Detection method and system for intelligent chip in circuit board

Abstract

The invention relates to the technical field of intelligent chip detection, in particular to a detection method and system for an intelligent chip in a circuit board, and the method comprises the steps: obtaining the image data of the intelligent chip and the image data of a reference target, obtaining a positioning target, amplifying the two image data to be consistent, carrying out the positioning, and building a two-dimensional coordinate system; dividing the two images according to the functional areas; obtaining coordinates of a to-be-detected target and coordinates of a reference target; positioning a first detection target and a first reference target according to the coordinates, and detecting a first detection result according to an image recognition algorithm; positioning a second detection target and a second reference target according to the coordinates, and determining a second detection result according to a dynamic path algorithm; through the method, a small detection target can be accurately positioned, corresponding chip internal circuit connection lines can be detected, the conditions of missing detection and error detection can be reduced through the identified target coordinates, and the accuracy of intelligent chip detection is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent chip detection, and specifically provides a detection method and system for intelligent chips in a circuit board. Background Art

[0002] As one of the core components of current intelligent integrated circuits, the quality of intelligent chips determines whether the entire intelligent integrated circuit can operate normally and accurately. Most of the existing technologies lack effective image recognition and coordinate system construction mechanisms, making it difficult to perform precise spatial mapping on intelligent chip images, resulting in the inability to achieve refined area analysis and identification position matching during subsequent detection processes, and thus reducing the accuracy rate of intelligent chip quality detection.

[0003] Therefore, a detection method and system for intelligent chips in a circuit board are proposed. Summary of the Invention

[0004] The purpose of the present invention is to provide a detection method and system for intelligent chips in a circuit board. By obtaining intelligent chip image data and reference target image data, after magnifying the two image data to the same scale and obtaining the positioning target, a two-dimensional coordinate system is established for positioning, and the two images are divided according to functional areas; the coordinates of the target to be detected and the coordinates of the reference target are obtained; the first detection target and the first reference target are located according to the coordinates, and the first detection result is detected according to the image recognition algorithm; the second detection target and the second reference target are located according to the coordinates, and the second detection result is determined according to the dynamic path algorithm. Through this method, precise positioning of smaller detection targets can be achieved, and at the same time, the internal circuit connections of the corresponding chips can be detected. The situation of missed detection and misdetection can also be reduced through the recognized target coordinates, improving the accuracy rate of intelligent chip detection.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A detection method for intelligent chips in a circuit board, comprising:

[0007] Obtaining intelligent chip image data and first reference target image data;

[0008] Positioning the first reference target image data with the intelligent chip image data, establishing a two-dimensional coordinate system for the intelligent chip image data and the first reference target image data, and dividing the intelligent chip image data and the first reference target image data into multiple intelligent chip detection areas and multiple reference detection areas;

[0009] Obtaining a first coordinate set and a second coordinate set of the intelligent chip detection area according to the two-dimensional coordinate system and the intelligent chip detection area; obtaining a first reference coordinate set and a second reference coordinate set of the reference detection area according to the two-dimensional coordinate system and the reference detection area;

[0010] Calculate the first similarity between the first coordinate set and the first reference coordinate set, and obtain the first detection target and the first reference target based on the first similarity; identify and compare the first detection target and the first reference target to generate the first detection result;

[0011] Obtain the second detection target through the second coordinate set, and obtain the second reference target through the second reference coordinate set; based on the second detection target and the second reference target; calculate the second similarity between the second detection target and the second reference target, and generate the second detection result;

[0012] Judge whether the intelligent chip is qualified according to the first detection result and the second detection result.

[0013] Preferably, the intelligent chip image data locates the first reference target image data, including:

[0014] Obtain the type data and morphological data of the first positioning target of the intelligent chip image data according to the first image recognition algorithm; traverse the first reference target image data through the first image recognition algorithm to obtain the preselected reference targets with the same type data;

[0015] Calculate the similarity of the preselected reference targets according to the morphological data, and obtain the second positioning target according to the maximum similarity value; through the first positioning target and the second positioning target, locate the intelligent chip image data and the first reference target image data.

[0016] Preferably, the number of the first positioning targets is not less than 3.

[0017] Preferably, obtaining the first coordinate set and the second coordinate set of the intelligent chip detection area according to the two-dimensional coordinate system and the intelligent chip detection area; obtaining the first reference coordinate set and the second reference coordinate set of the reference detection area according to the two-dimensional coordinate system and the reference detection area includes:

[0018] Identify the first target and the second target of the intelligent chip detection area or the reference detection area according to the second image recognition algorithm; the first target is the first target candidate box, and the second target includes the second key points and the second key lines; the second key lines and the second key points are associated through the association tags;

[0019] Obtain the center point coordinates of the first target candidate box of the intelligent chip detection area according to the two-dimensional coordinate system, generate the first target coordinates of the intelligent chip detection area and obtain the first coordinate set;

[0020] Obtain the central point coordinates of the first target candidate box of the reference detection area according to the two-dimensional coordinate system, generate the first target coordinates of the reference detection area, and obtain the first reference coordinate set;

[0021] Obtain the second key point coordinates of the intelligent chip detection area according to the two-dimensional coordinate system, generate the second target coordinates of the intelligent chip detection area, and obtain the second coordinate set; Obtain the second key point coordinates of the reference detection area according to the two-dimensional coordinate system, generate the second target coordinates of the reference detection area, and obtain the second reference coordinate set.

[0022] Preferably, identify and compare the first detection target and the first reference target, and the generated first detection result includes:

[0023] Identify the first detection target and the first reference target through the second image recognition algorithm; Compare according to the ASCII code of the recognition result of the second image recognition algorithm, and generate the first detection result according to the comparison result of the ASCII code.

[0024] Preferably, according to the second detection target and the second reference target; Calculate the second similarity between the second detection target and the second reference target, and the generated second detection result includes:

[0025] Obtain the associated second key line according to the second coordinate set to generate the second detection target;

[0026] Obtain the associated second key line according to the second reference coordinate set and the associated label to generate the second reference target;

[0027] Map the second detection target and the second reference target to a grid of size n*n according to the dynamic path algorithm to generate a detection grid; Map the second reference target to a grid of size n*n according to the dynamic path algorithm to generate a reference grid; Calculate the similarity between the detection grid and the reference grid to generate the second detection result.

[0028] A detection system for intelligent chips in a circuit board, comprising:

[0029] A data acquisition module that acquires intelligent chip image data and first reference target image data;

[0030] A detection area and reference area determination module that locates the first reference target image data from the intelligent chip image data, establishes a two-dimensional coordinate system for the intelligent chip image data and the first reference target image data, and divides the intelligent chip image data and the first reference target image data into multiple intelligent chip detection areas and multiple reference detection areas;

[0031] A coordinate generation module obtains a first coordinate set and a second coordinate set of the intelligent chip detection area according to the two-dimensional coordinate system and the intelligent chip detection area; obtains a first reference coordinate set and a second reference coordinate set of the reference detection area according to the two-dimensional coordinate system and the reference detection area;

[0032] A first detection module calculates a first similarity between the first coordinate set and the first reference coordinate set, and obtains a first detection target and a first reference target according to the first similarity; identifies and compares the first detection target and the first reference target, and generates a first detection result;

[0033] A second detection module obtains a second detection target through the second coordinate set and a second reference target through the second reference coordinate set; calculates a second similarity between the second detection target and the second reference target according to the second detection target and the second reference target, and generates a second detection result;

[0034] A detection and judgment module determines whether the intelligent chip is qualified according to the first detection result and the second detection result.

[0035] Preferably, for the detection area and reference area determination module, the first reference target image data located by the intelligent chip image data includes:

[0036] Obtain the type data and morphological data of the first positioning target of the intelligent chip image data according to the first image recognition algorithm; traverse the first reference target image data through the first image recognition algorithm to obtain the preselected reference targets with the same type data;

[0037] Calculate the similarity of the preselected reference targets according to the morphological data, and obtain the second positioning target according to the maximum similarity value; locate the intelligent chip image data and the first reference target image data through the first positioning target and the second positioning target.

[0038] Preferably, the number of the first positioning targets is not less than 3.

[0039] Preferably, for the second detection module, calculating the second similarity between the second detection target and the second reference target according to the second detection target and the second reference target, and generating the second detection result includes:

[0040] Obtain the associated second key line according to the second coordinate set, and generate a second detection target;

[0041] Obtain the associated second key line according to the second reference coordinate set and the associated label, and generate a second reference target;

[0042] Map the second detection target and the second reference target onto a grid of size n*n according to the dynamic path algorithm to generate a detection grid; map the second reference target onto a grid of size n*n according to the dynamic path algorithm to generate a reference grid; calculate the similarity between the detection grid and the reference grid to generate the second detection result.

[0043] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0044] 1. The present invention automatically identifies and determines the positioning targets of the same type of the intelligent chip and the reference target through the image recognition algorithm, calculates the similarity of the morphological data through the identified positioning targets, and further determines the positioning targets with the maximum similarity. Through this method, the positions and sizes of the intelligent chip and the reference target can be unified, which is convenient for generating corresponding coordinates for the target to be detected in the subsequent coordinate system generation for positioning and recognition, facilitating the subsequent detection work and improving the accuracy of quality detection.

[0045] 2. The present invention generates a coordinate system for the positioned intelligent chip and the reference target, and generates corresponding coordinates through the identification of the identification of the parts to be detected by the image recognition algorithm. This method can accurately locate the positions in the case of a large number of detection targets of the intelligent chip, and at the same time, based on the coordinates of the dual recognition targets, it can avoid missing the identification of the parts to be detected, improving the accuracy of quality detection.

[0046] 3. The present invention identifies the key points and key lines of the connection lines on the intelligent chip. Through the key points, a large number of connection lines can be located. At the same time, based on the label and region division, the positions of the internal circuit connection lines of the intelligent chip to be detected can be further determined to correspond to the connection lines to be detected of the reference target, so as to improve the accuracy of detection and avoid misdetection and missed detection; based on the dynamic path algorithm, the internal circuit connection lines of the chip can be detected, and at the same time, it can be determined whether there are position offsets, open circuits, etc. in the internal circuit connection lines of the chip, further improving the accuracy of quality detection of the internal circuit connection lines of the intelligent chip. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a schematic diagram of the method flow of the present invention;

[0048] Figure 2 It is a schematic diagram of the generation process of the associated labels of the second key points and the second key lines of the present invention;

[0049] Figure 3 It is a schematic diagram of the reference grid after calculating the second reference target by the dynamic path algorithm of the present invention;

[0050] Figure 4 It is a schematic diagram of the system flow of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0051] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0052] Embodiment 1

[0053] In order to improve the accuracy of quality inspection of the A intelligent chip, a detection method for intelligent chips in a circuit board is applied; as shown in Figure 1 shown, it includes:

[0054] Obtain intelligent chip image data and first reference target image data; the intelligent chip image data is obtained by a high-resolution industrial camera; the first reference target image data is a standard intelligent chip image;

[0055] The intelligent chip image data locates the first reference target image data; further, the intelligent chip image data locating the first reference target image data includes:

[0056] Obtain the type data and morphological data of the first positioning target of the intelligent chip image data according to the first image recognition algorithm; traverse the first reference target image data through the first image recognition algorithm to obtain the preselected reference targets with the same type data; the first image recognition algorithm is the yolov5 algorithm;

[0057] Since the intelligent chip is usually approximately rectangular, in order to accurately determine the position, referring to the principle of triangular positioning, at least 3 positioning targets are selected for positioning. The selection of the positioning targets and the quantity needs to comprehensively consider expert experience and the actual situation of the intelligent chip. Among them, the type data of the positioning targets cannot be the same. Such a setting helps to more accurately locate, reduce the error of the image recognition algorithm, improve the accuracy of positioning, and thus ensure the accuracy of subsequent detection. Further, the number of the first positioning targets is not less than 3.

[0058] Calculate the similarity of the preselected reference targets according to the morphological data, and obtain the second positioning target according to the maximum similarity value; through the first positioning target and the second positioning target, locate the intelligent chip image data and the first reference target image data.

[0059] Obtain the first coordinate set and the second coordinate set of the intelligent chip detection area according to the two-dimensional coordinate system and the intelligent chip detection area;

[0060] Establish a two-dimensional coordinate system for the intelligent chip image data and the first reference target image data, and divide the intelligent chip image data and the first reference target image data into multiple intelligent chip detection regions and multiple reference detection regions;

[0061] The intelligent chip detection regions and the reference detection regions are divided into multiple regions according to the internal structure of the intelligent chip, which can reduce the computational complexity during recognition and detection and improve the accuracy of detection. The specific division method can be either according to the physical structure of the intelligent chip or according to the functional modules of the chip. The specific scheme needs to be determined in combination with the actual situation of the intelligent chip and expert experience.

[0062] Further, obtain the first coordinate set and the second coordinate set of the intelligent chip detection region according to the two-dimensional coordinate system and the intelligent chip detection region; obtain the first reference coordinate set and the second reference coordinate set of the reference detection region according to the two-dimensional coordinate system and the reference detection region;

[0063] Further, obtaining the first reference coordinate set and the second reference coordinate set of the reference detection region according to the two-dimensional coordinate system and the reference detection region includes:

[0064] Identify the first target and the second target of the intelligent chip detection region or the reference detection region according to the second image recognition algorithm; the first target is the first target candidate box, and the second target includes the second key points and the second key lines; the second key lines and the second key points are associated through association tags;

[0065] The second image recognition algorithm includes the yolov5 algorithm and the DeepLSD algorithm. The yolov5 algorithm is used to obtain the first target and generate the first target candidate box after identifying the first target. Here, the first target is a specific identifier on the intelligent chip, such as a chip model identifier, a functional module identifier, etc. The DeepLSD algorithm is used to obtain the second key points and the second key lines on the second target. The second target is the internal circuit connection of the intelligent chip, the second key points are the starting point and the ending point of the circuit connection, and the second key line is the internal circuit connection of the chip.

[0066] Further, referring to Figure 2 As shown, the generation process of the association tags for the second key lines and the second key points is as follows: Perform secondary recognition on the second target according to the yolov5 algorithm. The recognition result is two points and a line connecting the two points. Generate a candidate box based on the recognition result of the yolov5 algorithm and generate the corresponding candidate box label; Perform three times of recognition on the points and lines within the candidate box using the yolov5 algorithm, and generate the corresponding starting point label, ending point label, and line label for the starting point, ending point, and line according to the candidate box label;

[0067] Obtain the center point coordinates of the first target candidate box in the intelligent chip detection area according to the two-dimensional coordinate system, generate the first target coordinates of the intelligent chip detection area and obtain the first coordinate set; obtain the center point coordinates of the first target candidate box in the reference detection area according to the two-dimensional coordinate system, generate the first target coordinates of the reference detection area and obtain the first reference coordinate set;

[0068] Obtain the coordinates of the second key points in the intelligent chip detection area according to the two-dimensional coordinate system, generate the second target coordinates of the intelligent chip detection area and obtain the second coordinate set; obtain the coordinates of the second key points in the reference detection area according to the two-dimensional coordinate system, generate the second target coordinates of the reference detection area and obtain the second reference coordinate set. The image recognition algorithm recognizes the features or identifiers of each component of the intelligent chip in the first target area, including the position features of the unmounted components and the identifier features of the mounted components.

[0069] By constructing a coordinate system for the intelligent chip to be detected and the reference target after positioning, and using the image recognition algorithm to recognize the target to be detected and the reference target, corresponding data is generated. This method can accurately determine the position of the target to be detected, effectively avoiding misdetection. At the same time, the coordinate data can be used as a basis during the detection process to prevent omission when identifying the intelligent chip to be detected, and can also provide corresponding position and corresponding quantity information to avoid missed detection, thereby improving the accuracy of detection;

[0070] Calculate the first similarity between the first coordinate set and the first reference coordinate set, and the first similarity is obtained by calculating the Pearson coefficient; obtain the first detection target and the first reference target according to the first similarity; identify and compare the first detection target and the first reference target to generate the first detection result;

[0071] Further, the second image recognition algorithm is used to recognize the first detection target and the first reference target. Among them, the first detection target and the first reference target cover various identifiers on the intelligent chip, such as chip model identifiers, functional area identifiers, etc. These identifiers are presented in the form of numbers, letters or specific symbols, and will be converted into ASCII codes after recognition. A detailed comparison is made based on the ASCII codes corresponding to the recognition results of the second image recognition algorithm. Since the ASCII code not only contains the numbers or letters in the identifier, but also includes the function module number or component number associated with the corresponding feature. With the two-dimensional coordinate system constructed previously, it is possible to accurately locate numerous detection targets on the intelligent chip. Through these clear and unique identifiers, it is possible to accurately judge whether there are incorrect identifiers, unclear identifiers on the chip, and whether there are component misinstallations or omissions during the chip manufacturing process. The collaborative operation of the computer and the image recognition algorithm can significantly improve the detection efficiency, effectively avoid the problem of low efficiency caused by a large number of detection tasks, which in turn affects the detection accuracy, thereby further improving the detection accuracy of the intelligent chip and ensuring the high-quality production of the chip;

[0072] Among them, the first detection target obtains the second detection target through the second coordinate set, and obtains the second reference target through the second reference coordinate set; according to the second detection target and the second reference target; calculate the second similarity between the second detection target and the second reference target, and the second similarity is obtained by calculating the Pearson coefficient; and generate a second detection result;

[0073] Further, according to the second coordinate set, the associated second key line is obtained to generate the second detection target;

[0074] According to the second reference coordinate set and the associated label, the associated second key line is obtained to generate the second reference target;

[0075] According to the dynamic path algorithm, the second detection target and the second reference target are mapped onto a grid of size n*n to generate a detection grid; according to the dynamic path algorithm, the second reference target is mapped onto a grid of size n*n to generate a reference grid, and the number of second reference targets is 2, and the reference grid is referred to Figure 3 as shown Figure 3 in which A1 is the second reference target, that is, the line in the reference detection area, Figure 3 in which the grid is the reference grid calculated by the dynamic path algorithm; calculate the similarity between the detection grid and the reference grid to generate the second detection result; the dynamic path algorithm is the Dijkstra algorithm;

[0076] This embodiment locates the position of the internal circuit connection on the smart chip through the positioning coordinates to avoid false detection and missed detection. At the same time, the position can be further reduced through area division to reduce the false detection and missed detection. Through the grid of the dynamic path algorithm, the position offset or disconnection of the internal circuit connection of the chip can be detected. At the same time, according to the coordinates identified by the internal circuit connection of the chip, it can further determine whether the false detection is caused by dust in the case of disconnection, so as to improve the detection accuracy of the internal circuit connection of the chip;

[0077] Whether the smart chip is qualified is determined according to the first test result and the second test result; specifically: if both the first test result and the second test result are qualified, it is determined to be qualified; otherwise, it is determined to be unqualified.

[0078] Embodiment 2

[0079] In order to improve the quality detection accuracy of B smart chip, a detection system for smart chip in circuit board is applied; Figure 4 As shown, including:

[0080] A data acquisition module, which acquires the smart chip image data and the first reference target image data;

[0081] A detection area and reference area determination module, wherein the smart chip image data locates the first reference target image data, establishes a two-dimensional coordinate system for the smart chip image data and the first reference target image data, and divides the smart chip image data and the first reference target image data into a plurality of smart chip detection areas and a plurality of reference detection areas;

[0082] Furthermore, the detection area and reference area determination module, the smart chip image data positioning the first reference target image data includes:

[0083] Acquire type data and morphological data of the first positioning target of the smart chip image data according to the first image recognition algorithm; traverse the first reference target image data through the first image recognition algorithm to acquire the pre-selected reference target with the same type data;

[0084] The similarity of the pre-selected reference target is calculated based on the morphological data, and the second positioning target is obtained based on the maximum similarity value; the smart chip image data and the first reference target image data are positioned through the first positioning target and the second positioning target.

[0085] Furthermore, the number of the first positioning targets is not less than 3.

[0086] A coordinate generation module obtains a first coordinate set and a second coordinate set of the intelligent chip detection area according to the two-dimensional coordinate system and the intelligent chip detection area; obtains a first reference coordinate set and a second reference coordinate set of the reference detection area according to the two-dimensional coordinate system and the reference detection area;

[0087] A first detection module calculates a first similarity between the first coordinate set and the first reference coordinate set, and obtains a first detection target and a first reference target according to the first similarity; identifies and compares the first detection target and the first reference target, and generates a first detection result;

[0088] A second detection module obtains a second detection target through the second coordinate set, and obtains a second reference target through the second reference coordinate set; calculates a second similarity between the second detection target and the second reference target according to the second detection target and the second reference target, and generates a second detection result;

[0089] Further, the second detection module calculates a second similarity between the second detection target and the second reference target according to the second detection target and the second reference target, and generating a second detection result includes:

[0090] Obtain an associated second key line according to the second coordinate set, and generate a second detection target;

[0091] Obtain an associated second key line according to the second reference coordinate set and the associated label, and generate a second reference target;

[0092] Map the second detection target and the second reference target to a grid of size n*n according to the dynamic path algorithm to generate a detection grid; map the second reference target to a grid of size n*n according to the dynamic path algorithm to generate a reference grid; calculate the similarity between the detection grid and the reference grid to generate the second detection result.

[0093] A detection and judgment module judges whether the intelligent chip is qualified according to the first detection result and the second detection result; judges whether the intelligent chip is qualified according to the first detection result and the second detection result; specifically: if both the first detection result and the second detection result are qualified, it is judged to be qualified; otherwise, it is judged to be unqualified.

[0094] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A detection method for intelligent chips in a circuit board, characterized in that, Including: Obtaining intelligent chip image data and first reference target image data; Locating the first reference target image data in the intelligent chip image data, establishing a two-dimensional coordinate system for the intelligent chip image data and the first reference target image data, and dividing the intelligent chip image data and the first reference target image data into multiple intelligent chip detection regions and multiple reference detection regions; Obtaining a first coordinate set and a second coordinate set of the intelligent chip detection region according to the two-dimensional coordinate system and the intelligent chip detection region; obtaining a first reference coordinate set and a second reference coordinate set of the reference detection region according to the two-dimensional coordinate system and the reference detection region; Calculating a first similarity between the first coordinate set and the first reference coordinate set, obtaining a first detection target and a first reference target according to the first similarity; identifying and comparing the first detection target and the first reference target, and generating a first detection result; Obtaining a second detection target through the second coordinate set, and obtaining a second reference target through the second reference coordinate set; According to the second detection target and the second reference target; Calculating a second similarity between the second detection target and the second reference target, and generating a second detection result; Judging whether the intelligent chip is qualified according to the first detection result and the second detection result.

2. The detection method for an intelligent chip in a circuit board according to claim 1, wherein, The intelligent chip image data locating the first reference target image data includes: Obtaining type data and morphological data of a first positioning target of the intelligent chip image data according to a first image recognition algorithm; traversing the first reference target image data through the first image recognition algorithm to obtain preselected reference targets with the same type data; Calculating the similarity of the preselected reference targets according to the morphological data, and obtaining a second positioning target according to the maximum similarity value; positioning the intelligent chip image data and the first reference target image data through the first positioning target and the second positioning target.

3. The detection method for an intelligent chip in a circuit board according to claim 2, characterized in that, The number of the first positioning targets is not less than 3.

4. A detection method for an intelligent chip in a circuit board according to claim 1, characterized in that, Obtaining a first coordinate set and a second coordinate set of the intelligent chip detection region according to the two-dimensional coordinate system and the intelligent chip detection region; Obtaining a first reference coordinate set and a second reference coordinate set of the reference detection region according to the two-dimensional coordinate system and the reference detection region includes: Identifying a first target and a second target in the intelligent chip detection region or the reference detection region according to a second image recognition algorithm; the first target is a first target candidate box, and the second target includes a second key point and a second key line; the second key line and the second key point are associated through an association label; Obtaining the center point coordinates of the first target candidate box in the intelligent chip detection region according to the two-dimensional coordinate system, generating the first target coordinates of the intelligent chip detection region and obtaining the first coordinate set; Obtaining the center point coordinates of the first target candidate box in the reference detection region according to the two-dimensional coordinate system, generating the first target coordinates of the reference detection region and obtaining the first reference coordinate set; Obtain the second key point coordinates of the intelligent chip detection area according to the two-dimensional coordinate system, generate the second target coordinates of the intelligent chip detection area and obtain the second coordinate set; obtain the second key point coordinates of the reference detection area according to the two-dimensional coordinate system, generate the second target coordinates of the reference detection area and obtain the second reference coordinate set.

5. A detection method for an intelligent chip in a circuit board according to claim 1, characterized in that, Identify and compare the first detection target and the first reference target, and generate the first detection result including: Identify the first detection target and the first reference target through the second image recognition algorithm; compare according to the ASCII code of the recognition result of the second image recognition algorithm, and generate the first detection result according to the comparison result of the ASCII code.

6. The detection method for an intelligent chip in a circuit board according to claim 1, wherein According to the second detection target and the second reference target; Calculate the second similarity between the second detection target and the second reference target, and generate the second detection result including: Obtain the associated second key line according to the second coordinate set and generate the second detection target; Obtain the associated second key line according to the second reference coordinate set and the associated label and generate the second reference target; Map the second detection target and the second reference target to a grid of size n*n according to the dynamic path algorithm to generate a detection grid; map the second reference target to a grid of size n*n according to the dynamic path algorithm to generate a reference grid; calculate the similarity between the detection grid and the reference grid to generate the second detection result.

7. A detection system for intelligent chips in a circuit board, characterized in that, Including: A data acquisition module that acquires intelligent chip image data and first reference target image data; A detection area and reference area determination module that locates the first reference target image data in the intelligent chip image data, establishes a two-dimensional coordinate system for the intelligent chip image data and the first reference target image data, and divides the intelligent chip image data and the first reference target image data into multiple intelligent chip detection areas and multiple reference detection areas; A coordinate generation module that obtains the first coordinate set and the second coordinate set of the intelligent chip detection area according to the two-dimensional coordinate system and the intelligent chip detection area; obtains the first reference coordinate set and the second reference coordinate set of the reference detection area according to the two-dimensional coordinate system and the reference detection area; A first detection module that calculates the first similarity between the first coordinate set and the first reference coordinate set, and obtains the first detection target and the first reference target according to the first similarity; Identify and compare the first detection target and the first reference target, and generate the first detection result; A second detection module that obtains the second detection target through the second coordinate set and obtains the second reference target through the second reference coordinate set; according to the second detection target and the second reference target; Calculate the second similarity between the second detection target and the second reference target, and generate the second detection result; A detection judgment module that determines whether the intelligent chip is qualified according to the first detection result and the second detection result.

8. The detection system for an intelligent chip in a circuit board according to claim 7, characterized in that, The detection area and reference area determination module, the intelligent chip image data locating the first reference target image data includes: Obtain the type data and morphological data of the first positioning target of the intelligent chip image data according to the first image recognition algorithm; traverse the first reference target image data through the first image recognition algorithm to obtain the preselected reference targets with the same type data. Calculate the similarity of the preselected reference targets according to the morphological data, and obtain the second positioning target according to the maximum similarity value; position the intelligent chip image data and the first reference target image data through the first positioning target and the second positioning target.

9. The detection system for an intelligent chip in a circuit board according to claim 8, characterized in that, The number of the first positioning targets is not less than 3.

10. The detection system for an intelligent chip in a circuit board according to claim 7, characterized in that, The second detection module, according to the second detection target and the second reference target; Calculate the second similarity between the second detection target and the second reference target, and generate a second detection result including: Obtain the associated second key line according to the second coordinate set to generate the second detection target. Obtain the associated second key line according to the second reference coordinate set and the associated label to generate the second reference target. Map the second detection target and the second reference target to a grid of size n*n according to the dynamic path algorithm to generate a detection grid; map the second reference target to a grid of size n*n according to the dynamic path algorithm to generate a reference grid; calculate the similarity between the detection grid and the reference grid to generate the second detection result.

Images