Client information identification method and system for circuit board

Abstract

The invention provides a client information identification method and system for a circuit board, and the method is characterized in that the method comprises the steps: 1, building a regular expression matching table, analyzing the data content in a standard image file of the circuit board, matching the analyzed data content with the regular expression table, and storing the successfully matched data content as primitive information; step 2, performing coordinate conversion, setting points per inch, determining the size of the canvas, drawing primitives in a layered manner, and performing rotary moving copying on the primitives to generate a standard image; step 3, adjusting the position and parameters of the image acquisition assembly to obtain a clear and accurate acquisition image; step 4, preprocessing of filtering and contour extraction is carried out on the collected image; 5, performing feature point extraction on the preprocessed image; step 6, matching the standard image with the acquired image; and 7, if the matching is successful, identifying the customer information of the circuit board corresponding to the standard image from the database and printing the customer information.

Description

Technical Field

[0001] The present application relates to the technical field of circuit board information identification, and in particular to a method and system for identifying customer information of a circuit board. Background Art

[0002] With the changes in the production scale of printed circuit boards (hereinafter referred to as circuit boards) and the continuous development of the industry, the degree of automation of its production is constantly improving, and the production process and demand are also gradually adjusted. In the mass production stage, each processing order usually corresponds to the product of a single customer. In the final stage of production, the circuit board is packaged, and the customer information can be obtained by scanning the barcode on the processing order. Then, a label containing the customer information is printed and affixed to the packaging bag to ensure accurate delivery to the customer. However, with the rapid development of the electronics industry, the research and development of new products has gradually increased, and the manufacturing of circuit board samples has also gradually increased. The number of circuit board samples is not large and the variety is large. In order to improve production efficiency and reduce costs, factories usually use the method of panelization for production, that is, the circuit boards of multiple customers are combined together as a whole for processing. This production method also has only one processing order. When these circuit boards are divided into boards for different customers, the barcode on the processing order cannot be used to obtain the customer information of each circuit board. Therefore, the identification and acquisition of customer information of the circuit board processed by panelization brings new challenges to the production of circuit boards. At present, most factories rely on manual comparison to confirm the customer information of circuit boards, but this solution is labor-intensive and error-prone, and cannot meet the needs of intelligent manufacturing of circuit boards. If errors occur during the recognition process, it will lead to production delays and extended delivery cycles, which will directly cause losses to manufacturers and cause serious consequences. Some factories also add identification symbols such as QR codes or customer numbers to the silk-screen layer of the circuit board and use OCR recognition to determine customer information, but this method will permanently leave symbols unrelated to the product on the circuit board, which most customers cannot accept. Summary of the invention

[0003] In view of this, the present invention provides a customer information identification method and system for circuit boards to solve the technical problems of low efficiency and low accuracy in the back-end link of existing circuit board production.

[0004] The present invention provides a method for identifying customer information of a circuit board, the method comprising: step 1, establishing a regular expression matching table, parsing data content in a circuit board standard file through a syntax analysis program, matching the parsed data content with the regular expression matching table, and storing the successfully matched data content as graphic element information; step 2, performing coordinate conversion according to the graphic element information, setting dots per inch, determining the canvas size, drawing the graphic element in layers, and then rotating, moving and copying the graphic element to generate a standard image that meets the circuit board standard; step 3, adjusting the position and parameters of the image acquisition component to obtain a clear and accurate acquisition image; step 4, performing filtering and contour extraction preprocessing on the acquisition image to improve the image quality and enhance the recognizability of the target information; step 5, extracting feature points from the preprocessed image for subsequent processing and comparison; step 6, performing a Pearson correlation coefficient function , compare the similarity of feature points, match the standard image and the acquired image, where r is the Pearson correlation coefficient, X is the standard image feature point, and Y is the acquired image feature point; step 7, if the match is successful, the customer information corresponding to the standard image is identified from the database.

[0005] Furthermore, the regular expression matching table includes coordinate data, drawing commands, and aperture definitions.

[0006] Furthermore, the step 1 includes: step 11, establishing a regular expression matching table; step 12, storing the circuit board standard file in blocks into the memory; step 13, establishing the corresponding primitive storage type, and performing syntax analysis through a syntax analysis program; step 14, matching the parsing result with the regular expression matching table, if the match is not completed, obtaining a new circuit board standard file, and going to step 12, if the match is completed, going to step 15; step 15, storing all successfully matched data content as primitive information.

[0007] Furthermore, the syntax analysis program includes a lexical analysis program.

[0008] Further, the step 2 includes: step 21, establishing a graphic object and setting a coordinate system; step 22, setting the size of the bitmap image and the number of dots per inch according to the requirements, so that the standard diagram and the image to be measured are consistent in resolution; step 23, using a layered drawing method, reading the information of each layer element from the data map, and drawing the required graphics according to the preset layer parameters.

[0009] Furthermore, the characteristic points include pads and circular holes.

[0010] Furthermore, the method also includes: step 8, printing the identified customer information.

[0011] The present invention also provides a customer information identification system for circuit boards, the system comprising: an image acquisition component for clearly and accurately acquiring images; an image acquisition card connected to the image acquisition component for converting the acquired images into digital signals and transmitting them to a computer for processing; a computer connected to the image acquisition card for establishing a regular expression matching table, parsing the data content in the circuit board standard file through a syntax analysis program, matching the parsed data content with the regular expression matching table, storing the successfully matched data content as graphic element information, performing coordinate conversion according to the graphic element information, setting the dots per inch, determining the canvas size, drawing the graphic elements in layers, and then rotating, moving and copying them to generate a standard image that meets the circuit board standard, performing filtering and contour extraction preprocessing on the acquired image, extracting feature points from the preprocessed image, and performing a Pearson correlation coefficient function on the preprocessed image. , compare the similarity of feature points, match the standard image with the captured image, and identify the customer information corresponding to the successfully matched standard image from the database.

[0012] Furthermore, the image acquisition component includes a camera, a lens and a light source.

[0013] Furthermore, the system also includes: a label printer connected to the computer to print the identified customer information.

[0014] The present invention provides a method and system for identifying customer information of a circuit board. The technical solution uses a camera and a lens to collect the image of the circuit board, and then converts the image into a digital signal through an image acquisition card and transmits it to a computer for processing. At the same time, the computer calls the circuit board standard file (Gerber, which is used by the circuit board industry software to describe the circuit board, such as the circuit layer, solder mask layer, character layer, etc., a document format collection of images and drilling and milling data) in the database for drawing, matches it with the collected circuit board image and obtains relevant information, and finally obtains the corresponding customer information from the database and prints it out through a label printer. The technical solution reduces the difference between the circuit board image and the Gerber image, realizes accurate image matching and customer information extraction, can avoid mistakes in manual visual inspection and improve efficiency, the feature extraction and matching module improves the anti-noise performance of the matching, and reduces the calculation complexity by optimizing the calculation process, can complete large-scale matching tasks in a short time, has high efficiency, and uses matching similarity as a matching metric, which can more accurately reflect the matching degree of the image. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a schematic diagram of a customer information identification system for a circuit board provided by the present invention; Figure 2 It is a schematic flow chart of a method for identifying customer information of a circuit board provided by the present invention; Figure 3 It is a schematic diagram of the Gerber file parsing process provided by the present invention; Figure 4 It is a schematic diagram of the lexical analysis process provided by the present invention; Figure 5 It is a schematic diagram of the standard image drawing process provided by the present invention. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] Embodiment 1: The present invention provides a method and system for identifying customer information of a circuit board. Figure 1 As shown, the system includes an image acquisition component, an image acquisition card, a computer and a label printer. Figure 2 As shown, the method steps are as follows.

[0018] Step 1: Create a regular expression matching table, analyze the data content in the circuit board standard file through the syntax analysis program, match the parsed data content with the regular expression matching table, and store the successfully matched data content as primitive information; Step 2: Convert coordinates according to the element information, set the number of dots per inch, determine the size of the canvas, draw the element layered, and then rotate and move it to copy it to generate a standard image that meets the circuit board standards; Step 3, adjusting the position and parameters of the image acquisition component to obtain a clear and accurate captured image; The image acquisition component is used to obtain clear and accurate captured images; the image acquisition component includes a camera, a lens and a light source.

[0019] Step 4: pre-processing the collected image by filtering and contour extraction to improve image quality and enhance the recognizability of target information; Step 5, extracting feature points from the preprocessed image for subsequent processing and comparison; Step 6: Use the Pearson correlation coefficient function , compare the similarity of feature points and match the standard image with the captured image; Step 7: If the match is successful, the customer information corresponding to the standard image is identified from the database.

[0020] An image acquisition card, connected to the image acquisition component, is used to convert the acquired images into digital signals and transmit them to a computer for processing; The computer is connected to the image acquisition card and is used to establish a regular expression matching table, parse the data content in the circuit board standard file through a syntax analysis program, match the parsed data content with the regular expression matching table, store the successfully matched data content as graphic element information, perform coordinate conversion according to the graphic element information, set the number of dots per inch, determine the canvas size, draw the graphic elements in layers, and then rotate, move and copy them to generate a standard image that meets the circuit board standard, perform filtering and contour extraction preprocessing on the acquired image, extract feature points from the preprocessed image, adopt a content-based Hu moment feature point normalization correlation matching algorithm, match the standard image with the acquired image by comparing the similarity of the feature points, and identify the customer information corresponding to the successfully matched standard image from the database.

[0021] The present invention provides a method and system for identifying customer information of a circuit board. The technical solution uses a camera and a lens to collect the image of the circuit board, and then converts the image into a digital signal through an image acquisition card and transmits it to a computer for processing. At the same time, the computer calls the Gerber file information in the database for drawing, matches it with the collected circuit board image and obtains relevant information, and finally prints out the corresponding customer information through a label printer. The technical solution reduces the difference between the circuit board image and the Gerber image, realizes accurate image matching and customer information extraction, can avoid errors in manual visual inspection and improve efficiency, the feature extraction and matching module improves the anti-noise performance of the matching, and reduces the calculation complexity by optimizing the calculation process, can complete large-scale matching tasks in a short time, has high efficiency, and uses matching similarity as a matching metric, which can more accurately reflect the matching degree of the image.

[0022] Embodiment 2: The present invention provides a method and system for identifying customer information of a circuit board, the system comprising an image acquisition component, an image acquisition card, a computer and a label printer. Figure 2 As shown, the method steps are as follows.

[0023] Step 1: Create a regular expression matching table, analyze the data content in the circuit board standard file through the syntax analysis program, match the parsed data content with the regular expression matching table, and store the successfully matched data content as primitive information; like Figure 3 As shown, the specific parsing process of the Gerber file is as follows.

[0024] Step 11, establishing a regular expression matching table; The regular expression matching table contains various elements that can accurately match the Gerber file, including coordinate data, drawing commands, aperture definitions, etc.

[0025] Step 12, storing the circuit board standard file in blocks into the memory; Step 13, establish the corresponding primitive storage type, and perform syntax analysis through a syntax analysis program; The syntax analysis program includes a lexical analysis program. Lexical analysis is the first step of the syntax analysis program. When performing lexical analysis, it is necessary to first define lexical rules to identify specific command codes, including commands for drawing line segments, arcs, or circles; rules can also be defined to parse coordinate values. These rules describe how to identify and process different elements in Gerber files. The lexical analyzer scans the contents of the Gerber file line by line or character by character according to these rules. Whenever an element that matches a rule is encountered, the lexical analyzer marks it as a specific symbol and extracts relevant information about the element, such as Figure 4 After the lexical analysis is completed, the syntax analysis constructs a syntax tree or syntax analysis table according to the rules, and parses and classifies the element-related information extracted from the lexical analysis according to the syntax rules.

[0026] Step 14, matching the parsing result with the regular expression matching table, if the matching is not completed, obtaining a new circuit board standard file, and going to step 12, if the matching is completed, going to step 15; Step 15: store all successfully matched data contents as graphic element information.

[0027] Step 2: Convert coordinates according to the element information, set the number of dots per inch, determine the size of the canvas, draw the element layered, and then rotate and move it to copy it to generate a standard image that meets the circuit board standards; Step 3, adjusting the position and parameters of the image acquisition component to obtain a clear and accurate captured image; Step 4: pre-processing the collected image by filtering and contour extraction to improve image quality and enhance the recognizability of target information; Step 5, extracting feature points from the preprocessed image for subsequent processing and comparison; Step 6: Use the Pearson correlation coefficient function , compare the similarity of feature points and match the standard image with the captured image; Step 7: If the match is successful, the customer information corresponding to the standard image is identified from the database.

[0028] The present invention provides a method and system for identifying customer information of a circuit board. The technical solution uses a camera and a lens to collect the image of the circuit board, and then converts the image into a digital signal through an image acquisition card and transmits it to a computer for processing. At the same time, the computer calls the Gerber file information in the database for drawing, matches it with the collected circuit board image and obtains relevant information, and finally prints out the corresponding customer information through a label printer. The technical solution reduces the difference between the circuit board image and the Gerber image, realizes accurate image matching and customer information extraction, can avoid errors in manual visual inspection and improve efficiency, the feature extraction and matching module improves the anti-noise performance of the matching, and reduces the calculation complexity by optimizing the calculation process, can complete large-scale matching tasks in a short time, has high efficiency, and uses matching similarity as a matching metric, which can more accurately reflect the matching degree of the image.

[0029] Embodiment three: The present invention provides a method and system for identifying customer information of a circuit board, the system comprising an image acquisition component, an image acquisition card, a computer and a label printer. Figure 1 As shown, the method steps are as follows.

[0030] Step 1: Create a regular expression matching table, analyze the data content in the circuit board standard file through the syntax analysis program, match the parsed data content with the regular expression matching table, and store the successfully matched data content as primitive information; Step 2: Convert coordinates according to the element information, set the number of dots per inch, determine the size of the canvas, draw the element layered, and then rotate and move it to copy it to generate a standard image that meets the circuit board standards; After the Gerber file is parsed, it is necessary to see the image intuitively. Therefore, the present invention uses the image device interface provided by the Windows system, namely GDI+. GDI+ provides developers with rich graphics drawing and display functions, making the development of graphical display interfaces simple and efficient. If Figure 5 As shown, the specific steps are as follows.

[0031] Step 21, create a graphic object and set the coordinate system; Step 22, setting the size and dots per inch of the bitmap image according to the requirements, so that the standard image and the image to be tested are consistent in resolution; Step 23, using a layered drawing method, reads the information of each layer of graphics elements from the data map, and draws the required graphics according to the preset layer parameters.

[0032] Graphic objects can also be called Graphics objects, bitmap file images are also called Bitmap images, dots per inch are also called DPI, and data maps are DataMaps. Since the technical solution only needs to collect the surface image of the circuit board, and the circuit board is generally formed by laminating multiple layers, the system only needs to study the layers that are visible on the surface and affect the performance of the circuit board when drawing the image, mainly the surface layer and the solder mask layer. The present invention realizes the drawing of the standard image of the circuit board by parsing the Gerber file, and the standard image information has a high degree of consistency with the reference image information of the circuit board design, and each layer corresponds to each other. According to the results, it can be seen that the system has a high degree of accuracy in processing the Gerber file, which fully meets the needs of subsequent processing.

[0033] Step 3, adjusting the position and parameters of the image acquisition component to obtain a clear and accurate captured image; In order to accurately extract size and position information from the image, it is first necessary to calibrate the camera in the image acquisition component. Camera calibration is a process of correcting the internal and external parameters of the camera, which enables the pixel coordinates in the image to correspond to the actual three-dimensional world coordinate system.

[0034] Step 4: pre-processing the collected image by filtering and contour extraction to improve image quality and enhance the recognizability of target information; Among them, image filtering can reduce or eliminate image noise, improve image quality, and provide a better foundation for subsequent image processing steps. The preprocessing of contour extraction is to identify and extract key features on the circuit board, such as component contours, traces, etc. Contour extraction usually uses edge detection algorithms to find the boundaries of objects in the image, so that further feature recognition, measurement and analysis can be performed.

[0035] Step 5, extracting feature points from the preprocessed image for subsequent processing and comparison; The characteristic points include pads and circular holes.

[0036] Step 6: Use the Pearson correlation coefficient function , compare the similarity of feature points and match the standard image with the captured image; The Pearson correlation coefficient is also called the Pearson product-moment correlation coefficient. When two variables X and Y have a linear relationship, this coefficient can be used to describe the correlation between the variables and determine its direction and strength. The Pearson correlation coefficient can not only reflect the direction of the relationship between the variables (indicated by the positive and negative signs), but also measure the strength of this relationship. Therefore, this application uses the Pearson correlation coefficient to measure whether the standard image matches the captured image.

[0037] Step 7: If the match is successful, the customer information corresponding to the standard image is identified from the database.

[0038] Step 8: extract and print the identified customer information.

[0039] The system also includes: a label printer connected to the computer to extract and print the identified customer information.

[0040] The present invention provides a method and system for identifying customer information of a circuit board. The technical solution uses a camera and a lens to collect the image of the circuit board, and then converts the image into a digital signal through an image acquisition card and transmits it to a computer for processing. At the same time, the computer quickly calls the Gerber file information in the database for drawing, matches it with the collected circuit board image and obtains relevant information, and finally prints out the corresponding customer information through a label printer. The technical solution reduces the difference between the circuit board image and the Gerber image, realizes accurate image matching and customer information extraction, can avoid mistakes in manual visual inspection and improve efficiency, the feature extraction and matching module improves the anti-noise performance of the matching, and reduces the calculation complexity by optimizing the calculation process, can complete large-scale matching tasks in a short time, has high efficiency, and uses matching similarity as a matching metric, which can more accurately reflect the matching degree of the image.

[0041] In summary, the embodiment of the present invention provides a method and system for identifying customer information of a circuit board. The technical solution uses a camera and a lens to capture the image of the circuit board, and then converts the image into a digital signal through an image acquisition card and transmits it to a computer for processing. At the same time, the computer calls the Gerber file information in the database for drawing, matches it with the collected circuit board image and obtains relevant information, and finally prints out the corresponding customer information through a label printer. This technical solution reduces the difference between the circuit board image and the Gerber image, achieves accurate image matching and customer information extraction, can avoid errors in manual visual inspection and improve efficiency, the feature extraction and matching module improves the anti-noise performance of the matching, and reduces the computational complexity by optimizing the calculation process, can complete large-scale matching tasks in a shorter time, has higher efficiency, and uses matching similarity as a matching metric, which can more accurately reflect the degree of image matching.

[0042] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for identifying customer information of a circuit board, characterized in that: The method comprises: Step 1, establish a regular expression matching table, parse the data content in the circuit board standard file through a syntax analysis program, match the parsed data content with the regular expression table, and store the successfully matched data content as graphic element information; Step 2: According to the primitive information, coordinate conversion is performed, dots per inch are set, canvas size is determined, primitives are drawn in layers, and then they are rotated, moved and copied to generate a standard image that meets the circuit board standard; Step 3, adjusting the position and parameters of the image acquisition component to obtain a clear and accurate captured image; Step 4: pre-processing the collected image by filtering and contour extraction to improve image quality and enhance the recognizability of target information; Step 5, extracting feature points from the preprocessed image for subsequent processing and comparison; Step 6, through the Pearson correlation coefficient function , compare the similarity of feature points, match the standard image and the collected image, where r is the Pearson correlation coefficient, X is the feature point of the standard image, and Y is the feature point of the collected image; Step 7: If the match is successful, the customer information corresponding to the standard image is identified from the database.

2. A method for identifying customer information of a circuit board according to claim 1, characterized in that: The regular expression matching table includes coordinate data, drawing commands, and aperture definitions.

3. A method for identifying customer information of a circuit board according to claim 1, characterized in that: The step 1 comprises: Step 11, establishing a regular expression matching table; Step 12, storing the circuit board standard file in blocks into the memory; Step 13, establish the corresponding primitive storage type, and perform syntax analysis through a syntax analysis program; Step 14, matching the parsing result with the regular expression matching table, if the matching is not completed, obtaining a new circuit board standard file, and going to step 12, if the matching is completed, going to step 15; Step 15: store all successfully matched data contents as graphic element information.

4. A method for identifying customer information of a circuit board according to claim 3, characterized in that: The syntax analyzer includes a lexical analyzer.

5. A method for identifying customer information of a circuit board according to claim 1, characterized in that: The step 2 comprises: Step 21, create a graphic object and set the coordinate system; Step 22, setting the size and dots per inch of the bitmap image according to the requirements, so that the standard image and the image to be tested are consistent in resolution; Step 23, using a layered drawing method, reads the information of each layer of graphics elements from the data map, and draws the required graphics according to the preset layer parameters.

6. A method for identifying customer information of a circuit board according to claim 1, characterized in that: The characteristic points include pads and circular holes.

7. A method for identifying customer information of a circuit board according to claim 1, characterized in that: The method further comprises: Step 8: Extract and print the identified customer information.

8. A system for implementing the method for identifying customer information of a circuit board according to claims 1 to 7, characterized in that: The system comprises: An image acquisition component, used to acquire images clearly and accurately; An image acquisition card, connected to the image acquisition component, is used to convert the acquired images into digital signals and transmit them to a computer for processing; The computer is connected to the image acquisition card and is used to establish a regular expression matching table. The data content in the circuit board standard file is parsed through a syntax analysis program, and the parsed data content is matched with the regular expression matching table. The successfully matched data content is stored as image element information. According to the image element information, coordinate conversion is performed, dots per inch are set, the canvas size is determined, and the image elements are drawn in layers. Then, the image elements are rotated, moved, and copied to generate a standard image that meets the circuit board standard. The collected image is pre-processed for filtering and contour extraction, and feature points are extracted from the pre-processed image. The Pearson correlation coefficient function is used to calculate the feature points of the pre-processed image. , compare the similarity of feature points, match the standard image with the captured image, and identify the customer information corresponding to the successfully matched standard image from the database.

9. A circuit board customer information identification system according to claim 8, characterized in that: The image acquisition component includes a camera, a lens and a light source.

10. A circuit board customer information identification system according to claim 8, characterized in that: The system also includes: a label printer connected to the computer to print out the identified customer information.

Images