Anti-counterfeiting traceability method, device and system based on paper grain characteristics
By digitally extracting paper texture features and storing them on the blockchain, the problems of easy counterfeiting and high cost of existing anti-counterfeiting and traceability technologies have been solved, achieving low-cost and efficient anti-counterfeiting and traceability, and ensuring the reliability and security of anti-counterfeiting and traceability.
Patent Information
- Application Number
- CN202310642962.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-06-01
- Publication Date
- 2026-01-30
AI Technical Summary
Existing QR code and RFID technologies have problems such as being easily counterfeited, tampered with, and costly in anti-counterfeiting and traceability, and cannot guarantee the reliability and widespread application of anti-counterfeiting and traceability.
By employing a digital extraction method for paper texture features, high-definition scanning equipment is used to locate the paper texture feature area. Combined with machine learning and data analysis, paper texture feature parameters are extracted, and PUF technology and blockchain are used for evidence storage and verification to achieve anti-counterfeiting and traceability.
It provides a low-cost, reliable, and efficient anti-counterfeiting and traceability solution, ensuring the unique binding and tamper-proof nature of the anti-counterfeiting and traceability label to the product, thereby improving the security and efficiency of anti-counterfeiting and traceability.
Smart Images
Figure CN121437002A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The application belongs to the technical field of digital anti-counterfeiting, and particularly relates to an anti-counterfeiting traceability method, device and system based on paper texture features. BACKGROUND
[0002] With the increasing demand for domestic industrial upgrading, anti-counterfeiting traceability has become an urgent demand for many manufacturers. At present, the two-dimensional code and bar code anti-counterfeiting traceability technology of "one product one code" has become the most widely used technology in the anti-counterfeiting field due to its low cost, easy scanning, and ability to store a large amount of information; but this technology has problems such as being easily counterfeited and tampered with, and cannot guarantee the reliability of anti-counterfeiting traceability. In addition, although the RFID technology has the advantages of high flexibility and fast reading speed, it has also been widely used in specific scenarios, but its high cost has limited its development in general application. SUMMARY
[0003] To solve the above problems in the prior art, the application uses paper texture features to realize anti-counterfeiting traceability, has the advantages of not being easily counterfeited and tampered with, and provides a low-cost, reliable and efficient solution for product anti-counterfeiting.
[0004] To achieve the above purpose, the application provides the following technical scheme:
[0005] A paper texture feature digital extraction method includes paper texture feature region positioning, paper surface texture image preprocessing, paper texture feature analysis processing, and paper texture feature extraction based on machine learning. Specifically,
[0006] S01: Paper texture feature region positioning: use a high-definition scanning device to scan the surface of the paper, detect and position the paper texture feature collection area;
[0007] S02. Paper surface texture image preprocessing step: after detecting and positioning the paper texture specific collection area, if a preprocessed paper texture feature area is detected, the paper surface texture image is preprocessed to obtain a paper texture feature image;
[0008] S03. Paper texture feature analysis processing step: analyze the preprocessed paper texture feature image, and for the paper texture of the preprocessed paper texture feature image, use a data analysis step to obtain parameters describing the paper texture;
[0009] S04. Paper texture feature extraction step: digitally process the parameters obtained through the paper texture feature analysis step to obtain a digital paper texture feature sequence.
[0010] Further, the preprocessing method includes size scaling, grayscale, and filtering.
[0011] The paper texture includes macro texture and small / micro texture of fluorescent silk banknote paper;
[0012] The data analysis step includes:
[0013] S05, for the macro texture of fluorescent silk banknote paper, structure analysis is adopted to fit the macro texture into a specific shape, and the macro texture is converted into a number through the preset shape rotation direction and the corresponding relationship of the number;
[0014] S06, the small / micro texture is described through the statistical analysis method by analyzing the probability of pixel gray value in the image appearing in different spatial position relationship through the Gray-Level Co-occurrence Matrix (GLCM);
[0015] S07, the paper texture features are described by calculating the covariance and contrast of the gray values between pixels; and the texture features are described by calculating the average gray value, variance and other statistical parameters of the image filtered by the Gabor filter;
[0016] The digital feature processing step includes:
[0017] S08, the multiple statistical parameters obtained by the statistical analysis method of the small / micro texture are digitally processed, and are merged with the digital macro texture and the macro texture center point coordinate data to form the final digital paper texture feature sequence.
[0018] A paper texture feature digital extraction device can realize the paper texture feature digital extraction method as described above.
[0019] A digital paper texture feature storage method includes,
[0020] S09, the digital paper texture feature sequence collected by the paper texture feature digital extraction device as described above is stored, and the digital paper texture feature sequence is bound with the product features.
[0021] Further, the product features can be product name, batch, production date and other information.
[0022] Further, the digital paper texture feature storage method further includes:
[0023] S10, the bound digital paper texture feature sequence and product feature information are packaged and processed.
[0024] A paper texture feature verification method includes:
[0025] The paper texture feature digital extraction method as described above, after obtaining the digital paper texture feature sequence through the method, further includes the step
[0026] S11. Send a query request.
[0027] Furthermore, the preprocessing methods include size scaling, grayscale conversion, and filtering;
[0028] The paper texture includes large textures and small / micro textures;
[0029] The data analysis steps include:
[0030] S12. For large textures, structural analysis is used to fit the macro texture into a specific shape, and the macro texture is converted into a number by using the preset shape rotation direction and the correspondence between the number.
[0031] S13. Small / micro textures are described by statistical analysis, specifically by analyzing the probability of pixel gray values appearing in different spatial positions in the image using the gray-level co-occurrence matrix.
[0032] S14. The paper texture features are described by calculating parameters such as the covariance and contrast of gray values between pixels; and the texture features are described by calculating statistical parameters such as the average gray value and variance of the image after Gabor filter.
[0033] The digital feature processing steps include:
[0034] S15. Digitize the multiple statistical parameters obtained from the small / micro textures through statistical analysis, and merge them with the digitized macro textures and the coordinate data of the macro texture center point to form the final digitized paper texture feature sequence.
[0035] A server-side device, comprising:
[0036] The server device receives the data collected by the paper texture feature digitization extraction device as described above;
[0037] The server-side device implements the digital paper texture feature storage method described above;
[0038] After receiving the request sent by the paper texture feature verification method as described above, the server device responds to the request.
[0039] A handheld verification device can implement the paper texture feature verification method described above.
[0040] Furthermore, the handheld verification terminal communicates with the server and sends a digitized paper texture feature sequence query request to the server to verify the authenticity of the information.
[0041] A paper texture feature-based anti-counterfeiting and traceability system includes the paper texture feature digitization extraction device described above, the server-side device described above, and the handheld verification terminal device described above.
[0042] The present invention, employing the above-mentioned technical solution, possesses the following beneficial effects: Utilizing PUF (Physical Unclonable Function) technology, the present invention digitizes the paper texture features on anti-counterfeiting labels printed on fluorescent banknote paper. Combined with a private blockchain-based anti-counterfeiting traceability management platform, it ensures the unique binding and tamper-proof nature of the anti-counterfeiting traceability label with the product, without incurring additional costs; only an additional paper texture feature digitization extraction process is required. The feature extraction device can convert the paper texture features into a string of numbers using a specific algorithm and upload it to the anti-counterfeiting traceability management platform for evidence storage. At the verification end, a smartphone or other device scans the paper texture feature area, and the extracted digitized paper texture features are compared with the evidence stored on the platform, thus conveniently and quickly achieving anti-counterfeiting authentication. Attached Figure Description
[0043] Figure 1 This is a flowchart of the paper texture feature extraction process of the present invention;
[0044] Figure 2 This is an interactive diagram of the anti-counterfeiting and traceability system of the present invention. Detailed Implementation
[0045] 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.
[0046] This invention provides a technical solution:
[0047] like Figure 1 As shown, a method for digitally extracting paper texture features includes steps such as locating paper texture feature regions, preprocessing paper surface texture images, analyzing and processing paper texture features, and extracting paper texture features based on machine learning. Specifically:
[0048] S01: Paper texture feature area localization step: The paper surface is scanned using a high-definition scanning device to detect and locate the paper texture feature acquisition area;
[0049] S02. Paper surface texture image preprocessing step: After detecting and locating the specific acquisition area of paper texture, if a preprocessing paper texture feature area is detected, the paper surface texture image is preprocessed to obtain the paper texture feature image.
[0050] S03. Paper texture feature analysis and processing step: The preprocessed paper texture feature image is analyzed, and data analysis steps are used to obtain parameters describing the paper texture texture based on the paper texture texture of the preprocessed paper texture feature image;
[0051] S04. Paper Texture Feature Extraction Step: The parameters obtained from the paper texture feature analysis step are digitized to obtain a digitized paper texture feature sequence.
[0052] As one embodiment, the preprocessing method includes, but is not limited to, size scaling, grayscale conversion, and filtering.
[0053] As one embodiment, the paper texture includes large and small / micro textures of fluorescent banknote paper.
[0054] As one embodiment, the data analysis steps include:
[0055] S05. For the large texture of fluorescent banknote paper, structural analysis is used to fit the macro texture into a specific shape, and the macro texture is converted into a number by the preset shape rotation direction and the correspondence between the number.
[0056] S06. Small / micro textures are described by statistical analysis using the Gray-Level Co-occurrence Matrix (GLCM) to analyze the probability of pixel gray values appearing in different spatial positions in the image.
[0057] S07. The paper texture features are described by calculating parameters such as the covariance and contrast of gray values between pixels; and the texture features are described by calculating statistical parameters such as the average gray value and variance of the image after Gabor filter.
[0058] The digital feature processing steps include:
[0059] S08. Digitize the multiple statistical parameters obtained from the small / micro textures through statistical analysis, and merge them together with the digitized macro textures and the coordinate data of the macro texture center point to form the final digitized paper texture feature sequence.
[0060] As an example, a paper texture feature digital extraction device can realize the paper texture feature digital extraction method as described above.
[0061] As one embodiment, a method for storing digital paper texture features includes:
[0062] S09. Store the digital paper texture feature sequence collected by the paper texture feature digitization extraction device as described above, and bind the digital paper texture feature sequence with the product features.
[0063] As one example, the product features may include information such as product name, batch number, and production date.
[0064] As one embodiment, the digital paper texture feature storage method further includes:
[0065] S10. Package the bound digital paper texture feature sequence with the product feature information and process it on the blockchain.
[0066] Packing data and processing it on the blockchain leverages the secure and tamper-proof characteristics of blockchain to further enhance data reliability.
[0067] As one embodiment, a paper texture feature verification method includes:
[0068] The paper texture feature digitization extraction method described above, after obtaining the digitized paper texture feature sequence through this method, also includes the following steps:
[0069] S11. Send a query request.
[0070] As one embodiment, the preprocessing method includes size scaling, grayscale conversion, and filtering.
[0071] As one embodiment, the specific features include large textures and small / micro textures.
[0072] As one embodiment, the data analysis steps include:
[0073] S12. For large textures, structural analysis is used to fit the macro texture into a specific shape, and the macro texture is converted into a number by using the preset shape rotation direction and the correspondence between the number.
[0074] S13. Small / micro textures are described by statistical analysis, specifically by analyzing the probability of pixel gray values appearing in different spatial positions in the image using the gray-level co-occurrence matrix.
[0075] S14. The paper texture features are described by calculating parameters such as the covariance and contrast of gray values between pixels; and the texture features are described by calculating statistical parameters such as the average gray value and variance of the image after Gabor filter.
[0076] The digital feature processing steps include:
[0077] S15. Digitize the multiple statistical parameters obtained from the small / micro textures through statistical analysis, and merge them with the digitized macro textures and the coordinate data of the macro texture center point to form the final digitized paper texture feature sequence.
[0078] As one embodiment, a server-side device includes:
[0079] The server device receives the data collected by the paper texture feature digitization extraction device as described above;
[0080] The server-side device implements the digital paper texture feature storage method described above;
[0081] After receiving the request sent by the paper texture feature verification method as described above, the server device responds to the request.
[0082] As an example, a handheld verification device can implement the paper texture feature verification method described above.
[0083] As one embodiment, the handheld verification terminal communicates with the server and sends a digitized paper texture feature sequence query request to the server to verify the authenticity of the information.
[0084] As one embodiment, an anti-counterfeiting and traceability system based on paper texture features includes a paper texture feature digitization extraction device, a server-side device, and a handheld verification terminal device.
[0085] This invention utilizes paper texture features combined with statistical analysis and Gabor filter feature extraction algorithms to achieve anti-counterfeiting and traceability. It can improve the reliability and efficiency of product anti-counterfeiting and traceability without increasing additional costs. This method can analyze the texture features of a specified area to extract feature information from the surface of fluorescent banknote paper. Then, through digitization and normalization processing, the paper's texture features are transformed into a digitized feature sequence. Compared with traditional QR code verification anti-counterfeiting, PUF offers higher security and is more difficult to replicate.
[0086] The above is a description of the present invention to help understand it. However, the implementation of the present invention is not limited to the above embodiments. Any changes, modifications, substitutions, combinations, or simplifications made without departing from the principle of the present invention should be considered equivalent substitutions and are included within the protection scope of the present invention.
Claims
1. A method for digital extraction of paper texture features, characterized by, comprising S01, paper texture feature area positioning step: using equipment to scan the surface of the paper, detecting and positioning the paper texture feature collection area; S02, paper surface texture image preprocessing step: after detecting and positioning the paper texture specific collection area, if the preprocessed paper texture feature area is detected, the paper surface texture image is preprocessed to obtain the paper texture feature image; S03, paper texture feature analysis and processing step: analyzing the preprocessed paper texture feature image, and using data analysis steps for the paper texture of the preprocessed paper texture feature image to obtain parameters describing the paper texture; S04, paper texture feature extraction step: digitally processing the parameters obtained through the paper texture feature analysis step to obtain a digital paper texture feature sequence.
2. The paper texture feature digital extraction method according to claim 1, wherein the preprocessing method comprises size scaling, gray scaling, and filtering; the paper texture comprises macro texture and small / micro texture of fluorescent silk banknote paper; the data analysis step comprises: S05, for the macro texture of fluorescent silk banknote paper, structure analysis is adopted to fit the macro texture into a specific shape, and the macro texture is converted into a number through a preset shape rotation direction and a corresponding relationship with the number; S06, the small / micro texture is described by analyzing the probability of pixel gray value appearing in different spatial position relationships in the image through a gray level co-occurrence matrix analysis method; S07, the paper texture feature is described by calculating the covariance and contrast of the gray values between pixels; and the texture feature is described by calculating the average gray level and variance of the image filtered by the Gabor filter; the digital feature processing step comprises: S08, the multiple statistical parameters obtained by the statistical analysis method for the small / micro texture are digitally processed, and are combined with the digital macro texture and the macro texture center point coordinate data to form a final digital paper texture feature sequence. The paper texture feature digital extraction method according to any one of claims 1-2 can be realized.
3. A paper texture feature digital extraction apparatus characterized by, comprising:
4. A method for storing evidence of digitized paper features, characterized by, S09, storing the digital paper texture feature sequence collected by the paper texture feature digital extraction device according to claim 2, and binding the digital paper texture feature sequence with the product feature. Further comprising:
5. The method of claim 4, wherein the step of digitizing the paper feature comprises the step of: S10, packaging the bound digital paper texture feature sequence and product feature information, and performing uplink processing. comprising the paper texture feature digital extraction method according to claim 1; after obtaining the digital paper texture feature sequence, further comprising 6. A paper texture feature verification method characterized by, S11, sending a query request. the preprocessing method comprises size scaling, gray scaling, and filtering; 7. The paper texture verification method of claim 6, wherein, the paper texture comprises macro texture and small / micro texture; the data analysis step comprises: S12, for the macro texture, structure analysis is adopted to fit the macro texture into a specific shape, and the macro texture is converted into a number through a preset shape rotation direction and a corresponding relationship with the number; S13, the small / micro texture is described by analyzing the probability of pixel gray value appearing in different spatial position relationships in the image through a gray level co-occurrence matrix analysis method; S14, describe the paper texture features by calculating the covariance and contrast of the gray values between pixels; and describe the texture features by calculating the average gray value and variance of the image filtered by the Gabor filter; The digital feature processing step comprises: S15, digitally process the multiple statistical parameters of the small / micro texture obtained by statistical analysis, and merge them with the digital macro texture and the macro texture center point coordinate data to form the final digital paper texture feature sequence.
8. A server device, comprising: Comprise: The server device receives the data collected by the paper texture feature digital extraction device according to claim 3; The server device implements the digital paper texture feature storage method according to claim 4 or 5; After receiving the request sent by the paper texture feature checking method according to claim 6 or 7, the server device responds to the request.
9. A hand-held verification end device, characterized by The paper texture feature checking method according to claim 6 or 7 can be implemented.
10. A paper feature based anti-counterfeiting traceability system characterized in that, The paper texture feature digital extraction device according to claim 3, the server device according to claim 8, and the handheld checking terminal device according to claim 9 are included.