Copper-clad plate glue sealing area identification method and device, storage medium and equipment

Abstract

The invention provides a copper-clad plate glue sealing area identification method and device, a storage medium and equipment. The method comprises the following steps: acquiring an acquisition image set of a copper-clad plate; splicing the collected image set according to a preset sequence to obtain a complete copper-clad plate image; inputting the complete copper-clad plate image into a trained U-Net model to obtain initial contour information of a sealing area; performing color space conversion on the initial contour information of the sealing glue area, and inputting the initial contour information into a hierarchical structure analysis model to obtain a sealing glue area contour set; and if no sub-contour exists in any contour in the sealant region contour set, outputting sealant region contour information. Through the combination of the trained U-Net, color space conversion and an analytic hierarchy process structure, the glue sealing area of the copper-clad plate is identified, the measurement efficiency of the glue sealing area in the printed circuit board is improved, and the identification accuracy of the glue sealing area is improved.

Description

Technical Field

[0001] The present invention relates to the field of industrial detection, and in particular to a method, a device, a storage medium and equipment for identifying a sealing area of ​​a copper clad plate. Background Art

[0002] Copper clad laminate sealing is a process used in the circuit board manufacturing process, mainly to protect the components and circuits on the circuit board from environmental factors (such as humidity, dust, etc.) and improve the reliability and service life of the circuit board. Sealing materials usually have good insulation, heat resistance and chemical stability, which can ensure that the circuit board can work stably in various environments.

[0003] In order to optimize the process, verify the design and check the quality of the glue sealing area on the copper clad laminate, it is necessary to measure the glue sealing area on the copper clad laminate. In the prior art, manual measurement and semi-automatic measurement are often used to measure the glue sealing area on the copper clad laminate. Figure 1 As shown in the figure, manual measurement requires operators to repeatedly mark points on the edge of the sealing area and draw the edge of the sealing area into a polygon for measurement. However, manual measurement takes a long time. It takes ten minutes to mark the edge of the sealing area of ​​a sample. The efficiency is low and the repeatability of the sample is also low. Semi-automatic measurement combines traditional visual algorithms to detect the edge of the sealing area and obtain the final measurement area after threshold filtering. However, the edge of the sealing area is prone to misjudgment and missed judgment, as shown in the attached figure. Figure 2 As shown, there is an error in the measured sealing area, and the sealing area needs to be corrected through manual calibration. Summary of the invention

[0004] Based on this, the present invention provides a method, device, storage medium and equipment for identifying the sealing area of ​​a copper clad laminate, which identifies the sealing area of ​​the copper clad laminate through the combination of trained U-Net, color space conversion and hierarchical analysis structure, thereby improving the measurement efficiency of the sealing area in the printed circuit board and improving the recognition accuracy of the sealing area.

[0005] In a first aspect, the present invention provides a method for identifying a sealing area of ​​a copper clad laminate, characterized by comprising:

[0006] Get a collection of images of the copper clad laminate;

[0007] The collected image set is spliced ​​in a preset order to obtain a complete copper clad laminate image;

[0008] Input the complete copper clad laminate image into the trained U-Net model to obtain initial contour information of the sealing area;

[0009] The initial contour information of the sealing area is converted into a color space and then input into a hierarchical structure analysis model to obtain a sealing area contour set;

[0010] If no sub-contour exists for any contour in the sealing area contour set, the sealing area contour information is output.

[0011] Furthermore, the copper clad laminate sealing area identification method further includes:

[0012] If any contour in the sealing area contour set has a sub-contour, the sub-contour is filled, and the sealing area contour set after the sub-contour is filled is input into the hierarchical structure analysis model again until any contour in the sealing area contour set has no sub-contour.

[0013] Furthermore, the copper clad laminate sealing area identification method further includes:

[0014] The area of ​​the sealing region is obtained according to the sealing region contour set.

[0015] Furthermore, the initial contour information of the sealing area is converted into a color space and then input into a hierarchical structure analysis model to obtain a sealing area contour set, specifically:

[0016] Converting the initial contour information of the sealing area from the RGB space to the HSV space, and obtaining the mask information of the sealing area;

[0017] The mask information of the sealing area is input into the hierarchical structure analysis model to obtain a sealing area contour set.

[0018] Furthermore, the specific expression for converting the initial contour information of the sealing area from the RGB space to the HSV space is:

[0019] ,

[0020] ,

[0021] ;

[0022] The specific expression of the mask information of the sealing area is:

[0023] ,

[0024] in, is the hue of the pixel, is the angle value of the pixel point, ranging from [0° to 360°], is the saturation of the pixel, is the brightness of the pixel, is the red channel intensity of the pixel, is the green channel intensity of the pixel, is the blue channel intensity of the pixel, Pixel The mask information, Pixel The color tone, is the minimum hue value of the pixel, is the maximum value of the pixel’s hue, Pixel The saturation of is the minimum saturation value of the pixel, is the maximum saturation value of the pixel, Pixel The brightness, is the minimum brightness of the pixel, is the maximum brightness of the pixel.

[0025] Furthermore, the mask information of the sealing area is input into the hierarchical structure analysis model to obtain the specific expression of the sealing area contour set:

[0026] ,

[0027] Among them, C is the contour set of the sealing area.

[0028] In a second aspect, the present invention further provides a copper clad laminate sealing region identification device, comprising:

[0029] An image acquisition module, used to obtain a collection of images of the copper clad laminate;

[0030] An image stitching module is used to stitch the collected image set in a preset order to obtain a complete copper clad laminate image;

[0031] A contour recognition module is used to input the complete copper clad laminate image into the trained U-Net model to obtain initial contour information of the sealing area;

[0032] A contour inspection module, used for converting the initial contour information of the sealing area into a color space and inputting the converted information into a hierarchical structure analysis model to obtain a set of contours of the sealing area;

[0033] The contour output module is used to output the contour information of the sealing area if no sub-contour exists in any contour in the sealing area contour set.

[0034] Furthermore, the copper clad laminate sealing area identification device also includes:

[0035] The contour correction module is used to fill the sub-contour if any contour in the sealing area contour information has a sub-contour, and input the sealing area contour set after the sub-contour is filled into the hierarchical structure analysis model again until no sub-contour exists in any contour in the sealing area contour set.

[0036] In a third aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of any one of the copper clad laminate sealing area identification methods in the first aspect are implemented.

[0037] In a fourth aspect, the present invention further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it executes any one of the copper clad laminate sealing area identification methods in the first aspect.

[0038] The beneficial effects of adopting the above technical solution are as follows: this embodiment obtains complete copper clad laminate image information through an acquisition device including a super depth of field structure, and processes the copper clad laminate image information in combination with a comprehensive model of U-Net, HSV space and hierarchical structure analysis model, accurately identifies the contour set of the sealing area on the copper clad laminate, and thus efficiently and accurately measures the area of ​​the sealing area. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art are briefly introduced below.

[0040] Figure 1 This is a schematic diagram of the manual measurement and marking of points in the prior art in one embodiment of the present application;

[0041] Figure 2 This is a schematic diagram of the prior art semi-automatic edge measurement that is prone to missed or misjudged in one embodiment of the present application;

[0042] Figure 3 This is a schematic diagram of a copper clad laminate including a sealing area in one embodiment of the present application;

[0043] Figure 4 This is a schematic diagram of a copper clad laminate structure including a sealing area in one embodiment of the present application;

[0044] Figure 5 This is a schematic diagram of a method for identifying a sealing area of ​​a copper clad laminate in one embodiment of the present application;

[0045] Figure 6 This is a schematic flow chart of a method for identifying a sealing area of ​​a copper clad laminate in one embodiment of the present application;

[0046] Figure 7This is a schematic diagram of a collection device in one embodiment of the present application;

[0047] Figure 8 This is a schematic diagram of the U-Net model structure in one embodiment of the present application;

[0048] Fig. 9 This is a schematic diagram of the initial outline of the sealing area in one embodiment of the present application;

[0049] Fig.10 This is a schematic diagram of an initial outline of a sealing area after color space conversion in one embodiment of the present application;

[0050] Fig.11 A schematic diagram of a sub-contour included in a sealing area contour set in one embodiment of the present application;

[0051] Fig.12 A schematic diagram showing that a sealing area contour set does not include a sub-contour in one embodiment of the present application;

[0052] Fig.13 This is a schematic diagram of the integrated model package in Analysis Pro in a copper clad laminate sealing region identification method in one embodiment of the present application;

[0053] Fig.14 Schematic diagram of a copper clad laminate sealing area identification device in one embodiment of the present application. DETAILED DESCRIPTION

[0054] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. In order to explain the present invention in more detail, the copper clad laminate sealing area identification method, device, storage medium and equipment provided by the present invention are specifically described below in combination with the drawings.

[0055] Unless otherwise defined, the technical terms or scientific terms used in the disclosure of this application should be understood by people with ordinary skills in the field to which the present invention belongs. The "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. Similarly, similar words such as "one", "one" or "the" do not indicate a quantitative limit, but indicate that there is at least one. Similar words such as "include" or "include" mean that the elements or objects appearing in front of the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. Similar words such as "connect" or "connected" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship can also change accordingly.

[0056] Circuit board sealants can prevent moisture or corrosive chemicals and gases in the air from corroding circuits, especially circuit board components and circuit board lines; in addition, sealants can also prevent mechanical shock and vibration, support and cushion delicate or fragile components, such as ferrites in transformer cores, and support circuit board pins and relieve most of the stress, so that the connection strength between the pins and the circuit board does not only rely on the solder joints.

[0057] The image of the copper clad board after sealing is as shown in the attached figure. Figure 3 and attached Figure 4 As shown, the inner circle area of ​​the copper clad laminate after sealing is equivalent to the printed circuit area of ​​the copper clad laminate, and the target area is the sealing area. The stability of the printed circuit on the copper clad laminate can be judged by measuring the sealing area. For example, it can be judged whether the sealing area evenly covers the printed circuit area of ​​the copper clad laminate to determine whether the printed circuit is fully protected, and the parameter settings of the dispensing machine (including dispensing speed, pressure, etc.) can be adjusted according to the actual area of ​​the sealing area to improve the efficiency and quality of copper clad laminate sealing.

[0058] In this regard, the present invention provides a copper clad laminate sealing area recognition method, which combines U-Net, color space conversion and hierarchical analysis structure to identify the sealing area of ​​the copper clad laminate, thereby improving the measurement efficiency of the sealing area in the printed circuit board and improving the recognition accuracy of the sealing area. Figure 5 The schematic diagram of the copper clad laminate sealing area identification method and the attached Figure 6 A schematic flow chart of a method for identifying a copper clad laminate sealing region is shown.

[0059] The embodiment of the present application provides an application scenario of the copper clad laminate sealing region identification method, and the application scenario includes the terminal device provided in the embodiment, and the terminal device includes but is not limited to a smart phone and a computer device, wherein the computer device can be at least one of a desktop computer, a portable computer, a laptop computer, a mainframe computer, a tablet computer, etc. The user operates the terminal device to obtain the contour information of the copper clad laminate sealing region. For the specific process, please refer to the embodiment of the copper clad laminate sealing region identification method.

[0060] In addition, the implementation of the copper clad laminate sealing area identification method in the embodiment of the present application requires obtaining the image information of the copper clad laminate through a collection device including a super depth of field and a metallographic microscope. The collection device cooperates with the annular lighting component so that a clear outline can be seen at the imaging source. Among them, the collection device includes a super depth of field digital microscope, which fuses the images of different depths of field into an ultra-large depth of field image, while realizing high-magnification detail observation of traditional optical microscopes, and can also perform a large depth of field comprehensive observation of the sample; and the collection device is provided with a zoom lens body to achieve a conversion from 50 times to 5800 times, ensuring a long working distance to avoid collision with the sample, so that a long working distance and a wide range of switching magnifications can be achieved in one lens body; further with a swingable observation head, it can achieve multi-angle panoramic observation of the sample.

[0061] In this embodiment, as shown in the attached Figure 7 As shown, the specific specifications of the above-mentioned acquisition equipment are: the total magnification is in the range of 50x to 11600x, the field of view range is 8.93mm-0.09mm, the working distance is 10mm, the Z-axis travel distance of the high-precision mirror frame is 50mm, the Z-axis travel distance of the swing mirror frame is 50mm, and the electric Z-axis travel distance is 30mm.

[0062] Based on the above acquisition equipment, the steps of the copper clad laminate sealing area recognition method in this embodiment are as follows:

[0063] Step S101, obtaining a set of collected images of a copper clad laminate.

[0064] Specifically, since the image acquisition range of the acquisition device is limited, the image acquired by the acquisition device at a single time only includes a partial area of ​​the copper clad laminate. The acquisition device needs to acquire images of different sub-areas of the copper clad laminate for multiple times to piece together a complete copper clad laminate image. In this embodiment, the acquisition image set is an image set of multiple sub-areas in the copper clad laminate acquired by the acquisition device within a set time period.

[0065] Step S102, splicing the collected image set according to a preset order to obtain a complete copper clad laminate image.

[0066] Specifically, in this embodiment, the acquisition device can acquire the image acquisition sequence and position information of the copper clad laminate by splicing the acquired image set to obtain a complete copper clad laminate image.

[0067] In addition to stitching the acquired images according to the acquisition order and position information in the above step S102, key points and descriptors in the acquired image set can also be extracted through algorithms such as SIFT (Scale-Invariant Feature Transform) or SURF (Speed ​​Up Robust Features), and matching points can be found by comparing key points between different images to achieve stitching of the acquired image set.

[0068] Step S103, inputting the complete copper clad laminate image into the trained U-Net model to obtain initial contour information of the sealing area.

[0069] Specifically, combined with Figure 8 As shown in FIG. 1 , the U-Net model is a neural network including upsampling (Decoder) and downsampling (Encoder), which is used to learn image content, restore image position information, and finally generate a segmented image result. In this embodiment, the U-Net model is used to identify the contour information of the sealing area. Figure 8 The left half of the image is composed of two 3×3 convolutional layers (ReLU) and a 2×2 maximum pooling layer (maxpooling). The downsampling part is mainly used to understand the content of the complete copper clad plate image, but the position information of the complete copper clad plate image is discarded; the upsampling part (i.e., the attached Figure 8 The right half of the image is composed of a convolutional layer, feature concatenation (concat) and two 3×3 convolutional layers (ReLU) repeatedly. The upsampling part is mainly used to combine the downsampling part's understanding of the image content and restore the image's position information.

[0070] The U-Net model of this embodiment can be obtained by training the complete copper clad laminate sample image after marking the sealing area, and in the case of using an ultra-depth of field acquisition device in this embodiment, the image accuracy of the obtained complete copper clad laminate image is relatively high. Therefore, the U-Net model training of this application does not require a large number of samples for training. Only 5-10 complete copper clad laminate sample images are needed to complete the training of the U-Net model and obtain the trained U-Net model.

[0071] The initial contour information of the sealing area obtained by the U-Net model includes the sealing area range and the edge lines of the sealing area, as shown in the attached figure. Fig. 9 shown.

[0072] Step S104 , converting the initial contour information of the sealing area into a color space and inputting the converted information into a hierarchical structure analysis model to obtain a sealing area contour set.

[0073] Specifically, the initial contour information of the sealing area obtained by the U-Net model still has some fuzzy details that need further inspection, so the color space conversion and hierarchical structure analysis model are introduced, specifically:

[0074] Step S201 : converting the initial contour information of the sealing area from the RGB space to the HSV space, and obtaining the mask information of the sealing area.

[0075] Among them, as attached Fig.10 As shown, this embodiment can better segment the target area and improve the accuracy of edge detection enhancement by converting the initial contour information of the sealing area from the RGB space to the HSV space. The specific expression for converting each pixel point in the initial contour information of the sealing area from the RGB space to the HSV space is:

[0076] ,

[0077] ,

[0078] ,

[0079] in, The hue of the pixel, indicating the position of the color spectrum, usually expressed as an angle value express, The range is from 0° to 360°; The saturation of the pixel refers to the purity or intensity of the pixel color, that is, the proportion of gray components in the color. When the saturation is 0%, the color of the pixel becomes gray, and when the saturation is 100%, the color of the pixel is the brightest. The brightness of the pixel point ranges from 0% to 100%, where 0% means the pixel point is black and 100% means the pixel point has the highest brightness; is the red channel intensity of the pixel, ranging from 0 to 255; is the green channel intensity of the pixel, ranging from 0 to 255; The blue channel intensity of the pixel, ranging from 0 to 255.

[0080] The mask information of the sealing area is:

[0081] ,

[0082] in, Pixel The mask information, Pixel The color tone, is the minimum hue value of the pixel, is the maximum value of the pixel’s hue, Pixel The saturation of is the minimum saturation value of the pixel, is the maximum saturation value of the pixel, Pixel The brightness, is the minimum brightness of the pixel, is the maximum brightness of the pixel.

[0083] Step S202: inputting the mask information of the sealing area into a hierarchical structure analysis model to obtain a sealing area contour set.

[0084] The hierarchical structure analysis model in step S202 is specifically a contour detection model in OPENCV, and the cv.findContours() function is used to find the contour set of the sealing area in the mask information of the sealing area. The specific expression of the contour set of the sealing area is:

[0085] ,

[0086] Among them, C is the contour set of the sealing area.

[0087] It should be noted that the sealing area contour set obtained by the cv2.RETR_EXTERNAL flag of OPENCV's cv.findContours() function includes a parent contour matrix and a child contour matrix, where the relationship between the parent contour matrix and the child contour matrix is ​​as follows:

[0088] ,

[0089] ,

[0090] in, It is the hierarchical relationship between any contour in the sealing area contour set and other contours. Outline of the sealing area The next contour at the same level, Outline of the sealing area The previous contour at the same level, Outline of the sealing area The first subcontour of Outline of the sealing area The parent contour.

[0091] Step S105 : if any contour in the sealing area contour set does not have a sub-contour, output the sealing area contour set.

[0092] Specifically, based on the hierarchical relationship in the above-mentioned sealing area contour set information When it is determined that the obtained sealing area contour set does not contain any sub-contours, it means that the obtained sealing area contour set has a high credibility, and the sealing area contour set can be directly output.

[0093] Step S106, if any contour in the sealing area contour set has a sub-contour, fill the sub-contour, and input the sealing area contour set filled with sub-contours into the hierarchical structure analysis model again, until no contour in the sealing area contour set has a sub-contour.

[0094] Specifically, based on the hierarchical relationship in the above-mentioned sealing area contour set information If the sealing area contour set contains sub-contours, it means that there are some missed judgments in the current sealing area contour set, as shown in the attached figure. Fig.11 As shown in the figure, at this time, it is necessary to refill the sub-contours and analyze the hierarchical structure of the sealing area contour set again until there are no sub-contours (that is, no missed judgment phenomenon) and then output the sealing area contour set, as shown in the attached figure. Fig.12 shown.

[0095] Step S107 , obtaining the area of ​​the sealing region according to the sealing region contour set.

[0096] Furthermore, the area of ​​the sealing area can be directly calculated based on the sealing area contour set. The calculation process can be implemented by calling the cv.contouArea() function in OPENCV, or other methods can be used to calculate the area of ​​the sealing area, which is not limited in this embodiment.

[0097] This embodiment uses a collection device with a super depth of field structure to obtain complete copper clad laminate image information, and combines the comprehensive model of U-Net, HSV space and hierarchical structure analysis model to process the copper clad laminate image information, accurately identify the contour set of the sealing area on the copper clad laminate, and thus measure the area of ​​the sealing area efficiently and accurately. And the comprehensive model of this embodiment can be integrated in LibTorch of PyTorch and directly called, as shown in the attached Fig.13 As shown, it does not need to rely on network connection and can be used efficiently after encapsulation without other calling interfaces.

[0098] It should be understood that although the Figure 5The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Figure 5 At least part of the steps may include multiple sub-steps or sub-stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0099] The above embodiments of the present invention describe in detail the copper clad laminate sealing glue area recognition method. The above methods disclosed in the present invention can be implemented by various forms of equipment. Therefore, the present invention also discloses a copper clad laminate sealing glue area recognition device. Fig.14 , specific embodiments are given below to explain in detail.

[0100] An image acquisition module 301 is used to acquire a collection of images of the copper clad laminate;

[0101] An image stitching module 302 is used to stitch the collected image set in a preset order to obtain a complete copper clad laminate image;

[0102] Contour recognition module 303, used for inputting the complete copper clad laminate image into the trained U-Net model to obtain initial contour information of the sealing area;

[0103] The contour inspection module 304 is used to convert the initial contour information of the sealing area into a color space and then input it into a hierarchical structure analysis model to obtain a set of contours of the sealing area;

[0104] The contour output module 305 is configured to output the contour information of the sealing area if no sub-contour exists in any contour in the sealing area contour set.

[0105] Furthermore, the copper clad laminate sealing area identification device also includes:

[0106] The contour correction module 306 is used to fill the sub-contour if any contour in the sealing area contour information has a sub-contour, and input the sealing area contour set after the sub-contour is filled into the hierarchical structure analysis model again until no sub-contour exists in any contour in the sealing area contour set.

[0107] The area calculation module 307 is used to obtain the area of ​​the sealing area according to the sealing area contour set.

[0108] Furthermore, the above-mentioned contour verification module includes a space conversion unit and a structure analysis unit, wherein:

[0109] The space conversion unit is used to convert the initial contour information of the sealing area from the RGB space to the HSV space, and obtain the mask information of the sealing area;

[0110] The structure analysis unit is used to input the mask information of the sealing area into the hierarchical structure analysis model to obtain a set of contours of the sealing area.

[0111] For the copper clad laminate sealing glue area identification device, all of them can be found in the above definition of the method, which will not be repeated here. Each module in the above device can be implemented in whole or in part by software, hardware and a combination thereof. The above modules can be embedded in or independent of the processor of the terminal device in the form of hardware, or stored in the memory of the terminal device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0112] In one embodiment, the present invention further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above-mentioned copper clad laminate sealing region identification method are implemented.

[0113] The computer-readable storage medium may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read-only memory), an EPROM (erasable programmable read-only memory), a hard disk or a ROM. Optionally, the computer-readable storage medium includes a non-transitory computer-readable storage medium. The computer-readable storage medium has a storage space for program codes for executing any method step of the above method. These program codes may be read from or written into one or more computer program products, and the program codes may be compressed in an appropriate form.

[0114] In one embodiment, the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the above-mentioned copper clad laminate sealing area identification method when executing the computer program.

[0115] The computer device includes a memory, a processor, and one or more computer programs, wherein the one or more computer programs can be stored in the memory and configured to be executed by one or more processors, and the one or more application programs are configured to execute the above-mentioned copper clad laminate sealing area identification method.

[0116] The processor may include one or more processing cores. The processor uses various interfaces and lines to connect the various parts of the entire computer device, and executes various functions of the computer device and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory, and calling data stored in the memory. Optionally, the processor can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor can integrate one or more combinations of a central processing unit (Central Processing Unit, CPU), a reporting verifier (Graphics Processing Unit, GPU) for buried data, and a modem. Among them, the CPU mainly processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing display content; and the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor, but may be implemented separately through a communication chip.

[0117] The memory may include a random access memory (RAM) or a read-only memory (ROM). The memory may be used to store instructions, programs, codes, code sets or instruction sets. The memory may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc. The data storage area may also store data created by the terminal device during use, etc.

[0118] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those 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. However, these 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 invention.

Claims

1. A method for identifying a sealing area of ​​a copper clad laminate, characterized in that: include: Get a collection of images of the copper clad laminate; The collected image set is spliced ​​in a preset order to obtain a complete copper clad laminate image; Input the complete copper clad laminate image into the trained U-Net model to obtain initial contour information of the sealing area; The initial contour information of the sealing area is converted into a color space and then input into a hierarchical structure analysis model to obtain a sealing area contour set; If no sub-contour exists for any contour in the sealing area contour set, the sealing area contour information is output.

2. The copper clad laminate sealing area identification method according to claim 1, characterized in that: Also includes: If any contour in the sealing area contour set has a sub-contour, the sub-contour is filled, and the sealing area contour set after the sub-contour is filled is input into the hierarchical structure analysis model again until any contour in the sealing area contour set has no sub-contour.

3. The method for identifying the sealing area of ​​a copper clad laminate as claimed in claim 2, characterized in that: Also includes: The area of ​​the sealing region is obtained according to the sealing region contour set.

4. The method for identifying the sealing area of ​​a copper clad laminate as claimed in claim 3, characterized in that: The initial contour information of the sealing area is converted into a color space and then input into a hierarchical structure analysis model to obtain a sealing area contour set, specifically: Converting the initial contour information of the sealing area from the RGB space to the HSV space, and obtaining the mask information of the sealing area; The mask information of the sealing area is input into the hierarchical structure analysis model to obtain a sealing area contour set.

5. The copper clad laminate sealing area identification method according to claim 4, characterized in that: The specific expression for converting the initial contour information of the sealing area from the RGB space to the HSV space is: , ， ； The specific expression of the mask information of the sealing area is: ， in, is the hue of the pixel, is the angle value of the pixel point, ranging from [0° to 360°], is the saturation of the pixel, is the brightness of the pixel, is the red channel intensity of the pixel, is the green channel intensity of the pixel, is the blue channel intensity of the pixel, Pixel The mask information, Pixel The color tone, is the minimum hue value of the pixel, is the maximum value of the pixel’s hue, Pixel The saturation of is the minimum saturation value of the pixel, is the maximum saturation value of the pixel, Pixel The brightness, is the minimum brightness of the pixel, is the maximum brightness of the pixel.

6. The copper clad laminate sealing area identification method according to claim 5, characterized in that: The specific expression for inputting the mask information of the sealing area into the hierarchical structure analysis model to obtain the sealing area contour set is: ， Among them, C is the contour set of the sealing area.

7. A copper clad laminate sealing area identification device, characterized in that: include: An image acquisition module, used to obtain a collection of images of the copper clad laminate; An image stitching module is used to stitch the collected image set in a preset order to obtain a complete copper clad laminate image; A contour recognition module is used to input the complete copper clad laminate image into the trained U-Net model to obtain initial contour information of the sealing area; A contour inspection module, used for converting the initial contour information of the sealing area into a color space and inputting the converted information into a hierarchical structure analysis model to obtain a set of contours of the sealing area; The contour output module is used to output the contour information of the sealing area if no sub-contour exists in any contour in the sealing area contour set.

8. The copper clad laminate sealing region identification device according to claim 7, characterized in that: Also includes: The contour correction module is used to fill the sub-contour if any contour in the sealing area contour information has a sub-contour, and input the sealing area contour set after the sub-contour is filled into the hierarchical structure analysis model again until no sub-contour exists in any contour in the sealing area contour set.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for identifying the sealing area of ​​a copper clad laminate according to any one of claims 1 to 6 are implemented.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it performs the copper clad laminate sealing area identification method according to any one of claims 1 to 6.

Images