Defect detection method, device and equipment for flexible circuit board and storage medium
By employing image recognition technology and an automatic detection method based on color-area relationships, the problem of automating the detection of hole alignment in flexible circuit boards has been solved, improving detection efficiency and accuracy, and making it suitable for the production of flexible circuit boards.
Patent Information
- Application Number
- CN202410887530.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-03
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-07-03
AI Technical Summary
In the existing technology, it is difficult to automatically detect whether the holes in the conductive layer and the insulating layer are aligned during the production process of flexible circuit boards, which makes manual inspection time-consuming, labor-intensive and prone to errors.
Image recognition technology is used to acquire images of flexible circuit boards. The location of holes is identified through preprocessing and preset recognition models. The alignment of conductive and insulating layers is automatically detected by utilizing the color-area relationship in the hole images. This includes the use of convolutional neural network models and mesh generation techniques.
It achieves automated detection of hole alignment in flexible circuit boards, improves detection efficiency, reduces error rate, does not affect production efficiency, and is practical.
Smart Images

Figure CN118967553A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of image defect detection, and in particular to a defect detection method, device and storage medium for a flexible circuit board. Background Art
[0002] Flexible printed circuit (FPC) is a special electronic component made of multiple layers of materials. It mainly includes a substrate layer, which is usually a flexible insulating material such as polyester film or polyimide film; a conductive layer, which uses conductive copper foil to form the wires and welding areas of the circuit; and an insulating layer, which is used to isolate the conductive layer to prevent short circuits or other damage to the circuit. These hierarchical structures enable flexible printed circuits to not only have good electrical properties, but also adapt to curved and space-constrained application environments, such as mobile devices, medical devices, and automotive electronics.
[0003] At present, when flexible circuit boards are produced, the conductive layer and the insulating layer need to be bonded together. However, during the bonding process, it is necessary to ensure that the holes opened on the conductive layer and the insulating layer are aligned as much as possible. This ensures that in the subsequent component installation and circuit connection, the position and size of the holes meet the design requirements, thereby avoiding circuit connection problems and functional failures caused by hole position deviations.
[0004] In the prior art, before bonding the insulating layer and the conductive layer, people usually use a magnifying glass to manually detect the defect of misaligned holes. Obviously, this method is time-consuming and labor-intensive, and has a high error rate. Therefore, people need a solution that can automatically detect whether the holes are aligned before bonding the insulating layer and the conductive layer. Summary of the invention
[0005] Therefore, the present invention provides a defect detection method for a flexible circuit board, so as to solve the problem in the prior art of how to automatically detect whether holes are aligned before bonding the insulating layer and the conductive layer.
[0006] The present invention provides a defect detection method for a flexible circuit board, comprising: Acquire a captured image, where the captured image is taken perpendicular to the plane where the flexible circuit board is located, and is an image of the flexible circuit board after the conductive layer covers the insulating layer; Preprocessing the collected image to obtain an optimized image; Based on a preset recognition model, positions of a plurality of preset holes in the optimization image are identified, and an image of each preset hole is intercepted to obtain a hole image; According to the area size relationship between the first color, the second color, the third color and the fourth color in the hole image, it is detected whether the conductive layer and the insulating layer are aligned, wherein the first color is the color of the insulating layer, the second color is the color of the conductive layer, the third color is the color superimposed after the insulating layer covers the conductive layer, and the fourth color is the background color when the image is captured.
[0007] The present invention also provides a preferred solution: based on a preset recognition model, the positions of multiple preset holes in the optimized image are identified, and an image of each preset hole is intercepted to obtain a hole image, including: Divide the optimized image into multiple grids of preset sizes; Identify the probability of a preset hole existing in each grid based on a preset recognition model; According to the probability of the existence of a preset hole in each grid, the positions of a plurality of preset holes are obtained and an image of each preset hole is captured.
[0008] The present invention also provides a preferred solution: the area of the grid is smaller than the area of the smallest preset hole.
[0009] The present invention also provides a preferred solution: the preset recognition model is a convolutional neural network model, and the preset recognition model includes an input layer, at least one convolutional layer, at least one fully connected layer and an output layer connected in sequence, wherein the number of nodes in the input layer is equal to the number of pixels in the optimized image, and each node in the input layer is used to input the three color channel values of a pixel in the optimized image, and the number of nodes in the output layer is equal to the number of grids in the optimized image, and each node in the output layer is used to output a probability description vector corresponding to a grid, and the elements of the probability description vector include: the confidence probability of at least one detection frame where the preset hole in the grid is located, the center coordinates of at least one detection frame where the preset hole in the grid is located, and the size of at least one detection frame where the preset hole in the grid is located.
[0010] The present invention also provides a preferred solution: according to the probability of the existence of a preset hole in each grid, the positions of multiple preset holes are obtained and the image of each preset hole is intercepted, including: According to the multiple probability description vectors output by the preset recognition model, multiple non-overlapping target detection frames with the highest confidence probability are obtained; The positions of multiple target detection frames are captured from the optimized image to obtain images of multiple preset holes.
[0011] The present invention also provides a preferred solution: detecting whether the conductive layer and the insulating layer are aligned according to the area size relationship between the first color, the second color, the third color and the fourth color in the hole image, including: According to the area size relationship between the first color and the second color, and the area ratio relationship between the third color and the fourth color in each hole image, a hole overlap evaluation value of each hole image is obtained, wherein the hole overlap evaluation value is used to characterize the degree of overlap between the holes opened on the conductive layer and the holes opened on the insulating layer in the hole image; If the hole overlap evaluation values corresponding to all hole images do not exceed the preset standard threshold, it is determined that the conductive layer and the insulating layer are aligned.
[0012] The present invention also provides a preferred solution: the hole overlap evaluation value is calculated by the following formula: ; in, represents the hole overlap evaluation value, , , and The areas of the first color, second color, third color and fourth color in the hole image respectively, is the area of the preset hole corresponding to the type of hole image, is the area of the target detection box corresponding to the hole image, To preset hyperparameters, and They have different preset weights.
[0013] The present invention also provides a defect detection device for a flexible circuit board, comprising: An image acquisition module is used to acquire an image, where the image is taken perpendicular to the plane where the flexible circuit board is located, and is an image of the flexible circuit board after the conductive layer covers the insulating layer; An image optimization module is used to preprocess the collected image to obtain an optimized image; A hole recognition module, used to recognize the positions of multiple preset holes in the optimized image based on a preset recognition model, and intercept the image of each preset hole to obtain a hole image; The hole detection module is used to detect whether the conductive layer and the insulating layer are aligned according to the area size relationship between the first color, the second color, the third color and the fourth color in the hole image, wherein the first color is the color of the insulating layer, the second color is the color of the conductive layer, the third color is the color superimposed after the insulating layer covers the conductive layer, and the fourth color is the background color when the image is captured.
[0014] The present invention also provides an electronic device, comprising: Memory and processor; The memory is used to store programs, and the processor is used to execute the steps in any one of the above-mentioned methods for detecting defects in flexible circuit boards when executing the programs.
[0015] The present invention also provides a computer-readable storage medium for storing computer-readable programs or instructions, which, when executed by a processor, can implement the steps in any of the above-mentioned methods for detecting defects in flexible circuit boards.
[0016] The beneficial effects of adopting the above embodiment are: The present invention provides a defect detection method for a flexible circuit board. The method first obtains an image after a conductive layer covers an insulating layer in the flexible circuit board as a captured image, then preprocesses the captured image to obtain an optimized image, then identifies the positions of multiple preset holes in the optimized image based on a preset recognition model, and intercepts the image of each preset hole to obtain a hole image, and finally detects whether the conductive layer and the insulating layer are aligned according to the area size relationship between a first color, a second color, a third color and a fourth color in the hole image, wherein the first color is the color of the insulating layer, the second color is the color of the conductive layer, the third color is the color superimposed after the insulating layer covers the conductive layer, and the fourth color is the background color when the captured image is shot. Compared with the prior art, the present invention realizes automatic detection of hole alignment based on the idea of using image recognition technology to locate holes and obtain hole images, and then detecting the hole images. When detecting alignment, the holes are aligned by comparing the area size relationship between the first color, the second color, the third color and the fourth color. The purpose of rapid detection is achieved by simply comparing the color proportions rather than complex models, so that the entire defect detection process can not only be automatically operated, but also will not affect the processing efficiency of the flexible circuit board, so that it can be actually applied in production. It perfectly solves the problem of how to automatically detect whether the holes are aligned before bonding the insulating layer and the conductive layer, and has good practicality. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] Figure 1 A method flow chart of an embodiment of a defect detection method for a flexible circuit board provided by the present invention; Figure 2 A schematic diagram of the colors of the preset holes in the present invention; Figure 3 for Figure 1 The method flow chart of step S103; Figure 4 A schematic structural diagram of an embodiment of a defect detection device for a flexible circuit board provided by the present invention; Figure 5 This is a schematic structural diagram of an electronic device provided by the present invention. DETAILED DESCRIPTION
[0018] 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 of 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.
[0019] Combination Figure 1 As shown, a specific embodiment of the present invention discloses a defect detection method for a flexible circuit board, comprising: S101, obtaining a captured image, where the captured image is an image of the flexible circuit board after the conductive layer covers the insulating layer, taken perpendicularly to the plane where the flexible circuit board is located; S102, preprocessing the collected image to obtain an optimized image; S103, identifying the positions of multiple preset holes in the optimized image based on a preset recognition model, and intercepting an image of each preset hole to obtain a hole image; S104. Detect whether the conductive layer and the insulating layer are aligned based on the area size relationship among the first color, the second color, the third color and the fourth color in the hole image, wherein the first color is the color of the insulating layer, the second color is the color of the conductive layer, the third color is the color presented after the insulating layer covers the conductive layer, and the fourth color is the background color when the image is captured.
[0020] It is understandable that the conductive layer in the present invention can be understood as the conductive layer itself, and can be understood as the collection of all layers below the insulating layer in the flexible circuit board including the conductive layer, that is, the conductive layer plus the substrate layer, etc. The specific layers of the conductive layer can be flexibly specified according to the actual process sequence, and it is only necessary to ensure that the conductive layer is located below the insulating layer (that is, the side of the insulating layer away from the camera device) when shooting an image.
[0021] Compared with the prior art, the present invention realizes automatic detection of hole alignment based on the idea of using image recognition technology to locate holes and obtain hole images, and then detecting the hole images. When detecting alignment, the holes are aligned by comparing the area size relationship between the first color, the second color, the third color and the fourth color. The purpose of rapid detection is achieved by simply comparing the color proportions rather than complex models, so that the entire defect detection process can not only be automatically operated, but also will not affect the processing efficiency of the flexible circuit board, so that it can be actually applied in production. It perfectly solves the problem of how to automatically detect whether the holes are aligned before bonding the insulating layer and the conductive layer, and has good practicality.
[0022] In order to facilitate observation of the circuit in practice, the insulating layer generally has a certain degree of transparency. It is understandable that when the insulating layer covers the conductive layer, if the preset holes opened on the insulating layer and the conductive layer are not aligned, then the following will appear: Figure 2 In the case shown, the conductive layer covering the insulating layer will present the third color, and the middle part of the preset hole will directly present the color of the background on which the conductive layer is placed, that is, the fourth color (such as the color of the workbench, or when the conductive layer is placed on the light-emitting platform, the fourth color will present the color of the light source, such as white). At the same time, the positions in the preset holes of the two layers that are not aligned will be misaligned, and the insulating layer that does not cover the conductive layer will directly present its own color, that is, the first color. Similarly, the conductive layer that is not covered by the insulating layer will also present its own color, that is, the second color.
[0023] It is understandable that if the preset holes are well aligned, the area of the fourth color will be closer to the area of the preset holes themselves, and the area of the third color will not deviate greatly. At the same time, the areas of the first color and the second color will be smaller and the areas of the two will be the same. Based on the above rules, it is possible to directly determine whether the preset holes are aligned. In the process of computer image processing, the above content can be achieved by directly counting the number of pixels of each color and then making a simple comparison. Compared with other recognition algorithms or models, it is obvious that the execution speed of the above process is extremely fast. In the actual production process, it can be detected in real time as the personnel adjust the position of the insulating layer, and a prompt will be issued when the preset holes are aligned, thereby performing adhesion and improving the efficiency of defect detection, which has a high practical value.
[0024] For the above step S101, the acquisition image is taken perpendicular to the plane where the flexible circuit board is located, and is an image of the conductive layer in the flexible circuit board covering the insulating layer, which can be achieved in any way. For example, a high-precision camera is added to the workbench where the insulating layer is currently laid to achieve the acquisition of the acquisition image. It can also be considered that a luminous workbench is designed, and a high-precision camera is also set above the workbench for special alignment detection.
[0025] Furthermore, for the above-mentioned step S102, the collected image is preprocessed to obtain an optimized image, which can also be implemented in any existing manner. For example, the preprocessing method includes but is not limited to graying, filtering, image enhancement, geometric transformation and other processing. Graying is the process of converting a color image into a grayscale image, which simplifies image analysis by removing color information. Filtering technology is used to remove noise or detail information in an image. Common filters include Gaussian filters and median filters. Gaussian filters smooth images by weighted averaging of neighborhood pixels, which is suitable for smoothing and removing high-frequency noise; while median filters are used to remove low-frequency noise, etc. Image enhancement techniques include histogram equalization and contrast enhancement, which are used to enhance the visual effect and information content of the image. Histogram equalization enhances image contrast and brightness by adjusting the distribution of image pixels. Geometric transformation includes operations such as rotation, scaling and translation, which are used to correct the angle and size of the image to meet specific subsequent analysis requirements in the present invention.
[0026] Further, combined with Figure 3 As shown, in a preferred embodiment, the above step S103, identifying the positions of multiple preset holes in the optimized image based on the preset recognition model, and intercepting the image of each preset hole to obtain the hole image, specifically includes: S301, dividing the optimized image into a plurality of grids of preset specifications; S302, identifying the probability of a preset hole existing in each grid based on a preset recognition model; S303 , according to the probability that a preset hole exists in each grid, obtain the positions of multiple preset holes and capture an image of each preset hole.
[0027] The preset recognition model in the above process can be implemented by any existing model such as R-CNN neural network model, YOLO neural network model, etc. In this embodiment, the image is optimized to be divided into multiple grids of preset specifications. The advantage is that each grid can be judged separately. On the one hand, the complexity of the preset recognition model can be reduced (because the number of input data for each recognition is significantly reduced), the efficiency and parallelism of the algorithm can be improved, and the flexibility and accuracy of the algorithm can be guaranteed at the same time.
[0028] Furthermore, in a preferred embodiment, the area of the grid is smaller than the area of the smallest preset hole. After the probability of the preset hole existing in each grid is calculated, the grids with higher probability and adjacent to each other can be spliced to locate the preset hole.
[0029] The significance of the above limitation is to ensure that one grid is only used to identify one preset hole, thereby ensuring the accuracy of the algorithm and avoiding undesirable phenomena such as calculation errors caused by the existence of two or more preset holes in one grid.
[0030] Furthermore, in a preferred embodiment, the preset recognition model is a convolutional neural network model, and the preset recognition model includes an input layer, at least one convolutional layer, at least one fully connected layer and an output layer connected in sequence, wherein the number of nodes in the input layer is equal to the number of pixels in the optimized image, and each node in the input layer is used to input the three color channel values of a pixel in the optimized image, the number of nodes in the output layer is equal to the number of grids in the optimized image, and each node in the output layer is used to output a probability description vector corresponding to a grid, and the elements of the probability description vector include: the confidence probability of at least one detection box where the preset holes in the grid are located (equivalent to the probability that a certain type of preset holes exists in each grid), the center coordinates of at least one detection box where the preset holes in the grid are located, and the size of at least one detection box where the preset holes in the grid are located.
[0031] The structure of the above preset recognition model is actually a simplified improvement of the existing YOLO neural network model. Specifically, because the application scenario in this embodiment is single, the input image is a simple flexible circuit board covered with an insulating layer, and the image content basically only includes a large number of colors and holes. Therefore, in this embodiment, the pooling layer of the existing YOLO neural network is omitted to ensure accuracy while improving the algorithm operation efficiency.
[0032] At the same time, the most important thing is that this embodiment greatly omits the data content that the model needs to output. In the prior art, the vector output by the YOLO neural network needs to include the probabilities of multiple recognition objects. In the application scenario of this embodiment, because the number of types of preset holes in a flexible circuit board is limited, this embodiment omits the probability of the recognition object in the output vector, and only uses the detection box to represent the probability of predicted holes of different specifications. In the YOLO neural network, the "bounding box" usually refers to the bounding box predicted by the neural network, which is used to identify the position and size of the target object detected in the input image. Therefore, the method of using the detection box in this embodiment to represent the probability of predicted holes of different specifications omits the elements of the probability description vector as described above for multiple recognition objects, simplifies the vector length, reduces the number of data that needs to be predicted, greatly reduces the amount of data that needs to be considered by the preset recognition model, and improves efficiency. On the other hand, the recognition accuracy of the entire model is improved due to the increase in the detection box.
[0033] In addition, the structure of the preset recognition model in this embodiment is combined with the restriction that the area of the grid is smaller than the area of the smallest preset hole, which further improves the accuracy and avoids the inaccuracy caused by the simultaneous existence of two holes in a grid, thereby overcoming the defects of the existing YOLO model (especially the YOLOv1 model).
[0034] Further, in a preferred embodiment, the above step S303, obtaining the positions of multiple preset holes and capturing the image of each preset hole according to the probability of the presence of the preset hole in each grid, specifically includes: According to the multiple probability description vectors output by the preset recognition model, multiple non-overlapping target detection frames with the highest confidence probability are obtained; The positions of multiple target detection frames are captured from the optimized image to obtain images of multiple preset holes.
[0035] The above process can be implemented by using the existing non-maximum suppression method to obtain multiple target detection frames. The advantage of the above process is that the target detection frame is directly used as the cropping range of each preset hole identified, eliminating the process of determining the interception range, while ensuring the cropping flexibility and accuracy for preset holes of different specifications. In addition, the above target detection frame will also be directly used for the subsequent calculation of the hole overlap evaluation value, providing a data reference basis for it.
[0036] Further, in a preferred embodiment, the above step S104, detecting whether the conductive layer and the insulating layer are aligned according to the area size relationship between the first color, the second color, the third color and the fourth color in the hole image, specifically includes: According to the area size relationship between the first color and the second color, and the area ratio relationship between the third color and the fourth color in each hole image, a hole overlap evaluation value of each hole image is obtained, wherein the hole overlap evaluation value is used to characterize the degree of overlap between the holes opened on the conductive layer and the holes opened on the insulating layer in the hole image; If the hole overlap evaluation values corresponding to all hole images do not exceed the preset standard threshold, it is determined that the conductive layer and the insulating layer are aligned.
[0037] The above process simultaneously determines the hole overlap from two dimensions: the area size relationship between the first color and the second color, and the area ratio relationship between the third color and the fourth color, to ensure recognition accuracy and avoid interference caused by shadows and the like.
[0038] Specifically, in a preferred embodiment, the hole overlap evaluation value is calculated by the following formula: ; in, represents the hole overlap evaluation value, , , and The areas of the first color, second color, third color and fourth color in the hole image respectively, is the area of the preset hole corresponding to the type of hole image, is the area of the target detection box corresponding to the hole image, To preset hyperparameters, and They have different preset weights.
[0039] The significance of the above formula is that the first term is used to measure the difference between the first color and the second color, and the second term is used to measure the proportional relationship between the third color and the fourth color. The area of the target detection box and the area of the preset hole are introduced as references for standard data to make it more accurate. The result is ensured to be an integer by preset hyperparameters, and the degree of influence is controlled by preset weights. The preset weights and preset hyperparameters can be obtained by any existing method through experiments.
[0040] Combination Figure 4 As shown, the present invention also provides a defect detection device for a flexible circuit board, comprising: The image acquisition module 410 is used to acquire an image, which is an image taken perpendicular to the plane where the flexible circuit board is located, and is an image of the flexible circuit board after the conductive layer covers the insulating layer; The image optimization module 420 is used to pre-process the collected image to obtain an optimized image; A hole recognition module 430 is used to recognize the positions of multiple preset holes in the optimized image based on a preset recognition model, and to capture an image of each preset hole to obtain a hole image; The hole detection module 440 is used to detect whether the conductive layer and the insulating layer are aligned according to the area size relationship between the first color, the second color, the third color and the fourth color in the hole image, wherein the first color is the color of the insulating layer, the second color is the color of the conductive layer, the third color is the color superimposed after the insulating layer covers the conductive layer, and the fourth color is the background color when the image is captured.
[0041] It should be noted here that the corresponding system provided in the above embodiments can implement the technical solutions described in the above method embodiments. The specific implementation principles of the above modules or units can be found in the corresponding contents in the above method embodiments, which will not be repeated here.
[0042] refer to Figure 5 , shows a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. In this embodiment, the electronic device includes: Memory 510 and processor 520; The memory 510 is used to store programs, and the processor 520 is used to execute the defect detection method for the flexible circuit board in the above embodiment when executing the program.
[0043] This embodiment further provides a computer-readable storage medium on which a defect detection program for a flexible circuit board is stored. When the defect detection program for a flexible circuit board is executed by a processor, the steps in the above embodiment can be implemented.
[0044] The present invention provides a defect detection method for a flexible circuit board. The method first obtains an image after a conductive layer covers an insulating layer in the flexible circuit board as a captured image, then preprocesses the captured image to obtain an optimized image, then identifies the positions of multiple preset holes in the optimized image based on a preset recognition model, and intercepts the image of each preset hole to obtain a hole image, and finally detects whether the conductive layer and the insulating layer are aligned according to the area size relationship between a first color, a second color, a third color and a fourth color in the hole image, wherein the first color is the color of the insulating layer, the second color is the color of the conductive layer, the third color is the color superimposed after the insulating layer covers the conductive layer, and the fourth color is the background color when the captured image is shot. Compared with the prior art, the present invention realizes automatic detection of hole alignment based on the idea of using image recognition technology to locate holes and obtain hole images, and then detecting the hole images. When detecting alignment, the holes are aligned by comparing the area size relationship between the first color, the second color, the third color and the fourth color. The purpose of rapid detection is achieved by simply comparing the color proportions rather than complex models, so that the entire defect detection process can not only be automatically operated, but also will not affect the processing efficiency of the flexible circuit board, so that it can be actually applied in production. It perfectly solves the problem of how to automatically detect whether the holes are aligned before bonding the insulating layer and the conductive layer, and has good practicality.
[0045] It should be noted that the various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.
[0046] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A defect detection method for a flexible circuit board, characterized in that: include: Acquire a captured image, where the captured image is taken perpendicular to the plane where the flexible circuit board is located, and is an image of the flexible circuit board after the conductive layer covers the insulating layer; Preprocessing the collected image to obtain an optimized image; Based on a preset recognition model, positions of a plurality of preset holes in the optimization image are identified, and an image of each preset hole is intercepted to obtain a hole image; According to the area size relationship between the first color, the second color, the third color and the fourth color in the hole image, it is detected whether the conductive layer and the insulating layer are aligned, wherein the first color is the color of the insulating layer, the second color is the color of the conductive layer, the third color is the color superimposed after the insulating layer covers the conductive layer, and the fourth color is the background color when the image is captured.
2. The defect detection method of the flexible circuit board according to claim 1, characterized in that: The positions of multiple preset holes in the optimized image are identified based on a preset recognition model, and an image of each preset hole is intercepted to obtain a hole image, including: Divide the optimized image into multiple grids of preset sizes; Identify the probability of a preset hole existing in each grid based on a preset recognition model; According to the probability of the existence of a preset hole in each grid, the positions of a plurality of preset holes are obtained and an image of each preset hole is captured.
3. The defect detection method of the flexible circuit board according to claim 2, characterized in that: The area of the grid is smaller than the area of the smallest preset hole.
4. The defect detection method of the flexible circuit board according to claim 3, characterized in that: The preset recognition model is a convolutional neural network model, which includes an input layer, at least one convolutional layer, at least one fully connected layer and an output layer connected in sequence, wherein the number of nodes in the input layer is equal to the number of pixels in the optimized image, and each node in the input layer is used to input the three color channel values of a pixel in the optimized image, the number of nodes in the output layer is equal to the number of grids in the optimized image, and each node in the output layer is used to output a probability description vector corresponding to a grid, and the elements of the probability description vector include: the confidence probability of at least one detection box where a preset hole exists in the grid, the center coordinates of at least one detection box where a preset hole exists in the grid, and the size of at least one detection box where a preset hole exists in the grid.
5. The defect detection method for a flexible circuit board according to claim 4, characterized in that: According to the probability of the existence of a preset hole in each grid, the positions of multiple preset holes are obtained and the image of each preset hole is intercepted, including: According to the multiple probability description vectors output by the preset recognition model, multiple non-overlapping target detection frames with the highest confidence probability are obtained; The positions of multiple target detection frames are captured from the optimized image to obtain images of multiple preset holes.
6. The defect detection method of the flexible circuit board according to claim 5, characterized in that: According to the area size relationship among the first color, the second color, the third color and the fourth color in the hole image, detecting whether the conductive layer and the insulating layer are aligned includes: According to the area size relationship between the first color and the second color, and the area ratio relationship between the third color and the fourth color in each hole image, a hole overlap evaluation value of each hole image is obtained, wherein the hole overlap evaluation value is used to characterize the degree of overlap between the holes opened on the conductive layer and the holes opened on the insulating layer in the hole image; If the hole overlap evaluation values corresponding to all hole images do not exceed the preset standard threshold, it is determined that the conductive layer and the insulating layer are aligned.
7. The defect detection method of the flexible circuit board according to claim 6, characterized in that: The hole overlap evaluation value is calculated by the following formula: ; in, represents the hole overlap evaluation value, , , and The areas of the first color, second color, third color and fourth color in the hole image respectively, is the area of the preset hole corresponding to the type of hole image, is the area of the target detection box corresponding to the hole image, To preset hyperparameters, and They have different preset weights.
8. A defect detection device for a flexible circuit board, characterized in that: include: An image acquisition module is used to acquire an image, where the image is taken perpendicular to the plane where the flexible circuit board is located, and is an image of the flexible circuit board after the conductive layer covers the insulating layer; An image optimization module is used to preprocess the collected image to obtain an optimized image; A hole recognition module, used to recognize the positions of multiple preset holes in the optimized image based on a preset recognition model, and intercept the image of each preset hole to obtain a hole image; The hole detection module is used to detect whether the conductive layer and the insulating layer are aligned according to the area size relationship between the first color, the second color, the third color and the fourth color in the hole image, wherein the first color is the color of the insulating layer, the second color is the color of the conductive layer, the third color is the color superimposed after the insulating layer covers the conductive layer, and the fourth color is the background color when the image is captured.
9. An electronic device, characterized in that: include: Memory and processor; The memory is used to store a program, and the processor is used to execute the steps of the defect detection method for a flexible circuit board according to any one of claims 1 to 7 when executing the program.
10. A computer-readable storage medium, characterized in that: Used to store computer-readable programs or instructions, which, when executed by a processor, can implement the steps of the defect detection method for a flexible circuit board as described in any one of claims 1 to 7.
Citation Information
Patent Citations
Plug seedling growth vigor non-destructive monitoring method and device based on color and depth information
CN109115776A
YOLO-based image target identification method and system, and storage medium
CN109977943A
Method for detecting appearance defects of laser welding seam
CN115797354A
Postoperative management method and system based on wearable monitoring equipment
CN117854700A
Image Detection Method, Apparatus, Electronic Device and Storage Medium
US20210209802A1
