A method, system, device and medium for detecting defects in the gold finger area of a circuit board

Abstract

The present invention discloses a method, system, device and medium for defect detection in the gold finger area of a circuit board, which relates to the field of electronic component production. After obtaining an image of the circuit to be measured, a target detection framework based on deep learning is used to locate the gold finger image area in the circuit to be measured. The image of the circuit to be measured is segmented according to the coordinates of the gold finger image area in the image of the circuit to be measured to obtain a gold finger area image. Then, the gold finger area image is analyzed to obtain the defect detection result of the printed circuit board. It can automatically detect the defects existing in the gold finger area of the printed circuit board by computer, avoiding the problems of unstable and inaccurate detection results obtained by manual visual inspection for gold finger areas with relatively similar features, and has strong practicability.

Description

Technical Field

[0001] The present invention relates to the field of electronic component production, and specifically, to a method, system, device and medium for detecting defects in the gold finger area of a circuit board. Background Art

[0002] With the booming development of the electronics industry, circuit design has become more complex and meticulous. As the main carrier of the electronic product circuit, the printed circuit board has increasingly strict requirements for its manufacturing process. The production process of the printed circuit board involves multiple processes, and different processes may cause different degrees of defects on the printed circuit board surface. The gold finger area is an area on the printed circuit board composed of multiple golden conductive contacts for signal transmission. Because its surface is gold-plated and the conductive contacts are arranged like fingers, it is called a "gold finger". In the printed circuit board, the gold finger, as the outlet of the external connection network, is a key area affecting the quality of the printed circuit board. At present, for the detection of printed circuit boards, pictures are usually taken by an AOI automatic optical inspection machine, and then manual visual inspection is used to classify the defects. However, manual visual inspection has great subjectivity. Especially for the detection of the gold finger area with relatively similar features, long-term manual work will greatly affect the visual inspection results, resulting in inaccurate detection results. Summary of the Invention

[0003] In order to solve the problem that when detecting a printed circuit board, for the detection of the gold finger area with relatively similar features, long-term manual work will greatly affect the visual inspection results, resulting in unstable and inaccurate detection results, the present invention provides a method, system, device and medium for detecting defects in the gold finger area. By locating the gold finger area on the printed circuit board and then analyzing the key area of the image obtained after positioning, the defects existing in the gold finger area of the printed circuit board can be automatically detected by a computer.

[0004] To achieve the above invention purpose, the present invention provides a method for detecting defects in the gold finger area of a circuit board, including the following steps:

[0005] Obtain an image of the circuit to be tested;

[0006] Identify the image of the circuit to be tested, obtain the coordinates of the target area, and segment the image of the circuit to be tested according to the coordinates of the target area to obtain an image of the gold finger area;

[0007] Process the image of the gold finger area to obtain image data;

[0008] Analyze the image data to obtain a defect detection result.

[0009] Among them, the principle of the present invention is as follows: After obtaining the image of the circuit to be measured, the computer recognizes the image of the circuit to be measured, locates the image area of the gold finger in the circuit to be measured, obtains the coordinates of the gold finger image area in the image of the circuit to be measured, segments the image of the circuit to be measured according to the coordinates to obtain the gold finger area image, then analyzes the gold finger area image through a series of image processing algorithms to obtain image data, and finally analyzes the image data to obtain the defect detection result of the printed circuit board.

[0010] Further, in order to accurately locate the gold finger area in the circuit, a target detection framework based on deep learning is used to obtain the coordinates of the target area. The obtaining of the coordinates of the target area of the circuit to be measured includes the following steps:

[0011] Obtain a plurality of circuit sample diagrams, label the gold finger areas in the circuit sample diagrams to obtain a first training set;

[0012] Train a first target detection framework based on the first training set to obtain a first target detection model;

[0013] Use the first target detection model to recognize the image of the circuit to be measured to obtain the coordinates of the target detection area.

[0014] Further, if there is excess copper defect in the gold finger area, it may cause a short circuit in the circuit when the gold finger area is used, thus resulting in unqualified quality of the printed circuit board. For the recognition of the excess copper defect in the gold finger area, a target detection framework based on deep learning is used. Therefore, the following steps are also included before processing the gold finger area image:

[0015] Obtain a plurality of circuit defect sample diagrams, label the defect positions and categories in the circuit defect sample diagrams to obtain a second training set;

[0016] Train a second target detection framework based on the second training set to obtain a second target detection model;

[0017] The processing of the gold finger area image to obtain image data includes the following steps:

[0018] Use the second target detection model to recognize the gold finger area image to obtain an image recognition result.

[0019] Among them, since it is necessary to manually label the features in the sample set used to train the target detection framework to obtain the training set, in order to improve the recognition accuracy of the target detection model obtained after training the target detection framework, as many samples as possible are required, which leads to a large workload. To reduce the workload, a Faster-RCNN target detection framework combined with the FPN structure is adopted. The Faster-RCNN target detection framework combined with the FPN structure is applicable to deep learning problems with a small sample size and can effectively reduce the workload of pre-processing the sample set.

[0020] Further, if there are dirt defects in the gold finger area, it may cause poor circuit contact when the gold finger area is used, resulting in unqualified printed circuit board quality. When identifying dirt defects in the gold finger area, the processing of the gold finger area image includes the following steps:

[0021] To facilitate computer image processing, the gold finger area image is binarized to obtain a binary image;

[0022] To filter out possible noises in the image and improve the accuracy of image processing, the binary image is filtered to obtain a first image;

[0023] The pixel gray value of the binarized image is 255 or 0. The pixel points at the dirt areas in the gold finger area will be distinguished from the pixel points at the normal circuit image after binarization, and together with the printed circuit board substrate area, they will appear black, while the normal circuit part will appear white. Therefore, the dirt in the gold finger area can be detected by detecting the area of the connected regions in the image. Therefore, the connected regions in the first image are detected;

[0024] Calculate the area of each connected region in the first image;

[0025] The analysis of the image data to obtain the defect detection result includes the following steps:

[0026] Since there may be dirt in the gold finger area, the presence of dirt will reduce the area of the normal part. Therefore, judge the size of the connected region area. If the area of the connected region is less than the standard value, the gold finger area image has a defect.

[0027] Among them, in order to avoid missing detection caused by the removal of small dirt in the gold finger area image due to filtering, the filtering is implemented by using the method of morphological opening operation. First, the binary image is eroded, and then the eroded image is dilated to obtain the first image. The morphological opening operation can eliminate isolated white dots, burrs and small bridges outside the image while keeping the overall position and shape of the image unchanged.

[0028] Further, if there are metal oxidation defects in the gold finger area, it may reduce the service life of the printed circuit board, resulting in unqualified quality of the printed circuit board. When identifying metal oxidation defects in the gold finger area, the processing of the gold finger area image includes the following steps:

[0029] For the convenience of computer image processing, the gold finger area image is grayscale processed to obtain a grayscale image;

[0030] To filter out the possible noise in the image and improve the accuracy of image processing, the grayscale image is filtered to obtain a second image;

[0031] Since the detection of printed circuit boards is mostly carried out in an industrial production environment and the industrial light source used for obtaining images is relatively stable, when there are metal oxidation defects in the gold fingers, the color of the gold finger area image is darker than that of the standard gold finger area, while the color of the printed circuit board substrate remains unchanged. Therefore, the average grayscale value of the oxidized image will decrease. According to the average grayscale value of the gold finger area image, it can be judged whether there are oxidation defects in the gold finger area of the printed circuit board. Therefore, calculate the average grayscale value of the second image to obtain the second image data;

[0032] The analysis of the image data to obtain the defect detection result includes the following steps:

[0033] Compare the size of the second image data with the grayscale interval of the standard image. If the second image data is not within the grayscale interval of the standard image, there are defects in the gold finger area image.

[0034] Among them, when there are metal oxidation defects in the gold finger area, the original golden area becomes dark golden. Since the collected image is an RGB image, for an RGB image, the main differences between gold and dark gold exist in the R channel component and G channel component of the image. To avoid the B channel component from affecting the average grayscale value of the image, the B channel component of the image can be compensated to keep the B channel component of the image fixed. Therefore, take a picture of the circuit under test under blue light to obtain the image of the circuit under test.

[0035] Among them, since the collected image is an RGB image, for an RGB image, the main differences between gold and dark gold exist in the R channel component and G channel component of the image. To avoid the B channel component from affecting the average grayscale value of the image, when calculating the average grayscale value of the image, the B channel component of the image can be excluded. The grayscale processing of the gold finger area image includes the following steps:

[0036] Obtain the R component and G component of the pixels of the gold finger area image;

[0037] Perform weighted calculations on the R component and the G component to obtain the pixel grayscale value;

[0038] Generate a grayscale image based on the pixel grayscale value.

[0039] To achieve the above-mentioned invention purpose, the present invention also provides a circuit board gold finger area defect detection system, and the system includes:

[0040] An image acquisition unit for acquiring an image of a circuit to be measured;

[0041] A region recognition unit for recognizing the image of the circuit to be measured, obtaining the coordinates of the target region, and segmenting the image of the circuit to be measured according to the coordinates of the target region to obtain a gold finger area image;

[0042] A processing unit for processing the gold finger area image to obtain image data;

[0043] An analysis unit for analyzing the image data to obtain a defect detection result;

[0044] The system is used to implement the steps of the circuit board gold finger area defect detection method.

[0045] To achieve the above-mentioned invention purpose, the present invention also provides a circuit board gold finger area defect detection device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the circuit board gold finger area defect detection method are implemented.

[0046] To achieve the above-mentioned invention purpose, the present invention also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the circuit board gold finger area defect detection method are implemented.

[0047] One or more technical solutions provided by the present invention have at least the following technical effects or advantages: By locating the gold finger area on the printed circuit board and then analyzing the key area of the image obtained after positioning, the present invention can automatically detect the defects existing in the gold finger area of the printed circuit board by computer, avoiding the problem of unstable and inaccurate detection results obtained by manual visual inspection for gold finger areas with relatively similar features, and has strong practicability. Description of the Drawings

[0048] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, form a part of the present invention, and do not limit the embodiments of the present invention;

[0049] Figure 1It is a schematic diagram of the defect detection process for the gold finger area in the present invention;

[0050] Figure 2 It is a schematic diagram of the target detection result for the gold finger area in the present invention;

[0051] Figure 3 It is a schematic diagram of the residual copper defect detection result for the gold finger area in the present invention;

[0052] Figure 4 It is a schematic diagram of the defect detection system for the gold finger area in the present invention. Detailed implementation manners

[0053] In order to more clearly understand the above objects, features and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific implementation manners. It should be noted that, without conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other.

[0054] In the following description, many specific details are set forth in order to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited by the specific embodiments disclosed below.

[0055] Embodiment 1

[0056] Please refer to Figure 1 , the present invention provides a method for detecting defects in the gold finger area of a circuit board, including the following steps:

[0057] Obtain the image of the circuit to be tested;

[0058] Identify the image of the circuit to be tested, obtain the coordinates of the target area, and segment the image of the circuit to be tested according to the coordinates of the target area to obtain the image of the gold finger area;

[0059] Process the image of the gold finger area to obtain image data;

[0060] Analyze the image data to obtain the defect detection result.

[0061] In Embodiment 1, the obtaining of the coordinates of the target area is implemented through a target detection framework based on deep learning. The obtaining of the coordinates of the target area of the circuit to be tested includes the following steps:

[0062] Obtain a plurality of circuit sample diagrams, label the gold finger area in the circuit sample diagrams to obtain a first training set;

[0063] Train a first target detection framework based on the first training set to obtain a first target detection model;

[0064] Use the first target detection model to identify the image of the circuit to be measured, and obtain the coordinates of the target detection area.

[0065] Among them, the target detection framework can be the RCNN series, YOLO series, and SSD series frameworks. The RCNN series target detection frameworks include the RCNN, Fast-RCNN, and Faster-RCNN frameworks. The Faster-RCNN target detection framework assigns all four steps required for target detection, namely candidate region generation, feature extraction, classifier classification, and regressor regression, to the deep neural network, and all four steps are run on the GPU, greatly improving the operation efficiency. Therefore, in this embodiment, the Faster-RCNN target detection framework is preferably combined with the FPN structure, which can effectively be applied to the target detection problem with a small sample size.

[0066] Among them, the processing of the image of the gold finger area includes grayscale processing, binarization processing, filtering processing, etc. The specific processing method is determined according to the possible defect types of the image of the gold finger area, and this embodiment does not make a limitation here.

[0067] Embodiment 2

[0068] Please refer to Figure 1 , the present invention provides a method for detecting defects in the gold finger area of a circuit board. On the basis of Embodiment 1, for the excess copper defect in the gold finger area of the printed circuit board, before processing the image of the gold finger area, the following steps are further included:

[0069] Obtain multiple circuit defect sample diagrams, label the defect positions and categories in the circuit defect sample diagrams, and obtain a second training set;

[0070] Train a second target detection framework based on the second training set to obtain a second target detection model;

[0071] The processing of the image of the gold finger area to obtain image data includes the following steps:

[0072] Use the second target detection model to identify the image of the gold finger area, and obtain an image recognition result, as shown in Figure 3 shown.

[0073] Among them, the target detection framework can be the RCNN series, YOLO series, and SSD series frameworks. The RCNN series target detection frameworks include the RCNN, Fast-RCNN, and Faster-RCNN frameworks. The Faster-RCNN target detection framework hands over the four steps required for target detection, namely candidate region generation, feature extraction, classifier classification, and regressor regression, all to the deep neural network, and the four steps all run on the GPU, greatly improving the operation efficiency. Therefore, in this embodiment, the Faster-RCNN target detection framework is preferably combined with the FPN structure, which can effectively be applied to the target detection problem with a small sample size.

[0074] Embodiment III

[0075] Please refer to Figure 1 , the present invention provides a method for detecting defects in the gold finger area of a circuit board. On the basis of Embodiment I, for the dirt defects in the gold finger area of the printed circuit board, the processing of the gold finger area image includes the following steps:

[0076] Perform binarization processing on the gold finger area image to obtain a binarized image;

[0077] Perform filtering processing on the binarized image to obtain a first image;

[0078] Detect the connected regions in the first image;

[0079] Calculate the areas of the connected regions in the first image;

[0080] The analysis of the image data to obtain the defect detection result includes the following steps:

[0081] Judge the size of the connected region area. If the connected region area is less than the standard value, there are defects in the gold finger area image.

[0082] Among them, the standard value of the connected region area is determined according to the design layout of the circuit to be measured in actual detection, and this embodiment does not make a limitation here.

[0083] Among them, the binarization processing is to find a suitable gray threshold, and according to the threshold, set the gray values of all pixels in the image to 0 or 255. The threshold selection methods include the bimodal method, P parameter method, maximum inter-class variance method, etc. Since the image of the circuit to be measured is usually collected under an industrial fixed light source, the gold finger area image obtained by segmenting the image of the circuit to be measured is an image with a relatively regular gray distribution. The bimodal method is preferably used to calculate the gray threshold.

[0084] Among them, the detection of the connected region and the calculation of the area of the connected region can be implemented by the Two-Pass algorithm or the Seed-Filling algorithm, which is not limited in this embodiment.

[0085] Among them, the filtering processing methods include mean filtering, box filtering, Gaussian filtering, morphological opening operation, and morphological closing operation, etc. The morphological opening operation realizes the filtering processing by performing an erosion operation on the binary image and then performing a dilation operation on the image after the erosion operation, which can effectively remove small dots, burrs, and small bridges in the image while keeping the overall shape of the image unchanged. Preferably, the morphological opening operation is used for the filtering processing of the image.

[0086] Embodiment 4

[0087] Please refer to Figure 1 , the present invention provides a method for detecting defects in the gold finger area of a circuit board. On the basis of Embodiment 1, for the metal oxidation defects in the gold finger area of the printed circuit board, the processing of the gold finger area image includes the following steps:

[0088] Perform grayscale processing on the gold finger area image to obtain a grayscale image;

[0089] Perform filtering processing on the grayscale image to obtain a second image;

[0090] Calculate the grayscale average value of the second image to obtain second image data;

[0091] The analysis of the image data to obtain the defect detection result includes the following steps:

[0092] Compare the size of the second image data with the grayscale interval of the standard image. If the second image data is not within the grayscale interval of the standard image, there are defects in the gold finger area image.

[0093] Among them, the grayscale interval of the standard image is determined according to the specific needs during actual detection, which is not limited in this embodiment.

[0094] Among them, the filtering processing methods include mean filtering, box filtering, Gaussian filtering, morphological opening operation, and morphological closing operation, etc. The morphological opening operation realizes the filtering processing by performing an erosion operation on the binary image and then performing a dilation operation on the image after the erosion operation, which can effectively remove small dots, burrs, and small bridges in the image while keeping the overall shape of the image unchanged. Preferably, the morphological opening operation is used for the filtering processing of the image.

[0095] Among them, the grayscale processing methods include the component method, the maximum value method, and the weighted average method. The weighted average method calculates the grayscale value of each pixel by weighting the R, G, and B components of the color RGB image with different weights. Preferably, the weighted average method is used to perform grayscale processing on the image of the gold finger area. The weights are determined according to the characteristics of the R, G, and B components of the actual image, and are not limited in this embodiment.

[0096] Further, when there are metal oxidation defects in the gold finger area, the original golden area becomes dark gold. Since the captured image is an RGB image, for an RGB image, the main differences between gold and dark gold exist in the R-channel component and G-channel component of the image. To avoid the B-channel component from affecting the average grayscale value of the image, the B-channel component of the image can be compensated. Therefore, the circuit under test is photographed under blue light to obtain the image of the circuit under test.

[0097] Further, to avoid the B-channel component from affecting the average grayscale value of the image, the B-channel component of the image can also be excluded when performing grayscale processing on the image of the gold finger area. The steps for performing grayscale processing on the image of the gold finger area include the following:

[0098] Obtain the R component and G component of the pixels in the image of the gold finger area;

[0099] Perform weighted calculation on the R component and G component to obtain the pixel grayscale value;

[0100] Generate a grayscale image according to the pixel grayscale value.

[0101] Embodiment Five

[0102] Embodiment Five of the present invention provides a defect detection device for the gold finger area of a circuit board, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps for defect detection of the gold finger area of the circuit board are implemented.

[0103] Embodiment Six

[0104] Embodiment Six of the present invention provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for defect detection of the gold finger area of the circuit board are implemented.

[0105] Among them, the processor can be a central processing unit (CPU), or can also be other general-purpose processors, digital signal processors, application specific integrated circuits, field programmable gate arrays, or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc.

[0106] The memory can be used to store the computer program and / or modules. The processor realizes various functions of the defective detection device for the gold finger area of the circuit board in the invention by running or executing the data stored in the memory. The memory mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function (such as a sound playback function, an image playback function, etc.). In addition, the memory can include high-speed random access memory, and can also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card, a secure digital card, a flash memory card, at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0107] If the defective detection device for the gold finger area of the circuit board 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 such an understanding, all or part of the processes in the above-described embodiment methods of the present invention can also be implemented by a computer program stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-described method embodiments can be implemented. Among them, the computer program includes computer program code, object code form, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disc, a computer memory, a read-only memory, a random access memory, a dot carrier signal, a telecommunication signal, and a software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction.

[0108] The basic concepts of the present invention have been described. Obviously, for those skilled in the art, the above detailed disclosure is only an example and does not constitute a limitation to this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are proposed in this specification, so such modifications, improvements, and corrections still fall within the spirit and scope of the exemplary embodiments of this specification.

[0109] Meanwhile, this specification uses specific terms to describe the embodiments of this specification. Such as "one embodiment", "an embodiment", and / or "some embodiments" mean a certain feature, structure, or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that the "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more at different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of this specification can be appropriately combined.

[0110] In addition, those skilled in the art can understand that various aspects of this specification can be described and illustrated by several patentable types or situations, including any new and useful processes, machines, products, or combinations of substances, or any new and useful improvements to them. Accordingly, various aspects of this specification can be executed entirely by hardware, can be executed entirely by software (including firmware, resident software, microcode, etc.), or can be executed by a combination of hardware and software. The above hardware or software can all be referred to as "data blocks", "modules", "engines", "units", "components", or "systems". In addition, various aspects of this specification may be embodied as a computer product located in one or more computer-readable media, which includes computer-readable program codes.

[0111] A computer storage medium may contain a propagated data signal containing computer program codes, such as on a baseband or as part of a carrier wave. This propagated signal may have various forms of representation, including electromagnetic form, optical form, etc., or a suitable combination of forms. A computer storage medium can be any computer-readable medium other than a computer-readable storage medium, which can be connected to an instruction execution system, device, or equipment to implement communication, propagation, or transmission for use of a program. The program codes located on the computer storage medium can be propagated through any suitable medium, including radio, cable, fiber optic cable, RF, or similar media, or any combination of the above media.

[0112] The computer program codes required for the operations of each part of this specification can be written in any one or more programming languages, including object-oriented programming languages such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET, Python, etc., conventional procedural programming languages such as C language, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, dynamic programming languages such as Python, Ruby, and Groovy, or other programming languages. The program codes can run entirely on the user's computer, or run on the user's computer as an independent software package, or run partially on the user's computer and partially on a remote computer, or run entirely on a remote computer or server. In the latter case, the remote computer can be connected to the user's computer through any network form, such as a local area network (LAN) or a wide area network (WAN), or connected to an external computer (e.g., through the Internet), or in a cloud computing environment, or used as a service such as software as a service (SaaS).

[0113] In addition, unless clearly stated in the claims, the order of the processing elements and sequences described in this specification, the use of numerical letters, or the use of other names are not used to limit the order of the processes and methods in this specification. Although some currently considered useful embodiments of the invention are discussed through various examples in the above disclosure, it should be understood that such details only serve the purpose of illustration, and the appended claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that conform to the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only through a software solution, such as installing the described system on an existing server or mobile device.

[0114] Similarly, it should be noted that, in order to simplify the presentation of the disclosure in this specification and thus help the understanding of one or more embodiments of the invention, in the previous description of the embodiments of this specification, multiple features are sometimes merged into one embodiment, drawing, or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than those mentioned in the claims. In fact, the features of the embodiments are fewer than all the features of the individual embodiments disclosed above.

[0115] For each patent, patent application, patent application publication, and other materials cited in this specification, such as articles, books, specifications, publications, documents, etc., their entire contents are hereby incorporated into this specification by reference. This does not include application history files that are inconsistent with or conflict with the content of this specification, nor files that limit the broadest scope of the claims of this specification (currently or subsequently appended to this specification). It should be noted that if there are any inconsistencies or conflicts between the descriptions, definitions, and / or uses of terms in the supplementary materials of this specification and the content described in this specification, the descriptions, definitions, and / or uses of terms in this specification shall prevail.

[0116] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications to these embodiments once they learn the basic creative concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications that fall within the scope of the present invention.

[0117] Obviously, those skilled in the art can make various changes and variations to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. A method for detecting defects in the gold finger area of a circuit board, characterized in that, It includes the following steps: Take a photo of the circuit under test under blue light to obtain an image of the circuit under test; Identify the image of the circuit under test to obtain the coordinates of the target area, and segment the image of the circuit under test according to the coordinates of the target area to obtain an image of the gold finger area; Process the image of the gold finger area to obtain image data; The processing of the image of the gold finger area includes the following steps: perform grayscale processing on the image of the gold finger area to obtain a grayscale image; perform filtering processing on the grayscale image to obtain a second image; calculate the grayscale average value of the second image to obtain the image data; The image of the gold finger area is an RGB image, and the grayscale processing of the image of the gold finger area includes the following steps: obtain the R component and G component of the pixels of the image of the gold finger area; perform weighted calculation on the R component and G component to obtain the pixel grayscale value; generate a grayscale image according to the pixel grayscale value; Analyze the image data to obtain a defect detection result; The analyzing the image data to obtain a defect detection result includes the following steps: Compare the size of the grayscale interval of the second image data with that of the standard image. If the second image data is not within the grayscale interval of the standard image, there are defects in the image of the gold finger area.

2. The method for detecting defects in the gold finger area of a circuit board according to claim 1, characterized in that The coordinates of the target area are obtained by the following steps: Obtain multiple circuit sample diagrams, label the gold finger areas in the circuit sample diagrams to obtain a first training set; Train a first object detection framework based on the first training set to obtain a first object detection model; Use the first object detection model to identify the image of the circuit under test to obtain the coordinates of the target area.

3. A method for detecting defects in the gold finger area of a circuit board according to claim 1, characterized in that, Before processing the image of the gold finger area, the following steps are also included: Obtain multiple circuit defect sample diagrams, label the defect positions and categories in the circuit defect sample diagrams to obtain a second training set; Train a second object detection framework based on the second training set to obtain a second object detection model; The processing of the image of the gold finger area to obtain image data includes the following steps: Use the second object detection model to identify the image of the gold finger area to obtain an image recognition result.

4. A method for detecting defects in the gold finger area of a circuit board according to claim 1, characterized in that, The processing of the image of the gold finger area includes the following steps: Perform binarization processing on the image of the gold finger area to obtain a binarized image; Perform filtering processing on the binarized image to obtain a first image; Detect the connected regions in the first image; Calculate the areas of the connected regions in the first image; The analyzing the image data to obtain a defect detection result includes the following steps: Judge the size of the area of the connected region. If the area of the connected region is smaller than the standard value, there are defects in the image of the gold finger area.

5. A method for detecting defects in the gold finger area of a circuit board according to claim 4, characterized in that, The filtering processing is to perform morphological opening operation on the binarized image.

6. A method for detecting defects in the gold finger area of a circuit board according to claim 2 or 3, characterized in that, The object detection framework is a Faster-RCNN object detection framework combined with an FPN structure.

7. A defect detection system for the gold finger area of a circuit board, characterized in that, The system includes: An image acquisition unit for taking a photo of the circuit under test under blue light to obtain an image of the circuit under test; An area recognition unit for recognizing the image of the circuit to be measured, obtaining the coordinates of the target area, and segmenting the image of the circuit to be measured according to the coordinates of the target area to obtain an image of the gold finger area; A processing unit for processing the image of the gold finger area to obtain image data; the processing of the image of the gold finger area includes the following steps: performing grayscale processing on the image of the gold finger area to obtain a grayscale image; performing filtering processing on the grayscale image to obtain a second image; calculating the grayscale average value of the second image to obtain the image data; The image of the gold finger area is an RGB image, and the grayscale processing of the image of the gold finger area includes the following steps: obtaining the R component and G component of the pixels of the image of the gold finger area; performing weighted calculation on the R component and G component to obtain the pixel grayscale value; generating a grayscale image according to the pixel grayscale value; An analysis unit for analyzing the image data to obtain a defect detection result; The analyzing the image data to obtain a defect detection result includes the following steps: Comparing the size of the grayscale interval of the second image data with that of the standard image. If the second image data is not within the grayscale interval of the standard image, there is a defect in the image of the gold finger area.

8. A defect detection device for the gold finger area of a circuit board, 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 steps of the method for detecting defects in the gold finger area of the circuit board according to any one of claims 1-5 are implemented.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, the steps of the method for detecting defects in the gold finger area of the circuit board according to any one of claims 1-5 are implemented.

Images