Golden finger image building method and golden finger defect detection method

Abstract

The invention discloses a golden finger image material building method and a golden finger defect detection method, and relates to the field of AOI image detection, and the method comprises the steps: obtaining a panorama of a standard material plate, recognizing all golden finger contours in the standard material plate, and distinguishing the types of golden fingers based on the characteristics of the golden finger contours; generating a golden finger small graph corresponding to each golden finger contour, carrying out image splicing processing on the same type of golden finger small graphs according to a preset puzzle rule, generating a golden finger standard sequence graph set, and obtaining a golden finger standard to-be-tested graph set of the to-be-tested material plate in a material running stage, and detecting gold finger defects in the gold finger to-be-sequenced graph set based on the gold finger standard sequenced graph set, and converting the gold finger defects detected in the gold finger to-be-sequenced graph into the panorama of the to-be-detected material plate to obtain a gold finger defect distribution condition. According to the scheme, the image modeling and segmentation matching method is used for defect detection, compared with traditional AI recognition, the precision is higher, and the problem of insufficient detection caused by chromatic aberration is avoided.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of AOI image detection, and in particular to a gold finger image construction method and a gold finger defect detection method. Background Art

[0002] As mentioned above, several gold fingers are set on the PCB printed circuit board for connecting with external hardware circuits. Ensuring the integrity of the gold fingers is a prerequisite for ensuring the normal operation of the circuit board, so the accuracy of gold finger defect detection is very important to the production line.

[0003] In related technologies, when visual inspection technology is used to detect gold finger defects on PCBs, due to uncertain factors such as optical solutions and visual inspection equipment stability, the color difference at the gold finger in the collected pictures is small, which may be ignored during defect identification, resulting in the inability to effectively detect the defects at the gold finger. If image scanning and manual inspection methods are used, the detection rate of the production line will be greatly affected. Summary of the invention

[0004] The embodiments of the present application provide a gold finger image building method and a gold finger defect detection method to solve the problem of low gold finger defect detection accuracy due to unstable light and visual equipment.

[0005] On the one hand, the present application provides a method for creating a gold finger image, the method comprising:

[0006] Obtain a panoramic view of the standard material board, identify all gold finger contours in the standard material board, and distinguish gold finger types based on gold finger contour features;

[0007] Generate a small cheat image corresponding to each cheat outline, perform image splicing on the same type of cheat images according to preset puzzle rules, and generate a set of cheat standard sequence images, where each cheat standard sequence image carries the outline information of all cheats in the corresponding image.

[0008] Specifically, the distinguishing the gold finger type based on the gold finger contour feature includes:

[0009] Match the identified gold finger contour features with contour feature labels to determine the gold finger types of all gold finger contours;

[0010] The gold finger types include at least typical gold fingers and atypical gold fingers. The typical gold fingers are gold finger structures whose quantity proportion in the standard material board exceeds the set threshold, and the atypical gold fingers are gold finger structures whose quantity proportion in the standard material board does not exceed the set threshold.

[0011] Specifically, generating a cheat sheet corresponding to each cheat outline, performing image stitching processing on cheat sheets of the same type according to a preset jigsaw puzzle rule to generate a cheat standard sequence diagram set includes:

[0012] Extract the corresponding small gold finger image containing the complete gold finger image from the panorama according to the gold finger outline;

[0013] According to the position distribution of various types of gold fingers on the standard material board, the extracted gold finger thumbnails are numbered and marked;

[0014] The target type and target number cheat sheet images are spliced ​​into several cheat sheet standard sequence images in the order of numbers, and label information is generated based on the contour coordinates of the cheat sheets corresponding to the target number;

[0015] The target number of tag information is embedded into the corresponding gold finger standard sequence diagram according to the number, and all gold finger standard sequence diagrams constitute a gold finger standard sequence diagram set.

[0016] Specifically, for typical cheating fingers, cheating finger thumbnails corresponding to a target number of typical cheating fingers with consecutive numbers are selected and spliced ​​to form a cheating finger standard sequence diagram, and the corresponding cheating finger standard sequence diagram is embedded with label information of the corresponding cheating finger;

[0017] For atypical cheat codes, select a single cheat code thumbnail to independently generate a cheat code standard sequence diagram, and embed the label information of the corresponding typical cheat code;

[0018] In the gold finger standard sequence diagram, the gold finger thumbnails are mapped to the target position of the image according to the numbering order.

[0019] Specifically, the extracted various gold finger thumbnails are numbered and marked according to the position distribution of each type of gold finger on the standard material board, including:

[0020] Determine the pixel positions of all gold finger outlines in the panorama, and number them in sequence according to the pixel positions and preset directions, and gold fingers of the same type are numbered consecutively.

[0021] On the other hand, the present application provides a gold finger defect detection method, the method comprising:

[0022] Obtain a panoramic view of the material board to be tested, identify the contours of all gold fingers to be tested in the material board to be tested, and distinguish the types of gold fingers based on the gold finger contour features;

[0023] Generate a small picture of the gold finger to be tested corresponding to each gold finger outline, perform image splicing processing on the small pictures of the gold fingers to be tested of the same type according to the preset puzzle rules, and generate a set of gold finger pictures to be sequenced, wherein each gold finger picture to be sequenced carries the outline information of all the gold fingers to be tested in the picture;

[0024] Based on the gold finger standard sequence diagram set, the gold finger defects in the gold finger sequence diagram set are detected, and the gold finger defects detected in the gold finger sequence diagram are converted into the panoramic diagram of the material board to be tested; the gold finger standard sequence diagram set is obtained after identification and splicing based on the panoramic diagram of the standard material board.

[0025] Specifically, the process of performing image stitching processing on small gold finger images to be tested of the same type according to preset jigsaw puzzle rules to generate a gold finger image set to be sequenced includes:

[0026] According to the position distribution of each type of gold finger to be tested on the material board to be tested, the extracted small pictures of each type of gold finger to be tested are numbered and marked;

[0027] Get the label information of the cheating outline contained in each cheating standard sequence diagram in the cheating standard sequence diagram set;

[0028] Based on the label information of the corresponding gold finger standard sequence diagram, the small gold finger images to be tested of the target type are spliced ​​in the order of numbers to generate a gold finger sequence diagram, and the label information is generated based on the contour coordinates of the target number of gold fingers to be tested;

[0029] The target number of label information is embedded into the corresponding gold finger sequence diagram according to the number, and all gold finger standard sequence diagrams constitute a gold finger standard sequence diagram set.

[0030] Specifically, based on the label information of the corresponding gold finger standard sequence diagram, the gold finger small images to be tested of the target type are spliced ​​in the order of numbers to generate the gold finger sequence diagram, including:

[0031] Get the number of small gold finger images to be tested contained in the gold finger to be sequenced image;

[0032] Extract the target type of gold finger small image to be tested to the target position of the gold finger sequence map in the order of numbering, and match it according to the label information of the gold finger small image at the corresponding position in the gold finger standard sequence map;

[0033] When the outline coordinate information and the cheating type of the cheating finger thumbnail to be tested do not match the label information of the cheating finger thumbnail, the target position of the cheating finger to be sequenced is filled with a blank thumbnail and blank cheating finger outline coordinates are added;

[0034] When the outline coordinate information and the cheating type of the cheating thumbnail to be tested match the label information of the cheating thumbnail, the cheating thumbnail to be tested is spliced ​​to the target position of the cheating thumbnail to be sequenced, and the corresponding cheating outline coordinates are added.

[0035] Specifically, the cheating finger types include at least typical cheating fingers and atypical cheating fingers. When the cheating finger to be tested is an atypical cheating finger type, a cheating finger to be sequenced map is directly generated according to the extracted cheating finger thumbnail to be tested; when the cheating finger to be tested is a typical cheating finger type, a cheating finger to be sequenced map is generated by splicing according to the cheating finger type and numbering order.

[0036] Specifically, the method of detecting the gold finger defects in the gold finger sequence diagram set based on the gold finger standard sequence diagram set, and converting the gold finger defects detected in the gold finger sequence diagram to be sequenced into the panoramic diagram of the material board to be tested includes:

[0037] The corresponding gold finger standard sequence diagram and the gold finger sequence diagram to be sequenced are matched and mapped, and the defect area of ​​the gold finger to be tested is determined according to the area difference surrounded by the two gold finger contour coordinates; the blank small image filled corresponds to the gold finger missing defect;

[0038] Map the defect area coordinates to the panoramic view of the material board to be tested, and determine the defect coordinates of the defect area in the panoramic view.

[0039] The beneficial effects of the technical solution provided by the embodiment of the present application include at least: the present application identifies the outline of the gold finger of the standard material board and classifies the gold finger, extracts the gold finger thumbnail according to the outline of the gold finger, and splices the thumbnails of different types of gold finger thumbnails according to the numbering sequence and type rules to generate multiple gold finger standard sequence diagram sets;

[0040] In the material running stage, the panoramic image of each material board to be tested uses the same contour recognition method to extract the contour of the gold finger to be tested and extract the small image of the gold finger to be tested; then the small image of the gold finger to be tested is spliced ​​according to the numbering and type rules to form a gold finger sequence map that is mapped to the gold finger standard sequence map, and then the defect area of ​​each gold finger on the material board to be tested is determined by subtraction from the contour area surrounded by the pixel level, realizing non-AI recognition defect detection. This solution uses image modeling and segmentation matching methods for defect detection, which is more accurate than traditional AI recognition and avoids the problem of insufficient detection due to color difference. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 is a flow chart of a method for building a golden finger image provided by an embodiment of the present application;

[0042] Figure 2 This is a panoramic view of a standard material board with a possible form of PCB structure;

[0043] Figure 3 This is an algorithm flow chart of a possible method for building a gold finger image;

[0044] Figure 4It is a schematic diagram of constructing a standard sequence diagram of a golden finger according to a golden finger thumbnail provided in an embodiment of the present application;

[0045] Figure 5 is a flow chart of a gold finger defect detection method provided in an embodiment of the present application;

[0046] Figure 6 It is an algorithm flow chart of a possible gold finger defect detection method;

[0047] Figure 7 A schematic diagram of generating a standard sequence diagram of a golden finger according to the golden finger thumbnails to be tested is shown;

[0048] Figure 8 A schematic diagram showing defect detection using a gold finger profile is shown;

[0049] Fig. 9 It is a structural block diagram of the golden finger image building device provided in the embodiment of the present application;

[0050] Fig.10 It is a structural block diagram of a gold finger defect detection device provided in an embodiment of the present application;

[0051] Fig.11 A structural block diagram of a computer device provided by an exemplary embodiment of the present application is shown. DETAILED DESCRIPTION

[0052] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0053] The term "multiple" as used herein refers to two or more than two. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the related objects are in an "or" relationship.

[0054] Figure 1 : is a flow chart of the golden finger image building method provided in the embodiment of the present application, comprising the following steps:

[0055] S1. Obtain a panoramic image of a standard material board, identify all gold finger contours in the standard material board, and distinguish gold finger types based on gold finger contour features;

[0056] The standard material board does not have any gold finger defects. The PCB board used for modeling, such as Figure 2A possible form of a panorama of a standard material board of a PCB structure is shown, in which several gold finger areas are distributed. The device first performs a synchronization operation to obtain a panoramic image of the corresponding standard material board. Optionally, the image can be binarized, and then edge contour recognition can be performed on the basis of the binarized image to identify all gold finger contours in the image.

[0057] Because the gold fingers on the standard material board are divided into many shapes, the specific shape and type are determined according to the actual PCB function. For example, the gold finger images are divided into typical and atypical categories according to the shape and quantity ratio. The typical gold finger is the gold finger structure whose quantity ratio in the standard material board exceeds the set threshold, and the atypical gold finger is the gold finger structure whose quantity ratio in the standard material board does not exceed the set threshold. Figure 2 Typical gold fingers are strips that occupy the majority of the entire PCB board, while atypical ones are special-shaped structures such as circles, squares, and discontinuous lines. When identifying, matching, identification, and differentiation can be performed based on various contour labels pre-calibrated by the system.

[0058] S2, generating a small gold finger image corresponding to each gold finger outline, and performing image splicing processing on the small gold finger images of the same type according to the preset puzzle rules to generate a gold finger standard sequence image set;

[0059] The gold finger thumbnail is an image extracted from a panoramic image or a binary image according to the recognized contour shape. In order to ensure the later matching and defect detection, the gold finger thumbnail can be selected with a specific size by the circumscribed rectangular frame of the gold finger contour. This step will extract all the gold finger thumbnails in the panoramic image.

[0060] For various types of gold finger thumbnails that have been extracted, in order to facilitate the efficiency of subsequent defect detection, a certain number of gold finger thumbnails can be spliced, that is, the gold finger thumbnails are transferred to a standard image for defect detection, for example, every 10 gold finger thumbnails are spliced ​​into a complete gold finger standard sequence diagram. For a large number of a certain type, this can form multiple gold finger standard sequence diagrams, and different types of gold finger thumbnails each generate corresponding gold finger standard sequence diagrams. For subsequent traceability and matching, each gold finger standard sequence diagram carries the contour information of all gold fingers in the corresponding diagram, so that the location source and corresponding contour features of each gold finger thumbnail can be determined. All gold finger standard sequence diagrams form a gold finger standard sequence diagram set, which can quickly perform defect detection during subsequent material running.

[0061] Figure 3 This is an algorithm flow chart of a possible gold finger image construction method, using typical and atypical gold fingers as examples. Figure 2The strip-shaped gold fingers that account for a relatively large proportion are typical gold fingers, and the corresponding outlines are determined as typical gold finger outlines, while the rest are determined as atypical gold finger outlines and atypical gold fingers.

[0062] In some embodiments, because the shapes and sizes of atypical gold fingers are mostly different, in order to avoid confusion, a gold finger standard sequence diagram is constructed separately, that is, Figure 2 Each atypical cheat code will be assembled individually according to the cheat code thumbnail. Only typical cheat codes will be selected to be combined into a cheat code standard sequence diagram in a certain number. In a possible implementation, 10 cheat code thumbnails are selected as a group for puzzle assembly. The specific steps are as follows:

[0063] A. Extract the corresponding gold finger thumbnail containing the complete gold finger image from the panorama according to the gold finger outline;

[0064] B. According to the position distribution of various types of gold fingers on the standard material board, the extracted gold finger thumbnails are numbered and marked;

[0065] The numbering is specifically performed according to the position of the gold finger. First, the pixel position of all gold finger outlines in the panoramic image is determined, and then the gold fingers of the same type are numbered consecutively according to the pixel position and the preset direction.

[0066] Figure 4 It is a schematic diagram of constructing a standard sequence diagram of a golden finger according to the golden finger thumbnails provided in an embodiment of the present application. Because the size of the panoramic image is large, the thumbnails can be numbered in order from top to bottom and from left to right. Figure 4 The red line box selects a group (5 as a group) for extraction, identification and numbering. The first three in the boxed area are typical gold finger structures, and the fourth and fifth are actually discontinuous atypical gold finger structures. Therefore, the dotted line box is directly determined as an atypical gold finger thumbnail by the number of strips (or two as a whole by area). In order to complete a set of spliced ​​images, (skip the atypical) continue to extract two typical gold finger thumbnails. When continuous numbering is used, the above can be expressed as the numbering sequence of L01, L02, L03, M01, M01, L04, L05. The type can be directly distinguished from the numbering. For typical gold fingers of the same type, they can be numbered consecutively L06, L07, etc.

[0067] C. Splice the target type and target number cheat sheet images into several cheat sheet standard sequence images in the order of numbers, and generate label information based on the contour coordinates of the corresponding target number cheat sheets;

[0068] Figure 4The right part is the standard sequence diagram of the golden finger formed after splicing. This application takes the small picture of the golden finger selected by the frame as an example. In the picture on the right, the 5 images are spliced ​​at the target position according to a specific spacing. The specific spacing is determined according to the actual situation, and this application will not be described in detail. Figure 4 The gold finger standard sequence diagram on the right is arranged in the order of P01-P05, and corresponds to the gold fingers L01-L05 in the panoramic view. The atypical gold fingers in the dotted box form a separate gold finger standard sequence diagram.

[0069] In the above process, for atypical cheating fingers, a single cheating finger thumbnail is selected to independently generate a cheating finger standard sequence diagram, and the label information of the corresponding typical cheating finger is embedded; in the cheating finger standard sequence diagram, the cheating finger thumbnail is mapped to the target position of the image according to the numbering order.

[0070] D. Embed the target number of tag information into the corresponding gold finger standard sequence diagram according to the number, and all gold finger standard sequence diagrams constitute a gold finger standard sequence diagram set.

[0071] Because the small images need to be matched and verified in subsequent defect detection, in order to ensure that the numbering and splicing positions are not set incorrectly due to the gold finger, the label information of the corresponding gold finger outline can be embedded in each gold finger standard sequence diagram. The label information can include the previously identified gold finger outline information, coordinate information and number information (in the panoramic image), etc. Finally, all the gold finger standard sequence diagrams form a gold finger standard sequence diagram set.

[0072] The above are the complete steps of modeling, material building and database building before running. After completing the above steps, the method can be used to perform defect detection on the produced material boards to be tested.

[0073] Figure 5 : is a flow chart of a gold finger defect detection method provided in an embodiment of the present application, comprising the following steps:

[0074] S1. Obtain a panoramic view of the material board to be tested, identify the contours of all gold fingers to be tested in the material board to be tested, and distinguish the types of gold fingers based on the gold finger contour features;

[0075] This step is exactly the same as the step in the aforementioned material building stage, the only difference being that the material board here is the material board to be tested.

[0076] S2, generating a small image of a gold finger to be tested corresponding to each gold finger outline, performing image splicing processing on small images of gold fingers to be tested of the same type according to a preset jigsaw puzzle rule, and generating a set of gold finger images to be sequenced;

[0077] The core implementation of splicing and generating the gold finger to be sequenced map is similar to the previous step, which is to merge the gold finger to be tested small map into the target position of the gold finger to be sequenced map according to a certain number and type, and at the same time, the outline information, outline coordinates and numbering of the small gold finger to be tested in the panoramic map are labeled and embedded into the map. For details, please refer to the steps of building materials to obtain the gold finger standard sequence map. It should be noted that because the overall structure of the material board is consistent with the distribution of gold fingers, the process of generating the gold finger to be sequenced map should also be generated in the order of extracting gold finger small maps, numbering and splicing according to the material building process, so as to ensure that the number of gold fingers to be tested contained in the gold finger to be sequenced map and the gold fingers in the gold finger standard sequence map satisfy a one-to-one mapping relationship.

[0078] S3. Detect the gold finger defects in the gold finger sequence diagram set based on the gold finger standard sequence diagram set, and convert the gold finger defects detected in the gold finger sequence diagram to be sequenced into the panoramic diagram of the material board to be tested.

[0079] In particular, the gold finger standard sequence diagram set is obtained after identification and splicing based on the panoramic image of the standard material board. The core of gold finger defect detection is to match the standard gold finger thumbnail with the gold finger thumbnail to be tested taken of the material board to be tested, and determine the defect area according to the difference in the gold finger contour area, that is, the area where the gold finger on the material board to be tested is missing or protruding. Because the gold finger thumbnail to be tested in the previous process is spliced ​​to the target position in the gold finger sequence diagram in a certain numbering order and quantity, the defective area of ​​the gold finger can be determined in batches by making a pixel-level difference between the images. After that, the gold finger defects are converted into the panoramic image of the material board to be tested, and the defective gold finger and defective area position of the material board to be tested can be determined.

[0080] In summary, the present application identifies the outline of the gold finger on the standard material board and classifies the gold finger, extracts the gold finger thumbnail with the gold finger outline, and splices the thumbnails of different types of gold finger thumbnails according to the numbering sequence and type rules to generate multiple gold finger standard sequence diagram sets;

[0081] In the material running stage, the panoramic image of each material board to be tested uses the same contour recognition method to extract the contour of the gold finger to be tested and extract the small image of the gold finger to be tested; then the small image of the gold finger to be tested is spliced ​​according to the numbering and type rules to form a gold finger sequence map that is mapped to the gold finger standard sequence map, and then the defect area of ​​each gold finger on the material board to be tested is determined by subtraction from the contour area surrounded by the pixel level, realizing non-AI recognition defect detection. This solution uses image modeling and segmentation matching methods for defect detection, which is more accurate than traditional AI recognition and avoids the problem of insufficient detection due to color difference.

[0082] Figure 6This is an algorithm flow chart of a possible gold finger defect detection method. It is also explained by taking typical and atypical gold fingers as examples. In the material running stage, the data of the material building process, that is, the gold finger standard sequence diagram set, is read. After identifying the typical and atypical gold finger contours and extracting the gold finger thumbnails to be tested, the steps of generating the gold finger sequence diagram set to be sequenced are executed, which may specifically include the following steps:

[0083] A. According to the position distribution of each type of gold finger to be tested on the material board to be tested, the extracted small pictures of various gold fingers to be tested are numbered and marked;

[0084] The numbering process of this step is consistent with the numbering strategy of the aforementioned material building process. The gold finger types are distinguished according to the types. The gold finger types include at least typical gold fingers and atypical gold fingers. When the gold finger to be tested is an atypical gold finger type, the gold finger to be sequenced map is directly generated according to the extracted gold finger thumbnail to be tested; when the gold finger to be tested is a typical gold finger type, the gold finger to be sequenced map is generated by splicing according to the gold finger type and numbering order.

[0085] B. Get the label information of the cheating outline contained in each cheating standard sequence diagram in the cheating standard sequence diagram set;

[0086] The process of generating the gold finger sequence map in this step is slightly different from the aforementioned material building step, and the material board here may contain defects. When the material board to be tested is also defect-free, the splicing process is no different from the aforementioned process, but when there are some serious gold finger defects on the material board to be tested here, and the gold finger area is so small that it leads to missed detection, etc., the spliced ​​gold finger sequence map may miss one or more small gold finger images to be tested, resulting in an error in the final matching. In response to this situation, this application needs to obtain the label information of the gold finger outline contained in the corresponding gold finger standard sequence diagram during splicing, and determine whether to place the defective small image to be tested in the target position based on the label information.

[0087] C. Based on the label information of the corresponding gold finger standard sequence diagram, the small gold finger diagrams to be tested of the target type are spliced ​​in the order of numbers to generate a gold finger sequence diagram, and the label information is generated based on the contour coordinates of the target number of gold fingers to be tested;

[0088] This step mainly considers the situation where the defect thumbnail to be tested is lost during the cutout (for example, the gold surface of the gold finger is completely peeled off during production and cannot be identified). This requires matching verification based on the position and number. The specific method can be determined as follows:

[0089] 1) Obtain the number of small gold finger images to be tested contained in the gold finger to be sequenced image;

[0090] 2) Extract the target type of gold finger small picture to be tested to the target position of the gold finger to be sequenced map in the order of numbering, and match it according to the label information of the gold finger small picture at the corresponding position in the gold finger standard sequence map;

[0091] Figure 7 The schematic diagram of generating a standard sequence diagram of gold fingers based on the small image of gold fingers to be tested is shown. In the red framed area in the schematic diagram, the gold surface of the first typical gold finger that should exist is completely peeled off and cannot be identified, so when numbering, only the second typical gold finger in the framed area can be numbered as the first, and so on. Assuming that the small image of the gold finger to be tested of the second typical gold finger is directly spliced ​​to the "W01" target position in the gold finger sequence diagram, this will cause all subsequent sequences to be wrong, and then the calculation of the defective area will also be wrong. After extracting the label information of the corresponding standard sequence diagram of the gold finger, it is possible to judge whether the spliced ​​gold finger sequence diagram satisfies the mapping relationship with the standard sequence diagram of the gold finger based on the label information (contour coordinates).

[0092] 3) When the outline coordinate information and the gold finger type of the gold finger thumbnail to be tested do not match the label information of the gold finger thumbnail, fill the target position of the gold finger to be sequenced with a blank thumbnail and add the blank gold finger outline coordinates;

[0093] If the match is wrong, it means that there should be a gold surface peeling and cannot be recognized, so a blank small picture is automatically added to fill in the "W01" target position to explain this.

[0094] Assuming the scenario is step 3), continue splicing according to the number, where Figure 7 The atypical gold finger in the red dotted box is also sampled by the above theory for separate splicing and fusion. Assuming that the gold surface of a single atypical gold finger is peeled off, the gold finger on the "lost" gold surface can be determined based on the difference in the number of gold finger sequencing maps, and then a gold finger sequencing map containing a blank small map can be generated separately. Figure 6 The image to be tested is the candidate cheating image to be sequenced formed by splicing the numbers of the cheating small images to be tested. The template image is the corresponding cheating standard sequence image. The position label matching can determine whether there is misalignment and loss, so as to ensure the correct output of the accurate sequence image.

[0095] exist Figure 7 In the figure, the last gold finger thumbnail is broken or dirty, and the gold finger thumbnail to be tested that is spliced ​​and mapped to the target position "W05" also has cracks.

[0096] 4) When the outline coordinate information and the cheating type of the cheating thumbnail to be tested match the label information of the cheating thumbnail, the cheating thumbnail to be tested is spliced ​​to the target position of the cheating thumbnail to be sequenced, and the corresponding cheating outline coordinates are added;

[0097] D. Embed the target number of label information into the corresponding gold finger sequence map according to the number, and all gold finger standard sequence maps constitute the gold finger standard sequence map set.

[0098] All the gold finger images to be tested are matched according to the numbering sequence and the label information of the corresponding gold finger images until the target number is reached to generate the gold finger sequencing image.

[0099] In some embodiments, the step of detecting gold finger defects in the gold finger sequence diagram set according to the gold finger standard sequence diagram set can be implemented by the following steps:

[0100] A. Position matching and mapping of the corresponding gold finger standard sequence diagram and the gold finger sequence diagram to be tested are performed, and the defect area of ​​the gold finger to be tested is determined according to the area difference surrounded by the two gold finger contour coordinates;

[0101] Figure 8 The schematic diagram of defect detection based on the gold finger contour is shown. The W05 target position and the P05 target position in the standard sequence diagram are the matching process of defects. The two small images can be directly overlapped according to the edge contour, and the defective part of the dotted line can be determined according to the difference in the contour edge. The same applies to protruding defects. For the case where a blank small image is filled, it corresponds to a complete gold finger missing defect.

[0102] B. Map the defect area coordinates to the panoramic view of the material board to be tested, and determine the defect coordinates of the defect area in the panoramic view.

[0103] The above process is to perform contour matching and difference calculation based on the position relationship of the gold finger to be sequenced. After calculating the position of the area, it is remapped to the panoramic view of the material board to be tested. You can then make a box mark or use other line marks in the panoramic view to remind the operator that the gold finger at that position has a defect.

[0104] Compared with the method of using AI image recognition defects, the above method does not need to consider the missed detection, false detection and low detection rate caused by light and angle chromatic aberration, and can greatly improve the detection accuracy and efficiency of gold fingers on PCB boards.

[0105] Fig. 9 : is a structural block diagram of a golden finger image building device provided in an embodiment of the present application, comprising:

[0106] The first recognition module 910 is used to obtain a panoramic view of the standard material board, identify all gold finger contours in the standard material board, and distinguish gold finger types based on gold finger contour features;

[0107] The first stitching module 920 is used to generate a small gold finger image corresponding to each gold finger outline, and stitch the gold finger images of the same type according to the preset stitching rules to generate a gold finger standard sequence image set, wherein each gold finger standard sequence image carries the outline information of all gold fingers in the corresponding image.

[0108] Fig.10 : is a structural block diagram of a gold finger defect detection device provided in an embodiment of the present application, comprising:

[0109] The second identification module 1010 is used to obtain a panoramic view of the material board to be tested, identify the contours of all the gold fingers to be tested in the material board to be tested, and distinguish the types of gold fingers based on the gold finger contour features;

[0110] The second splicing module 1020 is used to generate a small image of a gold finger to be tested corresponding to each gold finger contour, and perform image splicing processing on the small images of gold fingers to be tested of the same type according to a preset jigsaw puzzle rule to generate a set of gold finger to be sequenced images, wherein each gold finger to be sequenced image carries the contour information of all gold fingers to be tested in the image;

[0111] The detection module 1030 is used to detect the gold finger defects in the gold finger sequence diagram set based on the gold finger standard sequence diagram set, and convert the gold finger defects detected in the gold finger sequence diagram to be sequenced into the panoramic diagram of the material board to be tested; the gold finger standard sequence diagram set is obtained after identification and splicing based on the panoramic diagram of the standard material board.

[0112] The gold finger defect detection device provided in the embodiment of the present application can be applied to the gold finger defect detection method provided in the above embodiment. For relevant details, refer to the above method embodiment. The implementation principle and technical effect are similar and will not be repeated here.

[0113] It should be noted that the gold finger defect detection device provided in the embodiment of the present application is only illustrated by the division of the above-mentioned functional modules / functional units. In practical applications, the above-mentioned functions can be assigned to different functional modules / functional units as needed, that is, the internal structure of the gold finger defect detection device is divided into different functional modules / functional units to complete all or part of the functions described above. In addition, the implementation method of the gold finger defect detection method provided in the above method embodiment and the implementation method of the gold finger defect detection device provided in this embodiment belong to the same concept. The specific implementation process of the gold finger defect detection device provided in this embodiment is detailed in the above method embodiment, which will not be repeated here.

[0114] Fig.11The block diagram of a computer device provided by an exemplary embodiment of the present application is shown. It is a computer device such as a desktop computer, a laptop computer, a PDA, and a cloud server. The computer device may include, but is not limited to, a processor and a memory. Among them, the processor and the memory may be connected by a bus or in other ways. Among them, the processor may be a central processing unit (CPU). The processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, graphics processors (GPU), embedded neural network processors (NPU) or other dedicated deep learning coprocessors, discrete gates or transistor logic devices, discrete hardware components and other chips, or a combination of the above-mentioned various chips.

[0115] The processor may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content that needs to be displayed on the display screen. In some embodiments, the processor may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0116] As a non-transient computer-readable storage medium, the memory can be used to store non-transient software programs, non-transient computer executable programs and modules, such as program instructions / modules corresponding to the methods in the above-mentioned embodiments of the present application. The processor executes various functional applications and data processing of the processor by running the non-transient software programs, instructions and modules stored in the memory, that is, the method in the above-mentioned method implementation is realized. The memory may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created by the processor, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network and a combination thereof.

[0117] In some embodiments, the computer device may further optionally include: a peripheral device interface and at least one peripheral device. The processor, the memory and the peripheral device interface may be connected via a bus or a signal line. Each peripheral device may be connected to the peripheral device interface via a bus, a signal line or a circuit board. Specifically, the peripheral device includes: at least one of a radio frequency circuit, a display screen and a keyboard.

[0118] The peripheral device interface can be used to connect at least one peripheral device related to I / O (Input / Output) to the processor and the memory. In some embodiments, the processor, the memory, and the peripheral device interface are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor, the memory, and the peripheral device interface can be implemented on a separate chip or circuit board, which is not limited in this embodiment.

[0119] The display screen is used to display the UI (User Interface). The UI may include graphics, text, icons, videos and any combination thereof. When the display screen is a touch screen, the display screen also has the ability to collect touch signals on the surface or above the surface of the display screen. The touch signal can be input to the processor as a control signal for processing. At this time, the display screen can also be used to provide virtual buttons and / or virtual keyboards, also known as soft buttons and / or soft keyboards. In some embodiments, the display screen can be one, arranged on the front panel of the computer device; in other embodiments, the display screen can be at least two, respectively arranged on different surfaces of the computer device or in a folding design; in other embodiments, the display screen can be a flexible display screen, arranged on a curved surface or a folding surface of the computer device. Even, the display screen can be set to a non-rectangular irregular shape, that is, a special-shaped screen. The display screen can be made of materials such as LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode) and the like.

[0120] The power supply is used to power various components in the computer device. The power supply can be AC, DC, a disposable battery, or a rechargeable battery. When the power supply includes a rechargeable battery, the rechargeable battery can be a wired rechargeable battery or a wireless rechargeable battery. A wired rechargeable battery is a battery that is charged through a wired line, and a wireless rechargeable battery is a battery that is charged through a wireless coil. The rechargeable battery can also be used to support fast charging technology.

[0121] Those skilled in the art will appreciate that the structure shown in this embodiment does not constitute a limitation on the computer device, and may include more or fewer components than shown in the figure, or combine certain components, or adopt a different component arrangement.

[0122] The embodiment of the present application also discloses a computer-readable storage medium. Specifically, the computer-readable storage medium is used to store a computer program, and when the computer program is executed by the processor, the method in the above-mentioned method implementation is implemented. Those skilled in the art can understand that the implementation of all or part of the process in the above-mentioned implementation method of the present application can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the process of the implementation of the above-mentioned methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory (Flash Memory), a hard disk (Hard Disk Drive, abbreviated as: HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above-mentioned types of memory.

[0123] This specific embodiment is merely an explanation of the present invention and is not a limitation of the present invention. After reading this specification, those skilled in the art may make non-creative modifications to the present embodiment as needed. However, as long as they are within the scope of the claims of the present invention, they are protected by the patent law.

Claims

1. A method for building a golden finger image, characterized in that: The method comprises: Obtain a panoramic view of the standard material board, identify all gold finger contours in the standard material board, and distinguish gold finger types based on gold finger contour features; Generate a small cheat image corresponding to each cheat outline, perform image splicing on the same type of cheat images according to preset puzzle rules, and generate a set of cheat standard sequence images, where each cheat standard sequence image carries the outline information of all cheats in the corresponding image.

2. The method according to claim 1, characterized in that The distinguishing the gold finger type based on the gold finger contour feature includes: Match the identified gold finger contour features with contour feature labels to determine the gold finger types of all gold finger contours; The gold finger types include at least typical gold fingers and atypical gold fingers. The typical gold fingers are gold finger structures whose quantity proportion in the standard material board exceeds the set threshold, and the atypical gold fingers are gold finger structures whose quantity proportion in the standard material board does not exceed the set threshold.

3. The method according to claim 2, characterized in that The step of generating a small cheat image corresponding to each cheat outline, and performing image splicing processing on the small cheat images of the same type according to a preset puzzle rule to generate a set of cheat standard sequence images includes: Extract the corresponding small gold finger image containing the complete gold finger image from the panorama according to the gold finger outline; According to the position distribution of various types of gold fingers on the standard material board, the extracted gold finger thumbnails are numbered and marked; The cheating finger images of the target type and target quantity are spliced ​​into several cheating finger standard sequence images in the order of number, and label information is generated based on the contour coordinates of the cheating fingers of the corresponding target quantity; The target number of tag information is embedded into the corresponding gold finger standard sequence diagram according to the number, and all gold finger standard sequence diagrams constitute a gold finger standard sequence diagram set.

4. The method according to claim 3, characterized in that For typical cheating fingers, select a target number of cheating finger thumbnails corresponding to typical cheating fingers with consecutive numbers and splice them to form a cheating finger standard sequence diagram, and the corresponding cheating finger standard sequence diagram is embedded with the label information of the corresponding cheating finger; For atypical cheat codes, select a single cheat code thumbnail to independently generate a cheat code standard sequence diagram, and embed the label information of the corresponding typical cheat code; In the gold finger standard sequence diagram, the gold finger thumbnails are mapped to the target position of the image according to the numbering order.

5. The method according to claim 3, characterized in that: According to the position distribution of various types of gold fingers on the standard material board, the extracted gold finger thumbnails are numbered and marked, including: Determine the pixel positions of all gold finger outlines in the panorama, and number them in sequence according to the pixel positions and preset directions, and gold fingers of the same type are numbered consecutively.

6. A gold finger defect detection method, characterized in that: The method comprises: Obtain a panoramic view of the material board to be tested, identify the contours of all gold fingers to be tested in the material board to be tested, and distinguish the types of gold fingers based on the gold finger contour features; Generate a small picture of the gold finger to be tested corresponding to each gold finger outline, perform image splicing processing on the small pictures of the gold fingers to be tested of the same type according to the preset puzzle rules, and generate a set of gold finger pictures to be sequenced, wherein each gold finger picture to be sequenced carries the outline information of all the gold fingers to be tested in the picture; Based on the gold finger standard sequence diagram set, the gold finger defects in the gold finger sequence diagram set are detected, and the gold finger defects detected in the gold finger sequence diagram are converted into the panoramic diagram of the material board to be tested; the gold finger standard sequence diagram set is obtained after identification and splicing based on the panoramic diagram of the standard material board.

7. The method according to claim 6, characterized in that The method of performing image splicing processing on small gold finger images to be tested of the same type according to preset jigsaw puzzle rules to generate a gold finger image set to be sequenced includes: According to the position distribution of various types of gold fingers to be tested on the material board to be tested, the extracted small pictures of various types of gold fingers to be tested are numbered and marked; Get the label information of the cheating outline contained in each cheating standard sequence diagram in the cheating standard sequence diagram set; Based on the label information of the corresponding gold finger standard sequence diagram, the small gold finger images to be tested of the target type are spliced ​​in the order of numbers to generate a gold finger sequence diagram, and the label information is generated based on the contour coordinates of the target number of gold fingers to be tested; The target number of label information is embedded into the corresponding gold finger sequence diagram according to the number, and all gold finger standard sequence diagrams constitute a gold finger standard sequence diagram set.

8. The method according to claim 7, characterized in that Based on the label information of the corresponding gold finger standard sequence diagram, the gold finger small images to be tested of the target type are spliced ​​in the order of numbers to generate the gold finger sequence diagram to be sequenced, including: Get the number of small gold finger images to be tested contained in the gold finger to be sequenced image; Extract the target type of gold finger small image to be tested to the target position of the gold finger sequence map in the order of numbering, and match it according to the label information of the gold finger small image at the corresponding position in the gold finger standard sequence map; When the outline coordinate information and the cheating type of the cheating finger thumbnail to be tested do not match the label information of the cheating finger thumbnail, the target position of the cheating finger to be sequenced is filled with a blank thumbnail and blank cheating finger outline coordinates are added; When the outline coordinate information and the cheating type of the cheating thumbnail to be tested match the label information of the cheating thumbnail, the cheating thumbnail to be tested is spliced ​​to the target position of the cheating thumbnail to be sequenced, and the corresponding cheating outline coordinates are added.

9. The method according to claim 8, characterized in that The gold finger types include at least typical gold fingers and atypical gold fingers. When the gold finger to be tested is an atypical gold finger type, a gold finger sequence map is directly generated according to the extracted gold finger small map to be tested; when the gold finger to be tested is a typical gold finger type, a gold finger sequence map is generated by splicing according to the gold finger type and numbering order.

10. The method according to claim 8, characterized in that The method of detecting the gold finger defects in the gold finger sequence diagram set based on the gold finger standard sequence diagram set, and converting the gold finger defects detected in the gold finger sequence diagram to be sequenced into the panoramic diagram of the material board to be tested, includes: The corresponding gold finger standard sequence diagram and the gold finger sequence diagram to be sequenced are matched and mapped, and the defect area of ​​the gold finger to be tested is determined according to the area difference surrounded by the two gold finger contour coordinates; the blank small image filled corresponds to the gold finger missing defect; Map the defect area coordinates to the panoramic view of the material board to be tested, and determine the defect coordinates of the defect area in the panoramic view.

Images