquisition strategy is to use the side length of the image acquisition device as the moving distance each time, and to gradually acquire images from the outside to the inside in a clockwise direction, which can minimize the total moving distance of the image acquisition device, and to perform comprehensive image acquisition of the substrate to be inspected as quickly as possible to obtain one or more second images in the substrate to be inspected. b. Use the side length of the image acquisition device as the moving distance each time, and perform image acquisition in a row-by-column manner. In the case where the field of view information of the image acquisition device is a square, the side length of the image acquisition device can be used as the distance of each movement. For example, starting from the upper left to the right, the side length of the image acquisition device is used as the moving distance each time, and all the second image information of the first row is acquired. Then the image acquisition device is moved to the second row, and moved from the leftmost to the right, and the side length of the image acquisition device is used as the moving distance each time, and all the second image information of the second row is acquired. And so on, until all the image acquisitions of the entire substrate to be inspected are completed, and all the second images in the substrate to be inspected are obtained. The image acquisition strategy is to use the side length of the image acquisition device as the moving distance each time, and perform image acquisition in a row-by-column manner, which can perform comprehensive image acquisition of the substrate to be inspected in a more orderly manner to obtain one or more second images in the substrate to be inspected.

[0048] In one embodiment, the size information of the substrate to be inspected includes the length information and the width information of the substrate to be inspected, and the field of view information of the image acquisition device includes the length information and the width information of the image acquisition device. According to the size information of the substrate to be inspected and the field of view information of the image acquisition device, an image acquisition strategy is determined, including: Determining the number of times the image acquisition device moves in the length direction according to the length information of the substrate to be inspected and the length information of the image acquisition device; Determining the number of times the image acquisition device moves in the width direction according to the width information of the substrate to be inspected and the width information of the image acquisition device; The image acquisition strategy is determined according to the number of times the image acquisition device moves in the length direction and the number of times the image acquisition device moves in the width direction.

[0049] The length information of the substrate to be inspected can be divided by the length information of the image acquisition device to determine the number of times the image acquisition device moves in the length direction; the width information of the substrate to be inspected can be divided by the width information of the image acquisition device to determine the number of times the image acquisition device moves in the width direction. The image acquisition strategy is determined based on the number of times the image acquisition device moves in the length direction and the number of times the image acquisition device moves in the width direction.

[0050] Continuing with the previous example, the size information of the substrate to be inspected includes the length of 1000 and the width of 1000; the field of view information of the image acquisition device includes the length of the image acquisition device of 50 and the width of 20. Then, through division operation, it can be determined that the number of times the image acquisition device moves in the length direction is 20 times and the number of times the image acquisition device moves in the width direction is 50 times, and this is determined as the image acquisition strategy.

[0051] Figure 3 It is a schematic diagram of capturing an image of a substrate to be inspected according to an embodiment of the present application.

[0052] like Figure 3 As shown, the red area is the substrate area to be detected. Figure 3 The 25 rectangular frames included in the figure are schematic diagrams of the image acquisition device acquiring images. According to the length information of the substrate to be inspected and the length information of the image acquisition device, it is determined that the number of times the image acquisition device moves in the length direction is 5 times; according to the width information of the substrate to be inspected and the width information of the image acquisition device, it is determined that the number of times the image acquisition device moves in the width direction is 5 times; therefore, the determined image acquisition strategy is that the number of times the image acquisition device moves in the length direction is 5 times and the number of times the image acquisition device moves in the width direction is 5 times.

[0053] Figure 4 It is a schematic diagram of capturing an image of a substrate to be inspected according to another embodiment of the present application.

[0054] like Figure 4 As shown, the red area is the substrate area to be detected. Figure 4The 56 rectangular frames included in the figure are schematic diagrams of the image acquisition device acquiring images. According to the length information of the substrate to be inspected and the length information of the image acquisition device, it is determined that the number of times the image acquisition device moves in the length direction is 7 times; according to the width information of the substrate to be inspected and the width information of the image acquisition device, it is determined that the number of times the image acquisition device moves in the width direction is 8 times; therefore, the determined image acquisition strategy is that the number of times the image acquisition device moves in the length direction is 7 times and the number of times the image acquisition device moves in the width direction is 8 times.

[0055] The present application can determine the number of times the image acquisition device moves in the length direction according to the length information of the substrate to be inspected and the length information of the image acquisition device, determine the number of times the image acquisition device moves in the width direction according to the width information of the substrate to be inspected and the width information of the image acquisition device, and determine the image acquisition strategy according to the number of times the image acquisition device moves in the length direction and the number of times the image acquisition device moves in the width direction. The present application can uniformly, comprehensively and accurately acquire all second images of the substrate to be inspected.

[0056] In one embodiment, according to the image acquisition strategy corresponding to the size information of the substrate to be inspected, an image acquisition device is used to acquire an image of the substrate to be inspected to obtain one or more second images of the substrate to be inspected, including: An image acquisition strategy is determined based on the size information of the substrate to be inspected, the field of view information of the image acquisition device, and the pad arrangement information. Based on the image acquisition strategy, the image acquisition device is used to acquire images of the substrate to be inspected to obtain one or more second images of the substrate to be inspected.

[0057] Here, the pad arrangement information includes but is not limited to the position information of the pad distribution. For example, if the pad arrangement is mainly distributed in the upper right position of the substrate to be detected, which occupies 80% of the area, then the image acquisition strategy can be determined based on the size information of the substrate to be detected, the field of view information of the image acquisition device, and the pad arrangement information to acquire the image of the substrate to be detected at the upper right position of 80% of the area. For another example, if the pad arrangement is mainly distributed in the middle position of the substrate to be detected, which occupies 80% of the area, then the image acquisition strategy can be determined based on the size information of the substrate to be detected, the field of view information of the image acquisition device, and the pad arrangement information to acquire the image of the substrate to be detected at the middle position of 80% of the area.

[0058] Figure 5 It is a schematic diagram of capturing an image of a substrate to be inspected according to another embodiment of the present application.

[0059] like Figure 5 As shown, the red area is the substrate area to be detected. Figure 5The 9 rectangular frames included in the figure are schematic diagrams of the image acquisition device capturing images. Since the pad arrangement information is that the pads are distributed in 9 areas of the substrate to be detected, namely, the upper left, upper middle, upper right, middle left, center, middle right, lower left, lower middle, and lower right, the image acquisition strategy determined by the present application is to capture images of the above 9 areas based on the size information of the substrate to be detected, the field of view information of the image acquisition device, and the pad arrangement information, which can more quickly, effectively, and comprehensively capture all the second images including the pads in the substrate to be detected, thereby improving the efficiency of image acquisition.

[0060] The present application determines an image acquisition strategy according to the size information of the substrate to be inspected, the field of view information of the image acquisition device and the pad arrangement information, and based on the image acquisition strategy, performs image acquisition on the substrate to be inspected through the image acquisition device to obtain one or more second images of the substrate to be inspected. This can more quickly, effectively and comprehensively acquire all second images of the substrate to be inspected including the pads, thereby improving the efficiency of image acquisition.

[0061] S13, performing image recognition processing on one or more second images of the substrate to be inspected, and obtaining pad information corresponding to one or more pads in the substrate to be inspected.

[0062] Here, one or more second images in the substrate to be inspected can be processed by artificial intelligence image recognition to obtain pad information corresponding to one or more pads in the substrate to be inspected. The artificial intelligence image recognition processing includes but is not limited to image recognition processing methods such as YOLO, R-CNN, and SSD. Among them, the full name of YOLO is You Only Look Once, and YOLO is a deep learning algorithm for target detection. Its core idea is to solve the target detection task as a regression problem, and predict the bounding box and target category directly from the input image through a single convolutional neural network. The YOLO algorithm divides the input image into multiple grids, each of which is responsible for detecting the target falling within it. The full name of R-CNN is Region-Convolutional Neural Networks, which is the first algorithm that successfully applies deep learning to target detection. R-CNN implements target detection technology based on algorithms such as convolutional neural networks, linear regression, and support vector machines. The full name of the SSD algorithm is Single Shot MultiBox Detector. Among them, SingleShot indicates that the SSD algorithm belongs to the one-stage method, and MultiBox indicates that SSD is a multi-box prediction. The characteristics of SSD are: SSD extracts feature maps of different scales for detection. Large-scale feature maps can be used to detect small objects, while small feature maps are used to detect large objects. In addition, SSD uses prior frames of different scales and aspect ratios.

[0063] The pad information corresponding to one or more pads in the substrate to be inspected includes, but is not limited to, pad center point coordinate information, pad area coordinate information, pad size information, and the like.

[0064] S14, determining a detection result of the substrate to be detected according to pad information corresponding to one or more pads in the substrate to be detected and pad information in one or more standard substrates.

[0065] Here, the standard substrate refers to a pre-stored substrate that meets the standards. The standard substrate can be stored in the form of a Gerber file, for example. Gerber file is a computer software, a document format set that describes the image and drilling and milling data of the circuit board (circuit layer, solder mask layer, character layer, etc.) in the circuit board industry. It is a standard format for image conversion in the circuit board industry.

[0066] The pad information corresponding to one or more pads in the substrate to be inspected is compared with the pad information in one or more standard substrates to determine the inspection result of the substrate to be inspected. The inspection result of the substrate to be inspected determined includes but is not limited to: the offset of the pad, the standard substrate with the smallest offset from the substrate to be inspected, etc. Optionally, when comparing the pad information corresponding to one or more pads in the substrate to be inspected with the pad information in one or more standard substrates, the center point of the substrate to be inspected is aligned with the center point of the one or more standard substrates.

[0067] The present application acquires a first image of a substrate to be detected, and according to an image acquisition strategy corresponding to the size information of the substrate to be detected, performs image acquisition on the substrate to be detected through an image acquisition device, obtains one or more second images of the substrate to be detected, performs image recognition processing on the one or more second images of the substrate to be detected, obtains pad information corresponding to one or more pads in the substrate to be detected, and then determines the detection result of the substrate to be detected according to the pad information corresponding to one or more pads in the substrate to be detected and the pad information in one or more standard substrates. The present application determines the detection result of the substrate to be detected based on multiple pad information at different positions of the substrate to be detected and the pad information of the standard substrate, which can more accurately determine the real expansion and contraction, more reliably determine the expansion and contraction of the substrate to be detected, ensure the stability and reliability of substrate detection, and the result is more valuable for reference. In addition, the present application solves the technical problem that other detection methods cannot meet the detection requirements of modern PCB boards. The present application can be applied to the sub-pixel light point arrangement application scenario of chip on board (COB), which can greatly reduce the cost for panel manufacturers in the industry.

[0068] In one embodiment, determining the inspection result of the substrate to be inspected according to pad information corresponding to one or more pads in the substrate to be inspected and pad information in one or more standard substrates includes: The offsets of each pad in the substrate to be inspected corresponding to each pad in each standard substrate are determined according to pad information corresponding to one or more pads in the substrate to be inspected and pad information in one or more standard substrates.

[0069] Here, for any standard substrate, the center point of the substrate to be detected can be aligned with the standard substrate. Then, according to the coordinates corresponding to the different pads in the substrate to be detected, the pad information of the pad corresponding to one coordinate in the substrate to be detected is compared point by point with the pad information of the pad corresponding to the same coordinate in the standard substrate to determine the offset of the pad in the substrate to be detected corresponding to the corresponding pad in the standard substrate. And in the same way, the pad information of the pad corresponding to other coordinates in the substrate to be detected is compared with the pad information of the pad corresponding to the corresponding coordinate in the standard substrate to determine the offset of each pad. After determining the offset of each pad in the substrate to be detected corresponding to each pad in a standard substrate in the above manner, determine the offset of each pad in the substrate to be detected corresponding to each pad in other standard substrates in the same way, until the offset of each pad in the substrate to be detected corresponding to each pad in each standard substrate is determined.

[0070] Optionally, when comparing pad information corresponding to one or more pads in the substrate to be inspected with pad information in one or more standard substrates, the center point of the substrate to be inspected is aligned with the center point of the one or more standard substrates.

[0071] The present application can determine the offset of each pad in the substrate to be detected corresponding to each pad in each standard substrate by comparing the pad information corresponding to one or more pads in the substrate to be detected with the pad information in one or more standard substrates, so that the offset and difference of each pad information in the substrate to be detected and the corresponding pad information in the standard substrate can be accurately detected, and the substrate to be detected can be compared with any standard substrate for expansion and contraction detection and the pad offset can be output. The substrate detection method of the present application takes into account global information and the results are more reliable. The present application can more accurately and reliably determine the expansion and contraction of the substrate to be detected, ensure the stability and reliability of substrate detection, and solve the technical problem that other detection methods cannot meet the detection needs of modern PCB boards.

[0072] In one embodiment, determining the inspection result of the substrate to be inspected according to pad information corresponding to one or more pads in the substrate to be inspected and pad information in one or more standard substrates includes: The detection result of the substrate to be detected is determined according to the offset amount and the offset reference amount of each pad in the substrate to be detected corresponding to each pad in each standard substrate, wherein the detection result of the substrate to be detected includes any one of the following items: a preferred standard substrate and no preferred standard substrate among the standard substrates.

[0073] After determining the offsets of each pad in the substrate to be inspected corresponding to each pad in each standard substrate, the comparison and matching of the substrate to be inspected and each standard substrate can be completed based on an artificial intelligence classification strategy algorithm. The comparison and matching algorithm includes but is not limited to: CNN (Convolutional Neural Network), MLP (Multilayer Perceptron), RNN (Recurrent Neural Network), LSTM (Long Short-Term Memory), GAN (Generative AdversarialNets), etc. And input the offset reference amount. If the offsets of all substrates to be inspected and each standard substrate exceed the offset reference amount, the substrate to be inspected is classified into the NG class (Not Good) with no preferred standard substrate. If the offset between the substrate to be inspected and a certain standard substrate is the smallest, the standard substrate is determined as the preferred standard substrate among the standard substrates. If there is only one standard substrate, the offset between the substrate to be inspected and the standard substrate is determined.

[0074] Among them, CNN is a deep learning model, which is mainly used to process data with grid structure, such as image data. CNN mainly consists of three parts: convolution layer, pooling layer and fully connected layer. The convolution layer extracts local features of input data by sliding window; the pooling layer is used to reduce the spatial dimension of features, reduce the amount of calculation and prevent overfitting; the fully connected layer classifies or regresses the extracted features. MLP is a feedforward artificial neural network, which consists of an input layer, one or more hidden layers and an output layer. MLP can handle complex pattern recognition and classification problems by learning the nonlinear relationship between input and output. MLP is usually trained using the back propagation algorithm to minimize the prediction error by continuously adjusting the weights. RNN is a type of recurrent neural network that takes sequence data as input, recurses in the direction of sequence evolution, and all nodes (recurrent units) are connected in a chain. LSTM is a time recurrent neural network specially designed to solve the long-term dependency problem of general recurrent neural networks. GAN is a deep learning model. The basic principle of GAN is to generate data that is indistinguishable from the real thing by letting two neural networks - the generator and the discriminator - compete with each other.

[0075] The present application determines the preferred standard substrate and the non-preferred standard substrate among the various standard substrates according to the offset amounts and offset reference amounts of the various pads in the substrate to be detected corresponding to the various standard substrates. The present application can compare the expansion and contraction detection of the substrate to be detected with any standard substrate, and intelligently classify the substrate to be detected into the preferred standard substrates among the various standard substrates. The expansion and contraction of the substrate to be detected can be determined more accurately and reliably, thereby ensuring the stability and reliability of substrate detection, and solving the technical problem that other detection methods cannot meet the detection requirements of modern PCB boards.

[0076] In one embodiment, determining the inspection result of the substrate to be inspected according to pad information corresponding to one or more pads in the substrate to be inspected and pad information in one or more standard substrates includes: According to the offset of each pad in the substrate to be inspected corresponding to each pad in each standard substrate, the inspection result of each area of ​​the substrate to be inspected is determined, wherein the inspection result of each area of ​​the substrate to be inspected includes the comprehensive offset of the pad information of multiple pads in each area of ​​the substrate to be inspected relative to the pad information of corresponding multiple pads in the corresponding area of ​​each standard substrate.

[0077] LED display modules are usually formed by transferring and welding LED light-emitting chips to pads on the surface of the substrate using PCB (Printed Circuit Board) or transparent glass as substrates. For PCB, due to its material properties, it is easy to expand and shrink during the production and manufacturing process of LED modules, such as the process of welding LED light-emitting chips, which affects the quality of the product and may even cause the product to be scrapped. Due to temperature changes during the welding process, the expansion and contraction of different areas of the substrate to be tested may be different. Therefore, the present application can perform statistical analysis on different areas according to the offset of each pad in the substrate to be tested corresponding to each pad in each standard substrate, and determine the detection results of each area of ​​the substrate to be tested, such as the comprehensive offset of the pad information of multiple pads in the upper left area of ​​the substrate to be tested relative to the pad information of the corresponding multiple pads in the upper left area of ​​each standard substrate, and the comprehensive offset of the pad information of multiple pads in the middle area of ​​the substrate to be tested relative to the pad information of the corresponding multiple pads in the middle area of ​​each standard substrate. By evaluating and calculating the comprehensive offset of the pad information of multiple pads in each area of ​​the substrate to be inspected relative to the pad information of the corresponding multiple pads in the corresponding area of ​​each standard substrate in a region-by-region manner, the inspection results of each area of ​​the substrate to be inspected can be determined more accurately, and the calculation results can be obtained with more precision and finer granularity. The expansion and contraction of the substrate to be inspected can be determined more accurately and reliably, ensuring the stability and reliability of substrate inspection, and solving the technical problem that other inspection methods cannot meet the requirements of modern PCB board inspection.

[0078] Figure 6 It is a flow chart of a substrate detection method provided in an application embodiment of the present application.

[0079] S611: Capture an image of the substrate to be inspected to obtain a first image of the substrate to be inspected.

[0080] S6121: Using artificial intelligence (AI) to detect a first image of the substrate to be inspected, obtain coordinate information of a mark point of the substrate to be inspected.

[0081] S6122: Use artificial intelligence (AI) to detect and obtain the pad coordinate information and pad size information of the substrate position 1 to be detected. Similarly, use artificial intelligence (AI) to detect and obtain the pad coordinate information and pad size information of the substrate positions 2 to M-1 to be detected. S612M: Use artificial intelligence (AI) to detect and obtain the pad coordinate information and pad size information of the substrate position M to be detected.

[0082] S613: Obtain the mark points of the substrate to be inspected, the spatial coordinates of all pad points, and the pad size.

[0083] S614: Acquire the center point of the substrate to be inspected.

[0084] S621: Standard substrate library analysis.

[0085] S6221: Obtain the mark point coordinate information, all pad coordinate information, pad size information, and pad arrangement information of standard substrate 1. Similarly, obtain the mark point coordinate information, all pad coordinate information, pad size information, and pad arrangement information of standard substrate 2 to standard substrate N-1 respectively. S622N: Obtain the mark point coordinate information, all pad coordinate information, pad size information, and pad arrangement information of standard substrate N.

[0086] S623: Obtain the center point information of each standard substrate.

[0087] Those skilled in the art should understand that the above steps S611 to S614 and steps S621 to S623 can be performed simultaneously or sequentially. Any sequential execution of steps S611 to S614 and steps S621 to S623 falls within the protection scope of this application.

[0088] S63: Align the center of the substrate to be inspected with the center of each standard substrate.

[0089] S64: Calculate the offset of the mark point and each pad in the substrate to be inspected and the standard substrate.

[0090] S650, input the offset reference amount.

[0091] S651: Based on all pad offsets and each pad position information of standard substrate 1; and so on, based on all pad offsets and each pad position information of standard substrate N, confirm the best matching substrate based on artificial intelligence (AI), that is, the preferred standard substrate among all standard substrates.

[0092] S652: Determine the offset between the substrate to be inspected and each type of standard substrate.

[0093] S661: Determine whether the offset between the substrate to be inspected and each type of standard substrate is within the offset reference amount.

[0094] S662: If the offset between the substrate to be inspected and any type of standard substrate is not within the offset reference amount, the output is NG (Not Good), that is, there is no preferred standard substrate.

[0095] S663: If the offset between the substrate to be inspected and a certain standard substrate is the smallest and within the offset reference amount, the standard substrate is output as the best matching standard substrate, that is, the preferred standard substrate among all standard substrates.

[0096] Figure 7 It is a structural schematic diagram of a substrate detection device provided in one embodiment of the present application.

[0097] like Figure 7 As shown, the substrate detection device 7 includes: A first image acquisition module 71, used to acquire a first image of the substrate to be inspected; A second image acquisition module 72 is used to acquire an image of the substrate to be inspected by an image acquisition device according to an image acquisition strategy corresponding to the size information of the substrate to be inspected, so as to acquire one or more second images of the substrate to be inspected, wherein the size information of the substrate to be inspected is determined according to the coordinate information of multiple marking points in the first image of the substrate to be inspected; A pad information obtaining module 73 is used to perform image recognition processing on one or more second images of the substrate to be inspected, and obtain pad information corresponding to one or more pads in the substrate to be inspected; The detection result determination module 74 is used to determine the detection result of the substrate to be detected according to the pad information corresponding to one or more pads in the substrate to be detected and the pad information in one or more standard substrates.

[0098] Another embodiment of the present invention discloses a substrate detection device 7. Figure 7 Based on the corresponding embodiment, the second image acquisition module 72 is used for: Determining an image acquisition strategy according to the size information of the substrate to be inspected and the field of view information of the image acquisition device; Based on the image acquisition strategy, an image acquisition device is used to acquire images of the substrate to be inspected, so as to obtain one or more second images of the substrate to be inspected.

[0099] Another embodiment of the present invention discloses a substrate detection device 7. Figure 7 On the basis of the corresponding embodiment, the size information of the substrate to be detected includes the length information and the width information of the substrate to be detected, the field of view information of the image acquisition device includes the length information and the width information of the image acquisition device, and the second image acquisition module 72 is used for: Determining the number of times the image acquisition device moves in the length direction according to the length information of the substrate to be inspected and the length information of the image acquisition device; Determining the number of times the image acquisition device moves in the width direction according to the width information of the substrate to be inspected and the width information of the image acquisition device; An image acquisition strategy is determined according to the number of times the image acquisition device moves in the length direction and the number of times the image acquisition device moves in the width direction.

[0100] Another embodiment of the present invention discloses a substrate detection device 7. Figure 7 Based on the corresponding embodiment, the second image acquisition module 72 is further used for: An image acquisition strategy is determined according to the size information of the substrate to be inspected, the field of view information of the image acquisition device and the pad arrangement information.

[0101] Another embodiment of the present invention discloses a substrate detection device 7. Figure 7 On the basis of the corresponding embodiment, the substrate detection device 7 further includes: The size information determination module is used to perform image recognition processing on the first image of the substrate to be inspected, obtain coordinate information of multiple marking points in the first image of the substrate to be inspected, wherein the first image of the substrate to be inspected includes multiple marking points; and determine the size information of the substrate to be inspected according to the coordinate information of the multiple marking points in the first image of the substrate to be inspected.

[0102] Another embodiment of the present invention discloses a substrate detection device 7. Figure 7 On the basis of the corresponding embodiment, the size information determination module is further used to determine the size information of the marking point range according to the coordinate information of multiple marking points in the first image of the substrate to be inspected; and to reduce the size information of the marking point range to obtain the size information of the substrate to be inspected.

[0103] Another embodiment of the present invention discloses a substrate detection device 7. Figure 7 Based on the corresponding embodiment, the detection result determination module 74 is used to: According to the offset of each pad in the substrate to be inspected corresponding to each pad in each standard substrate, the inspection result of each area of ​​the substrate to be inspected is determined, wherein the inspection result of each area of ​​the substrate to be inspected includes the comprehensive offset of the pad information of multiple pads in each area of ​​the substrate to be inspected relative to the pad information of corresponding multiple pads in the corresponding area of ​​each standard substrate.

[0104] Another embodiment of the present invention discloses a substrate detection device 7. Figure 7 Based on the corresponding embodiment, the detection result determination module 74 is used to: The offsets of each pad in the substrate to be inspected corresponding to each pad in each standard substrate are determined according to pad information corresponding to one or more pads in the substrate to be inspected and pad information in one or more standard substrates.

[0105] Another embodiment of the present invention discloses a substrate detection device 7. Figure 7 Based on the corresponding embodiment, the detection result determination module 74 is used to: The detection result of the substrate to be detected is determined according to the offset amount and the offset reference amount of each pad in the substrate to be detected corresponding to each pad in each standard substrate, wherein the detection result of the substrate to be detected includes any one of the following items: a preferred standard substrate and no preferred standard substrate among the standard substrates.

[0106] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0107] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0108] The present application also provides a terminal device, such as Figure 8 As shown, the terminal device 8 includes: at least one processor 80, a memory 81, and a computer program 82 stored in the memory 81 and executable on the at least one processor 80, and when the processor 80 executes the computer program 82, the steps in any of the above-mentioned method embodiments are implemented.

[0109] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0110] An embodiment of the present application provides a computer program product. When the computer program product runs on a terminal device, the terminal device can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0111] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0112] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0113] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0114] In the embodiments provided in the present application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0115] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0116] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A substrate detection method, characterized in that: include: Acquire a first image of a substrate to be inspected; According to the image acquisition strategy corresponding to the size information of the substrate to be inspected, an image acquisition device is used to acquire an image of the substrate to be inspected, so as to obtain one or more second images of the substrate to be inspected, wherein the size information of the substrate to be inspected is determined according to the coordinate information of multiple marking points in the first image of the substrate to be inspected; Performing image recognition processing on one or more second images of the substrate to be inspected to obtain pad information corresponding to one or more pads in the substrate to be inspected; The inspection result of the substrate to be inspected is determined according to the pad information respectively corresponding to one or more pads in the substrate to be inspected and the pad information in one or more standard substrates.

2. The substrate detection method according to claim 1, characterized in that: The method of acquiring an image of the substrate to be inspected by an image acquisition device according to the image acquisition strategy corresponding to the size information of the substrate to be inspected to obtain one or more second images of the substrate to be inspected includes: Determining an image acquisition strategy according to the size information of the substrate to be inspected and the field of view information of the image acquisition device; Based on the image acquisition strategy, an image acquisition device is used to acquire images of the substrate to be inspected, so as to obtain one or more second images of the substrate to be inspected.

3. The substrate detection method according to claim 2, characterized in that: The size information of the substrate to be inspected includes length information and width information of the substrate to be inspected, the field of view information of the image acquisition device includes length information and width information of the image acquisition device, and determining the image acquisition strategy according to the size information of the substrate to be inspected and the field of view information of the image acquisition device includes: Determining the number of times the image acquisition device moves in the length direction according to the length information of the substrate to be inspected and the length information of the image acquisition device; Determining the number of times the image acquisition device moves in the width direction according to the width information of the substrate to be inspected and the width information of the image acquisition device; An image acquisition strategy is determined according to the number of times the image acquisition device moves in the length direction and the number of times the image acquisition device moves in the width direction.

4. The substrate detection method according to claim 2, characterized in that: The determining of the image acquisition strategy according to the size information of the substrate to be inspected and the field of view information of the image acquisition device also includes: An image acquisition strategy is determined according to the size information of the substrate to be inspected, the field of view information of the image acquisition device and the pad arrangement information.

5. The substrate detection method according to claim 1, characterized in that: The size information of the substrate to be inspected is determined based on the following steps: Performing image recognition processing on the first image of the substrate to be inspected to obtain coordinate information of a plurality of marking points in the first image of the substrate to be inspected, wherein the first image of the substrate to be inspected includes a plurality of marking points; The size information of the substrate to be inspected is determined according to the coordinate information of a plurality of marking points in the first image of the substrate to be inspected.

6. The substrate detection method according to claim 5, characterized in that: The step of determining the size information of the substrate to be inspected according to the coordinate information of a plurality of marking points in the first image of the substrate to be inspected comprises: Determine size information of a range of the marking points according to coordinate information of a plurality of marking points in the first image of the substrate to be inspected; The size information of the marking point range is reduced to obtain the size information of the substrate to be inspected.

7. The substrate detection method according to claim 1, characterized in that: The step of determining the inspection result of the substrate to be inspected according to the pad information respectively corresponding to one or more pads in the substrate to be inspected and the pad information in one or more standard substrates comprises: According to the offset of each pad in the substrate to be inspected corresponding to each pad in each standard substrate, the inspection result of each area of ​​the substrate to be inspected is determined, wherein the inspection result of each area of ​​the substrate to be inspected includes the comprehensive offset of the pad information of multiple pads in each area of ​​the substrate to be inspected relative to the pad information of corresponding multiple pads in the corresponding area of ​​each standard substrate.

8. A substrate detection device, characterized in that: include: A first image acquisition module, used to acquire a first image of the substrate to be inspected; a second image acquisition module, configured to acquire an image of the substrate to be inspected by an image acquisition device according to an image acquisition strategy corresponding to the size information of the substrate to be inspected, so as to acquire one or more second images of the substrate to be inspected, wherein the size information of the substrate to be inspected is determined according to the coordinate information of a plurality of marking points in the first image of the substrate to be inspected; A pad information acquisition module, used to perform image recognition processing on one or more second images of the substrate to be detected, and obtain pad information corresponding to one or more pads in the substrate to be detected; The detection result determination module is used to determine the detection result of the substrate to be detected according to the pad information corresponding to one or more pads in the substrate to be detected and the pad information in one or more standard substrates.

9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images