A method and system for identifying customer information of a circuit board

Abstract

The application provides a circuit board customer information identification method and system, characterized in that the method comprises the following steps: step 1, a regular expression matching table is established, data content in a circuit board standard image file is parsed, the parsed data content is matched with the regular expression table, and the data content matched successfully is stored as graphic element information; step 2, coordinate conversion is performed, the number of points per inch is set, the canvas size is determined, the graphic element is layered and drawn, and then the graphic element is rotated, moved and copied to generate a standard image; step 3, the position and parameters of an image acquisition component are adjusted to obtain a clear and accurate acquisition image; step 4, the acquisition image is subjected to filtering and contour extraction pretreatment; step 5, feature point extraction is performed on the pretreated image; step 6, the standard image and the acquisition image are matched; and step 7, if the matching is successful, the customer information of the circuit board corresponding to the standard image is identified from a database and printed.

Description

TECHNICAL FIELD

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

[0002] With the change of 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 continuously improved, and the production process and demand are gradually adjusted. In the mass production stage, each processing sheet usually corresponds to a single customer's product. In the last stage of production, the circuit board is packaged, the bar code on the processing sheet is scanned to obtain customer information, and then a label containing customer information is printed and attached to the packaging bag to ensure accurate delivery to the customer. However, with the rapid development of the electronics industry, the development of new products is gradually increasing, and the manufacturing of circuit board samples is also gradually increasing. The amount of circuit board samples is not large, and the variety is large. In order to improve production efficiency and reduce costs, the factory usually adopts the way of splicing board 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 sheet, and when these circuit boards are divided into different customer boards, the customer information of each circuit board cannot be obtained through the bar code on the processing sheet, so the customer information identification and acquisition of spliced circuit boards brings new challenges to circuit board production. At present, most factories rely on manual comparison to confirm the customer information of the circuit board, but this scheme is laborious and prone to error, and cannot meet the needs of intelligent manufacturing of circuit boards. If an error occurs in the identification process, it will cause production progress delay and delivery cycle extension, etc. These problems will directly cause loss to the manufacturer and cause serious consequences. Some factories add identification symbols such as two-dimensional codes or customer numbers to the silk screen layer of the circuit board, and determine the customer information through OCR identification, but this method will permanently leave symbols unrelated to the product on the circuit board, and most customers cannot accept it. SUMMARY

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

[0004] The application provides a circuit board customer information identification method, which comprises the following steps: step 1, a regular expression matching table is established, the data content in a circuit board standard file is parsed by a syntax analysis program, the parsed data content is matched with the regular expression matching table, and the data content matched successfully is stored as graphic element information; step 2, according to the graphic element information, coordinate conversion is carried out, the number of dots per inch is set, the canvas size is determined, the graphic element is layered and drawn, and then the layered and drawn graphic element is rotated, moved and copied to generate a standard image conforming to the circuit board standard; step 3, the position and parameters of an image acquisition component are adjusted to obtain a clear and accurate acquisition image; step 4, the acquisition image is preprocessed through filtering and contour extraction to improve the image quality and enhance the identifiable property of target information; step 5, feature points are extracted from the preprocessed image for subsequent processing and comparison; step 6, the similarity of the feature points is compared through a Pearson correlation coefficient function

[0005] , the standard image and the acquisition image are matched, wherein r is the Pearson correlation coefficient, X is the feature point of the standard image, and Y is the feature point of the acquisition image; and step 7, if the matching is successful, the customer information corresponding to the standard image is identified from a database.

[0006] Further, the regular expression matching table comprises coordinate data, drawing commands and aperture definitions.

[0007] Further, step 1 comprises the following steps: step 11, the regular expression matching table is established; step 12, the circuit board standard file is stored in blocks in the memory; step 13, the corresponding graphic element storage type is established, and syntax analysis is carried out through a syntax analysis program; step 14, the analysis result is matched with the regular expression matching table, if the matching is not completed, a new circuit board standard file is obtained, and the process returns to step 12, if the matching is completed, the process proceeds to step 15; and step 15, all the data content matched successfully is stored as graphic element information.

[0008] Further, the syntax analysis program comprises a lexical analysis program.

[0009] Further, step 2 comprises the following steps: step 21, a graphic object is established, and a coordinate system is set; step 22, the size of the bit map image and the number of dots per inch are set according to requirements, so that the standard image and the to-be-tested image remain consistent in resolution; and step 23, a layered drawing mode is adopted to read the information of each layer of graphic element from a data map, and the required graphic is drawn according to preset layer parameters.

[0010] Further, the feature points comprise pads and round holes.

[0011] Further, the method further comprises the following step: step 8, the identified customer information is printed.

[0012] The application further provides a customer information identification system of a circuit board, which comprises: an image acquisition component, which is used for acquiring images clearly and accurately; an image acquisition card, which is connected with the image acquisition component and is used for converting the acquired images into digital signals and transmitting the digital signals to a computer for processing; and the computer, which is connected with the image acquisition card, is used for establishing a regular expression matching table, analyzing data content in a circuit board standard file through a syntax analysis program, matching the analyzed data content with the regular expression matching table, storing the data content matched successfully as graphic element information, performing coordinate conversion, setting the number of dots per inch, determining the size of a canvas, layering and drawing the graphic elements, rotating, moving and copying the graphic elements, generating a standard image conforming to the circuit board standard, performing filtering and contour extraction on the acquired images, extracting feature points from the preprocessed images, comparing the similarity of the feature points through a Pearson correlation coefficient function , matching the standard image with the acquired image, and identifying the customer information corresponding to the standard image matched successfully from a database.

[0013] Further, the image acquisition component comprises a camera, a lens and a light source.

[0014] Further, the system further comprises a label printer, which is connected with the computer and is used for printing the identified customer information.

[0015] The application provides a customer information identification method and system of a circuit board, which comprises the following steps: acquiring a circuit board image through a camera cooperating with a lens, converting the image into a digital signal through an image acquisition card and transmitting the digital signal to a computer for processing. At the same time, the computer calls information of a circuit board standard file (Gerber, which is a document format collection of images and drilling and milling data of a circuit board industry software for describing a circuit board, such as a circuit layer, a solder resist layer and a character layer) in a database to draw and match the drawn image with the acquired circuit board image and obtain relevant information, and finally obtains corresponding customer information from the database and prints the customer information through a label printer. The technical scheme reduces the difference between the circuit board image and the Gerber image, realizes accurate image matching and customer information extraction, can avoid the mistakes of manual visual inspection and improve the efficiency, the feature extraction and matching module improves the anti-noise performance of matching, reduces the computational complexity through optimized calculation process, can complete a large-scale matching task in a short time, has high efficiency, uses matching similarity as a matching measurement index, and can more accurately reflect the matching degree of images. BRIEF DESCRIPTION OF DRAWINGS

[0016] Figure 1 is a schematic diagram of a customer information identification system of a circuit board provided by the application;

[0017] Figure 2This is a schematic diagram of a customer information identification method for a circuit board provided by the present invention;

[0018] Figure 3 This is a schematic diagram of the Gerber file parsing process provided by the present invention;

[0019] Figure 4 This is a schematic diagram of the lexical analysis process provided by the present invention;

[0020] Figure 5 This is a schematic diagram of the standard image drawing process provided by the present invention. Detailed Implementation

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] Example 1:

[0023] This invention provides a method and system for identifying customer information on a circuit board, such as... 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 steps of the method are as follows.

[0024] Step 1: Establish a regular expression matching table. Parse the data content in the circuit board standard file using a syntax analysis program, match the parsed data content with the regular expression matching table, and store the successfully matched data content as graphic element information.

[0025] Step 2: Based on the primitive information, perform coordinate transformation, set the number of dots per inch, determine the canvas size, draw primitives in layers, and then rotate, move and copy them to generate a standard image that conforms to the circuit board standard.

[0026] Step 3: Adjust the position and parameters of the image acquisition component to obtain a clear and accurate acquired image;

[0027] An image acquisition component is used to obtain clear and accurate acquired images; the image acquisition component includes a camera, a lens, and a light source.

[0028] Step 4: Perform preprocessing on the acquired images, including filtering and contour extraction, to improve image quality and enhance the recognizability of target information;

[0029] Step 5: Extract feature points from the preprocessed image for comparison in subsequent processing;

[0030] Step 6, comparing the similarity of feature points, matching the standard image and the collected image;

[0031] Step 7, if the matching is successful, the customer information corresponding to the standard image is identified from the database.

[0032] An image acquisition card is connected to the image acquisition component, used for converting the collected image into a digital signal and transmitting it to the computer for processing;

[0033] The computer is connected to the image acquisition card, used 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 data content matched successfully as graphic element information, performing coordinate conversion, setting the number of points per inch, determining the canvas size, layering the graphic elements, rotating, moving and copying them to generate a standard image conforming to the circuit board standard, filtering and contour extracting the collected image, extracting feature points from the preprocessed image, taking a content-based Hu moment feature point normalization correlation matching algorithm, comparing the similarity of feature points, matching the standard image and the collected image, and identifying the customer information corresponding to the matched standard image from the database.

[0034] The present application provides a circuit board customer information identification method and system, which acquires the circuit board image through a camera with a lens, 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 the corresponding customer information through a label printer. This technical solution reduces the difference between the circuit board image and the Gerber image, realizes accurate image matching and customer information extraction, can avoid the mistakes of manual visual inspection and improve the efficiency, the feature extraction and matching module improves the noise resistance of matching, and through optimizing the calculation process, the calculation complexity is reduced, which can complete large-scale matching tasks in a short time, has high efficiency, and uses matching similarity as the matching metric index, which can more accurately reflect the matching degree of the image.

[0035] Example two:

[0036] The present application provides a circuit board customer information identification method and system, which acquires the circuit board image through a camera with a lens, 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 the corresponding customer information through a label printer. This technical solution reduces the difference between the circuit board image and the Gerber image, realizes accurate image matching and customer information extraction, can avoid the mistakes of manual visual inspection and improve the efficiency, the feature extraction and matching module improves the noise resistance of matching, and through optimizing the calculation process, the calculation complexity is reduced, which can complete large-scale matching tasks in a short time, has high efficiency, and uses matching similarity as the matching metric index, which can more accurately reflect the matching degree of the image. Figure 2

[0037] ​​Step 1, 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, and storing the data content matched successfully as graphic primitive information;

[0038] As shown in Figure 3 , the specific Gerber file parsing process is as follows.

[0039] Step 11, establishing a regular expression matching table;

[0040] The regular expression matching table contains various elements that can accurately match the Gerber file, including coordinate data, drawing commands, aperture definitions, etc.

[0041] Step 12, storing the circuit board standard file in blocks to the memory;

[0042] Step 13, establishing a corresponding graphic primitive storage type, and performing syntax analysis through a syntax analysis program;

[0043] 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 define lexical rules to identify specific command codes, including commands for drawing lines, arcs, or circles; rules can also be defined to parse coordinate values. These rules describe the methods of identifying and processing different elements in the Gerber file. The lexical analyzer will scan the content of the Gerber file line by line or character by character according to these rules. Whenever an element that matches the rule is encountered, the lexical analyzer will mark it as a specific symbol and extract the relevant information of the element, such as Figure 4 As shown. After lexical analysis, the syntax analysis constructs a syntax tree or syntax analysis table according to the rules, and parses and classifies the element-related information extracted in the lexical analysis according to the syntax rules.

[0044] Step 14, matching the parsing result with the regular expression matching table. If the matching is not completed, a new circuit board standard file is obtained, and the process returns to step 12. If the matching is completed, the process proceeds to step 15;

[0045] Step 15, storing all matched data content as graphic primitive information.

[0046] Step 2, according to the graphic primitive information, performing coordinate conversion, setting the number of points per inch, determining the canvas size, layering the graphic primitives, and then rotating, moving, and copying them to generate a standard image that meets the circuit board standard;

[0047] Step 3, adjusting the position and parameters of the image acquisition component to obtain clear and accurate acquisition images;

[0048] Step 4, pre-treatment of filtering and contour extraction is performed on the collected image to improve the image quality and enhance the recognizability of the target information;

[0049] Step 5, feature point extraction is performed on the pre-treated image for subsequent processing and comparison;

[0050] Step 6, similarity of the feature points is compared by using the Pearson correlation coefficient function , and the standard image and the collected image are matched.

[0051] Step 7, if the matching is successful, the customer information corresponding to the standard image is identified from the database.

[0052] The application provides a circuit board customer information identification method and system, which comprises a camera cooperating with a lens to collect a circuit board image, an image acquisition card to convert the image into a digital signal and transmit the digital signal to a computer for processing. At the same time, the computer calls Gerber file information in a database to draw, matches the circuit board image collected and obtains relevant information, and finally prints the corresponding customer information by using a label printer. The technical scheme reduces the difference between the circuit board image and the Gerber image, realizes accurate image matching and customer information extraction, can avoid the mistakes of manual visual inspection and improve the efficiency, the feature extraction and matching module improves the noise resistance of the matching, reduces the calculation complexity by optimizing the calculation process, can complete a large-scale matching task in a short time, has high efficiency, and uses the matching similarity as a matching measurement index, which can more accurately reflect the matching degree of the image.

[0053] Embodiment three:

[0054] The application provides a circuit board customer information identification method and system, which comprises an image acquisition component, an image acquisition card, a computer and a label printer. As shown in the figure, the method comprises the following steps. Figure 1

[0055] Step 1, a regular expression matching table is established, the data content in the circuit board standard file is parsed by using a syntax analysis program, the parsed data content is matched with the regular expression matching table, and the data content matched successfully is stored as graphic element information;

[0056] Step 2, according to the graphic element information, coordinate conversion is performed, the number of points per inch is set, the canvas size is determined, the graphic elements are layered and drawn, and then the graphic elements are rotated, moved and copied to generate a standard image conforming to the circuit board standard;

[0057] ​After the Gerber file is parsed, the image needs to be seen directly, so the application uses the image device interface provided by the Windows system, that is, GDI+. GDI+ provides developers with rich graphic drawing and display functions, making the development of the graphic display interface simple and efficient. Figure 5 As shown in the following steps.

[0058] Step 21, establish a graphic object and set up a coordinate system;

[0059] Step 22, set the size and dots per inch of the bitmapped image according to the requirements, so that the standard graph and the measured graph remain consistent in resolution;

[0060] Step 23, adopt a layered drawing method to read the information of each layer of the graphic element from the data map, and draw the required graphic according to the preset layer parameters.

[0061] The graphic object can also be called Graphics object, the bitmapped file image is also called Bitmap image, and the dots per inch is also called DPI. Since the technical solution only needs to collect the surface image of the circuit board, and the circuit board is generally formed by pressing multiple layers, therefore, the system only needs to study the layers that are visible on the surface and will affect the performance of the circuit board, mainly the surface layer and the solder mask layer. The application realizes the drawing of the standard image of the circuit board by analyzing the Gerber file, and the standard image information is highly consistent with the circuit board design reference image information, and each layer corresponds to each other. According to the result, it can be known that the processing of the Gerber file by the system has high accuracy, and fully meets the needs of subsequent processing.

[0062] Step 3, adjust the position and parameters of the image acquisition component to obtain clear and accurate acquisition images;

[0063] In order to accurately extract the size and position information from the image, the camera in the image acquisition component needs to be calibrated first. 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.

[0064] Step 4, pre-process the collected images for filtering and contour extraction to improve image quality and enhance the recognizability of target information;

[0065] Among them, image filtering can reduce or eliminate image noise and improve image quality, providing a better foundation for subsequent image processing steps. The pre-processing 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 carried out.

[0066] Step 5, feature point extraction is performed on the pretreated image for subsequent processing and comparison;

[0067] The feature points include pads and round holes.

[0068] Step 6, the similarity of the feature points is compared by using a Pearson correlation coefficient function to match the standard image with the collected image.

[0069] The Pearson correlation coefficient is also known as the Pearson product-moment correlation coefficient, which can be used to describe the correlation between variables and determine the direction and strength of the correlation when two variables X and Y have a linear relationship. The Pearson correlation coefficient can not only reflect the direction of the relationship between variables (indicated by the sign), but also measure the strength of the relationship, so the present application uses the Pearson correlation coefficient to measure whether the standard image matches the collected image.

[0070] Step 7, if the matching is successful, the customer information corresponding to the standard image is identified from the database.

[0071] Step 8, the identified customer information is extracted and printed.

[0072] The system further comprises a label printer connected to the computer for extracting and printing the identified customer information.

[0073] The present application provides a customer information identification method and system for a circuit board, which comprises the following steps: a camera cooperates with a lens to collect an image of the circuit board, and then an image acquisition card is used to convert the image into a digital signal and transmit it to a computer for processing. At the same time, the computer rapidly calls the Gerber file information in the database for drawing, matches 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, realizes accurate image matching and customer information extraction, can avoid the mistakes of manual visual inspection and improve the efficiency, the feature extraction and matching module improves the noise resistance of the matching, and through the optimization of the calculation process, the calculation complexity is reduced, which can complete large-scale matching tasks in a short time, has high efficiency, and uses matching similarity as a matching measurement index, which can more accurately reflect the matching degree of the image.

[0074] In summary, the embodiment of the present application provides a circuit board customer information identification method and system, which comprises the following steps: a camera cooperates with a lens to collect a circuit board image, then an image acquisition card is used to convert the image into a digital signal and transmit it to a computer for processing. At the same time, the computer calls the Gerber file information in the database to draw, matches with the collected circuit board image and obtains relevant information, and finally the corresponding customer information is printed out through a label printer. The technical scheme reduces the difference between the circuit board image and the Gerber image, realizes accurate image matching and customer information extraction, can avoid the mistakes of manual visual inspection and improve the efficiency, the feature extraction and matching module improves the noise resistance of matching, and through optimizing the calculation process, the calculation complexity is reduced, large-scale matching tasks can be completed in a short time, has high efficiency, and uses matching similarity as the matching measurement index, can more accurately reflect the matching degree of the image.

[0075] The above merely describes the preferred embodiments of the present application and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for identifying customer information on a circuit board, characterized in that, The method includes: Step 1: Establish a regular expression matching table. Parse the data content in the circuit board standard file using a syntax analysis program, match the parsed data content with the regular expression matching table, and store the successfully matched data content as graphic element information. Step 2: Based on the primitive information, perform coordinate transformation, set the number of dots per inch, determine the canvas size, draw primitives in layers, and then rotate, move and copy them to generate a standard image that conforms to the circuit board standard. Step 3: Adjust the position and parameters of the image acquisition component to obtain a clear and accurate acquired image; Step 4: Perform preprocessing on the acquired images, including filtering and contour extraction, to improve image quality and enhance the recognizability of target information; Step 5: Extract feature points from the preprocessed image for comparison in subsequent processing; Step 6, using the Pearson correlation coefficient function The similarity of feature points is compared to match the standard image with the acquired 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 acquired image. Step 7: If the match is successful, the customer information corresponding to the standard image will be identified from the database.

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

3. The customer information identification method for a circuit board according to claim 1, characterized in that, Step 1 includes: Step 11: Create a regular expression matching table; Step 12: Store the standard circuit board file in blocks in memory; Step 13: Establish the corresponding primitive storage type and perform syntax analysis through a syntax analyzer; Step 14: Match the parsed results with the regular expression matching table. If the matching is not completed, obtain a new circuit board standard file and proceed to step 12. If the matching is completed, proceed to step 15. Step 15: Store all successfully matched data as primitive information.

4. The customer information identification method for a circuit board according to claim 3, characterized in that, The parsing program includes a lexical analyzer.

5. The customer information identification method for a circuit board according to claim 1, characterized in that, Step 2 includes: Step 21: Create a graphic object and set the coordinate system; Step 22: Set 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 have the same resolution. Step 23: Using a layered drawing method, read the information of each layer of graphic elements from the data map, and draw the required graphics according to the preset layer parameters.

6. The customer information identification method for a circuit board according to claim 1, characterized in that, The feature points include pads and holes.

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

8. A customer information identification system for a circuit board, to implement the customer information identification method for a circuit board according to any one of claims 1-7, characterized in that, The system includes: Image acquisition components are used to acquire images clearly and accurately. An image acquisition card, connected to an image acquisition component, is used to convert acquired images into digital signals and transmit them to a computer for processing. A computer, connected to an image acquisition card, is used to create a regular expression matching table. A syntax analyzer parses the data in the circuit board standard file, matches the parsed data against the regular expression matching table, and stores the successfully matched data as primitive information. Based on this primitive information, coordinate transformation is performed, the number of dots per inch is set, the canvas size is determined, and primitives are drawn in layers. These layers are then rotated, moved, and copied to generate a standard image conforming to the circuit board standard. The acquired image undergoes preprocessing, including filtering and contour extraction. Feature points are extracted from the preprocessed image using the Pearson correlation coefficient function. The similarity of feature points is compared, and the standard image is matched with the acquired image. The customer information corresponding to the successfully matched standard image is then identified from the database.

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

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

Images