CN115983874A - Wine anti-counterfeiting tracing method and system - Google Patents
Wine anti-counterfeiting tracing method and system Download PDFInfo
- Publication number
- CN115983874A CN115983874A CN202310126237.3A CN202310126237A CN115983874A CN 115983874 A CN115983874 A CN 115983874A CN 202310126237 A CN202310126237 A CN 202310126237A CN 115983874 A CN115983874 A CN 115983874A
- Authority
- CN
- China
- Prior art keywords
- image
- product
- feature
- classification
- characteristic diagram
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a wine anti-counterfeiting traceability method and a system thereof, which are used for obtaining a product deposit certificate image of a wine product to be traced from a block chain network structure and obtaining a product detection image of the wine product to be traced, which is acquired by a camera; and adopting an artificial intelligence technology based on deep learning, taking the difference between the product evidence storage image and the product detection image in a high-dimensional feature space as the difference between the data to be traced and the real-time detection data, and determining whether the wine to be traced is a genuine product or not based on difference expression. Therefore, the accuracy of the judgment result of whether the liquor to be traced is a genuine product or not can be improved, and the discrimination capability of the public on the fake liquor is further improved.
Description
Technical Field
The application relates to the technical field of intelligent anti-counterfeiting traceability, in particular to an anti-counterfeiting traceability method and an anti-counterfeiting traceability system for wines.
Background
The phenomenon that famous wine is counterfeited and counterfeited exists in the wine market of China in large quantity. In order to improve the identifying capability of the public on fake wine, anti-counterfeiting and tracing systems are provided for many wines on the market, for example, two-dimensional codes, electronic tags, AR and other technologies are used for commodity information inquiry and anti-counterfeiting verification.
However, these efforts cannot avoid the counterfeit or counterfeit wine, because some false pictures and words are uploaded by counterfeiters to construct a false tracing process, the above operations of the counterfeiters are technically difficult, and such counterfeit means also make consumers unable to identify them.
Therefore, an optimized wine anti-counterfeiting traceability scheme is expected.
Disclosure of Invention
The present application is proposed to solve the above-mentioned technical problems. The embodiment of the application provides a wine anti-counterfeiting traceability method and a system thereof, which are used for obtaining a product deposit image of a wine product to be traced from a block chain network structure and obtaining a product detection image of the wine product to be traced, which is acquired by a camera; and adopting an artificial intelligence technology based on deep learning, taking the difference between the product evidence storage image and the product detection image in a high-dimensional characteristic space as the difference between the data to be traced and the real-time detection data, and determining whether the wine to be traced is a genuine product or not based on difference expression. Therefore, the accuracy of the judgment result of whether the wine to be traced is a genuine product or not can be improved, and the discrimination capability of the public on the fake wine is further improved.
According to one aspect of the application, a wine anti-counterfeiting tracing method is provided, which comprises the following steps:
obtaining a product deposit evidence image of the wine product to be traced from the block chain network structure;
acquiring a product detection image of the wine product to be traced, which is acquired by a camera;
passing the product evidence storage image and the product detection image through a twin detection model comprising a first image encoder and a second image encoder to obtain an evidence storage characteristic diagram and a detection characteristic diagram, wherein the first image encoder and the second image encoder have the same network structure;
calculating a difference characteristic diagram between the evidence storing characteristic diagram and the detection characteristic diagram; and
and passing the differential characteristic diagram through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the wine to be traced is a genuine product or not.
In the wine anti-counterfeiting tracing method, the first image encoder and the second image encoder are convolutional neural network models using a space attention mechanism.
In the above wine anti-counterfeiting tracing method, the passing the product certificate storing image and the product detection image through a twin detection model including a first image encoder and a second image encoder to obtain a certificate storing characteristic diagram and a detection characteristic diagram includes: using the layers of the first image encoder to perform respectively: performing convolution processing on input data to generate a first convolution characteristic diagram; pooling the first volumetric feature map to generate a first pooled feature map; performing nonlinear activation on the first pooled feature map to generate a first activated feature map; calculating a mean of the respective positions of the first activation profile along a channel dimension to generate a first spatial feature matrix; calculating Softmax-like function values of all positions in the first spatial feature matrix to obtain a first spatial score matrix; calculating the position-based point multiplication of the first spatial feature matrix and the first spatial score matrix to obtain a first feature matrix; wherein, the first feature matrix output by the last layer of the first image encoder is the evidence storing feature map.
In the above wine anti-counterfeiting tracing method, the passing the product certificate storing image and the product detection image through a twin detection model including a first image encoder and a second image encoder to obtain a certificate storing characteristic diagram and a detection characteristic diagram includes: using the layers of the second image encoder to perform respectively: performing convolution processing on the input data to generate a second convolution characteristic diagram; pooling the second convolved feature map to generate a second pooled feature map; performing nonlinear activation on the second pooled feature map to generate a second activated feature map; calculating the mean value of each position of the second activation feature map along the channel dimension to generate a second spatial feature matrix; calculating Softmax-like function values of all positions in the second spatial feature matrix to obtain a second spatial score matrix; and calculating the position-based point multiplication of the second spatial feature matrix and the second spatial score matrix to obtain a second feature matrix; wherein the second feature matrix output by the last layer of the second image encoder is the detected feature map.
In the above wine anti-counterfeiting tracing method, the calculating a difference characteristic diagram between the evidence storing characteristic diagram and the detection characteristic diagram includes: calculating a difference feature map between the evidence storing feature map and the detection feature map by using the following formula; wherein the formula is:
wherein the content of the first and second substances,
represents the differential characteristic map, and>
represents the evidence-depositing characteristic map, and>
represents the detection characteristic map, and>
representing subtraction by position.
In the above wine anti-counterfeiting traceability method, the step of passing the differential feature map through a classifier to obtain a classification result, where the classification result is used to indicate whether the wine to be traced is genuine or not, includes: carrying out feature map expansion on the differential feature map to obtain a classification feature vector; carrying out local structure fuzzy correction on the classified feature vectors to obtain optimized classified feature vectors; and passing the optimized classified feature vector through a classifier to obtain the classification result.
In the method for tracing the anti-counterfeiting of the wines, the expanding the feature map of the differential feature map to obtain a classification feature vector comprises the following steps: and expanding the differential feature map according to a row vector to obtain the classification feature vector.
In the above wine anti-counterfeiting tracing method, the performing local structure fuzzy correction on the classification feature vector to obtain an optimized classification feature vector includes: carrying out local structure fuzzy correction on the classification characteristic vector according to the following formula to obtain an optimized classification characteristic vector; wherein the formula is:
wherein the content of the first and second substances,
represents the classification feature vector>
Representing the optimized classified feature vector, device for selecting or keeping>
A transposed vector representing the classification feature vector, be->
Represents the square of the two-norm of the classification feature vector, is->
Is an ordered vector of eigenvalues of the classification eigenvector in order of magnitude, and said classification eigenvector->
Is in the form of a column vector>
Represents a vector dot-multiply,. Or->
Representing a matrix multiplication.
In the above wine anti-counterfeiting tracing method, the step of passing the optimized classification feature vector through a classifier to obtain the classification result includes: performing full-join coding on the optimized classified feature vector by using a plurality of full-join layers of the classifier to obtain a coded classified feature vector; and passing the encoding classification feature vector through a Softmax classification function of the classifier to obtain the classification result.
According to another aspect of the application, a wine anti-counterfeiting traceability system is provided, which comprises:
the evidence storing image obtaining module is used for obtaining a product evidence storing image of the wine product to be traced from the block chain network structure;
the detection image acquisition module is used for acquiring a product detection image of the wine product to be traced by the camera;
an image encoding module, configured to pass the product evidence storage image and the product inspection image through a twin inspection model including a first image encoder and a second image encoder to obtain an evidence storage feature map and an inspection feature map, where the first image encoder and the second image encoder have the same network structure;
the difference characteristic diagram calculation module is used for calculating a difference characteristic diagram between the evidence storing characteristic diagram and the detection characteristic diagram; and
and the anti-counterfeiting traceability result generation module is used for enabling the differential characteristic graph to pass through a classifier to obtain a classification result, and the classification result is used for indicating whether the wine to be traceable is a genuine product or not.
Compared with the prior art, the wine anti-counterfeiting traceability method and the system thereof have the advantages that the product deposit image of the wine product to be traced is obtained from the block chain network structure, and the product detection image of the wine product to be traced, which is acquired by the camera, is obtained; and adopting an artificial intelligence technology based on deep learning, taking the difference between the product evidence storage image and the product detection image in a high-dimensional characteristic space as the difference between the data to be traced and the real-time detection data, and determining whether the wine to be traced is a genuine product or not based on difference expression. Therefore, the accuracy of the judgment result of whether the wine to be traced is a genuine product or not can be improved, and the discrimination capability of the public on the fake wine is further improved.
Drawings
The above and other objects, features and advantages of the present application will become more apparent by describing in more detail embodiments of the present application with reference to the attached drawings. The accompanying drawings are included to provide a further understanding of the embodiments of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the principles of the application. In the drawings, like reference numbers generally represent like parts or steps.
FIG. 1 is a scene schematic diagram of an anti-counterfeiting traceability method for wines according to an embodiment of the application.
FIG. 2 is a flow chart of the wine anti-counterfeiting traceability method according to the embodiment of the application.
FIG. 3 is a schematic diagram of an architecture of a wine anti-counterfeiting tracing method according to an embodiment of the present application.
Fig. 4 is a flowchart of substeps of step S150 in the wine anti-counterfeiting traceability method according to the embodiment of the application.
Fig. 5 is a flowchart of substeps of step S230 in the wine anti-counterfeiting traceability method according to an embodiment of the application.
FIG. 6 is a block diagram of an anti-counterfeiting traceability system for wines according to an embodiment of the application.
Detailed Description
Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be understood that the described embodiments are only some embodiments of the present application and not all embodiments of the present application, and that the present application is not limited by the example embodiments described herein.
Overview of scenes
Correspondingly, in the technical scheme of the application, the block chain technology is adopted to determine the tamper resistance and the authenticity of the data to be traced, meanwhile, the artificial intelligence technology based on deep learning and neural network is combined to intelligently compare the difference between the data to be traced and the real-time detection data, and whether the object to be traced is a genuine product is determined based on the difference expression.
Specifically, in the technical scheme of the application, a product evidence storage image of the wine product to be traced is obtained from the block chain network structure, and a product detection image of the wine product to be traced, which is acquired by the camera, is obtained. Here, the block link network structure may be a federation link to determine the non-tamper-ability and authenticity of the product authentication image by the technology-specificity of the block link network itself.
Then, the product evidence image and the product detection image are passed through a twin detection model comprising a first image encoder and a second image encoder to obtain an evidence feature map and a detection feature map, wherein the first image encoder and the second image encoder have the same network structure. It should be understood that if there is no difference between the product deposit image and the product inspection image at the image source side, there should be a high degree of consistency and alignment between the deposit feature map and the inspection feature map extracted by the first image encoder and the second image encoder having the same network structure; conversely, if there is a difference between the two at the image source domain, such difference will also be captured and retained by the first and second image encoders. In one particular example of the present application, the first image encoder and the second image encoder are convolutional neural network models with a spatial attention mechanism. It should be understood that the convolutional neural network model can effectively extract local features of a high-dimensional image through convolution kernels, and the features of the spatial dimensions can be made to have higher identifiability by combining a spatial attention mechanism, so that the accuracy of classification judgment is improved.
Further, in the technical solution of the present application, a difference feature map between the evidence storing feature map and the detection feature map is further calculated, so as to represent a difference between the product evidence storing image and the product detection image in a high-dimensional feature space. And then, the differential feature map is processed by a classifier to obtain a classification result, and the classification result is used for indicating whether the liquor to be traced is a genuine product or not.
Here, in the technical solution of the present application, the first image encoder and the second image encoder having the same network structure respectively perform high-dimensional feature extraction on the product deposit certificate image and the product inspection image, and represent a difference between the product deposit certificate image and the product inspection image in a high-dimensional feature space, that is, a substantial difference between the two images, by using a difference feature map between the two images. However, in the process of feature extraction, noise (represented as outliers in the feature map) existing in the source domain of the product certification image and the product detection image is also amplified synchronously through the processing of the first image encoder and the second image encoder, which may cause local structural blurring in the high-dimensional data manifold of the differential feature map, thereby reducing the expression certainty of the differential feature map and affecting the accuracy of the classification result of the differential feature map obtained by the classifier.
Based on this, the applicant of the present application develops the differential feature map to obtain a classification feature vector
Ordered hilbert completion of the vector was performed, expressed as:
Here, by mapping the ordered vectors into the hilbert space defined by the self-inner product of the vectors, a meaningful measurement of the numerical relationship of the feature set in the consistency space can be realized, on the basis of which a feature space with an orthorhombic structure is constructed by embedding the relative position of the feature vectors, and the structural completion in the feature space is performed on the high-dimensional manifold of the feature vectors based on the vector query, so that the reduction of the expression certainty of the feature vectors due to the fuzzification structure can be avoided, and the accuracy of the classification result obtained by the classifier of the differential feature map can be improved.
Based on this, this application provides a drinks anti-fake tracing method, and it includes: obtaining a product deposit evidence image of the wine product to be traced from the block chain network structure; acquiring a product detection image of the wine product to be traced, which is acquired by a camera; passing the product evidence storage image and the product detection image through a twin detection model comprising a first image encoder and a second image encoder to obtain an evidence storage characteristic diagram and a detection characteristic diagram, wherein the first image encoder and the second image encoder have the same network structure; calculating a difference characteristic diagram between the evidence storing characteristic diagram and the detection characteristic diagram; and obtaining a classification result by passing the differential feature map through a classifier, wherein the classification result is used for indicating whether the wine to be traced is a genuine product or not.
FIG. 1 is a scene schematic diagram of an anti-counterfeiting traceability method for wines according to an embodiment of the application. As shown in fig. 1, in this application scenario, first, a product certification image (e.g., C1 as illustrated in fig. 1) of the wine product to be traced is obtained from the blockchain network structure, and a product detection image (e.g., C2 as illustrated in fig. 1) of the wine product to be traced, which is acquired by a camera, is obtained. Then, inputting the acquired product certificate image and the product detection image into a server (for example, S as illustrated in fig. 1) deployed with a wine anti-counterfeiting traceability algorithm, wherein the server can process the product certificate image and the product detection image by the wine anti-counterfeiting traceability algorithm to generate a classification result for indicating whether the wine to be traced is genuine or not.
Having described the general principles of the present application, various non-limiting embodiments of the present application will now be described with reference to the accompanying drawings.
Exemplary method
FIG. 2 is a flowchart of an anti-counterfeiting tracing method for wines according to an embodiment of the application. As shown in FIG. 2, the wine anti-counterfeiting tracing method according to the embodiment of the application comprises the following steps: s110, obtaining a product deposit certificate image of the wine product to be traced from the block chain network structure; s120, acquiring a product detection image of the wine product to be traced, which is acquired by a camera; s130, enabling the product evidence storage image and the product detection image to pass through a twin detection model comprising a first image encoder and a second image encoder to obtain an evidence storage characteristic diagram and a detection characteristic diagram, wherein the first image encoder and the second image encoder have the same network structure; s140, calculating a difference characteristic diagram between the evidence storing characteristic diagram and the detection characteristic diagram; and S150, the differential feature map is processed by a classifier to obtain a classification result, and the classification result is used for indicating whether the wine to be traced is a genuine product or not.
FIG. 3 is a schematic diagram of an architecture of a wine anti-counterfeiting tracing method according to an embodiment of the present application. As shown in fig. 3, in the network architecture, first, a product deposit evidence image of the wine product to be traced is obtained from the blockchain network structure; then, acquiring a product detection image of the wine product to be traced, which is acquired by a camera; then, the product evidence storage image and the product detection image pass through a twin detection model comprising a first image encoder and a second image encoder to obtain an evidence storage characteristic diagram and a detection characteristic diagram, wherein the first image encoder and the second image encoder have the same network structure; then, calculating a difference characteristic diagram between the evidence storing characteristic diagram and the detection characteristic diagram; and finally, the differential feature map is processed by a classifier to obtain a classification result, and the classification result is used for indicating whether the wine to be traced is a genuine product or not.
Specifically, in step S110 and step S120, a product deposit evidence image of the wine product to be traced is obtained from the blockchain network structure; and acquiring a product detection image of the wine product to be traced, which is acquired by the camera. Correspondingly, in the technical scheme of the application, the block chain technology is adopted to determine the tamper resistance and the authenticity of the data to be traced, meanwhile, the artificial intelligence technology based on deep learning and neural network is combined to intelligently compare the difference between the data to be traced and the real-time detection data, and whether the object to be traced is a genuine product is determined based on the difference expression.
Specifically, in the technical scheme of the application, firstly, a product evidence storage image of the wine product to be traced is obtained from a block chain network structure, and a product detection image of the wine product to be traced, which is acquired by a camera, is obtained. Here, the block link network structure may be a federation link to determine the non-tamper-ability and authenticity of the product authentication image by the technology-specificity of the block link network itself.
Specifically, in step S130, the product certification image and the product inspection image are passed through a twin inspection model including a first image encoder and a second image encoder to obtain a certification feature map and an inspection feature map, the first image encoder and the second image encoder having the same network structure. Then, the product evidence storage image and the product detection image are passed through a twin detection model comprising a first image encoder and a second image encoder to obtain an evidence storage characteristic diagram and a detection characteristic diagram, wherein the first image encoder and the second image encoder have the same network structure.
It should be understood that if there is no difference between the product deposit image and the product inspection image at the image source side, there should be a high degree of consistency and alignment between the deposit feature map and the inspection feature map extracted by the first image encoder and the second image encoder having the same network structure; conversely, if there is a difference between the two at the image source domain, such difference will also be captured and retained by the first image encoder and the second image encoder.
In one particular example of the present application, the first image encoder and the second image encoder are convolutional neural network models with a spatial attention mechanism. It should be understood that the convolution neural network model can effectively extract local features of a high-dimensional image through convolution kernels, and the features of spatial dimensions can be made to have higher identifiability by combining a spatial attention mechanism, so that the accuracy of classification judgment is improved.
Further, in this embodiment of the present application, the passing the product certification image and the product inspection image through a twin inspection model including a first image encoder and a second image encoder to obtain a certification characteristic map and an inspection characteristic map includes: using the layers of the first image encoder to perform respectively: performing convolution processing on input data to generate a first convolution characteristic diagram; pooling the first volumetric feature map to generate a first pooled feature map; performing nonlinear activation on the first pooled feature map to generate a first activated feature map; calculating a mean of the positions of the first activation profile along a channel dimension to generate a first spatial signature matrix; calculating Softmax-like function values of all positions in the first spatial feature matrix to obtain a first spatial score matrix; calculating the position-based point multiplication of the first spatial feature matrix and the first spatial score matrix to obtain a first feature matrix; wherein the first feature matrix output by the last layer of the first image encoder is the evidence-storing feature map.
Still further, in an embodiment of the present application, the passing the product deposit certificate image and the product inspection image through a twin inspection model including a first image encoder and a second image encoder to obtain a deposit certificate feature map and an inspection feature map includes: using the layers of the second image encoder to perform respectively: performing convolution processing on the input data to generate a second convolution characteristic diagram; pooling the second convolved feature map to generate a second pooled feature map; performing nonlinear activation on the second pooled feature map to generate a second activated feature map; calculating the mean value of each position of the second activation feature map along the channel dimension to generate a second spatial feature matrix; calculating Softmax-like function values of all positions in the second spatial feature matrix to obtain a second spatial score matrix; and calculating the position-based point multiplication of the second spatial feature matrix and the second spatial score matrix to obtain a second feature matrix; wherein the second feature matrix output by the last layer of the second image encoder is the detected feature map.
Specifically, in step S140, a difference feature map between the verification feature map and the detection feature map is calculated. Further, in the technical solution of the present application, a difference feature map between the evidence storing feature map and the detection feature map is further calculated to represent a difference between the product evidence storing image and the product detection image in a high-dimensional feature space. And then, the differential feature map is processed by a classifier to obtain a classification result, and the classification result is used for indicating whether the wine to be traced is a genuine product or not.
Wherein, the calculating the difference characteristic diagram between the evidence storing characteristic diagram and the detection characteristic diagram comprises: calculating a difference characteristic diagram between the evidence storing characteristic diagram and the detection characteristic diagram by using the following formula; wherein the formula is:
wherein, the first and the second end of the pipe are connected with each other,
represents the differential characteristic map, and>
represents the evidence-depositing characteristic map, and>
represents the detection characteristic map, is combined with the detection characteristic map>
Representing subtraction by position.
Specifically, in step S150, the differential feature map is passed through a classifier to obtain a classification result, where the classification result is used to indicate whether the liquor to be traced is a genuine product or not. And finally, passing the differential feature map through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the wine to be traced is a genuine product or not. That is, the classifier is used to determine class probability labels to which the differential feature map belongs, wherein the class probability labels include that the wine to be traced is a genuine product (a first label) and that the wine to be traced is not a genuine product (a second label).
Fig. 4 is a flowchart of substeps of step S150 in the wine anti-counterfeiting traceability method according to an embodiment of the present application, and as shown in fig. 4, the step of passing the differential feature map through a classifier to obtain a classification result, where the classification result is used to indicate whether the wine to be traced is a genuine product, includes: s210, performing characteristic diagram expansion on the differential characteristic diagram to obtain a classification characteristic vector; s220, carrying out local structure fuzzy correction on the classification characteristic vector to obtain an optimized classification characteristic vector; and S230, passing the optimized classified feature vector through a classifier to obtain the classification result.
The expanding the feature map of the difference feature map to obtain a classification feature vector includes: and expanding the differential feature map according to a row vector to obtain the classification feature vector.
Here, in the technical solution of the present application, the first image encoder and the second image encoder having the same network structure respectively perform high-dimensional feature extraction on the product deposit certificate image and the product inspection image, and represent a difference between the product deposit certificate image and the product inspection image in a high-dimensional feature space, that is, a substantial difference between the two images, by using a difference feature map between the two images. However, in the process of feature extraction, noise (represented as outliers in the feature map) existing in the source domain of the product certification image and the product detection image is also amplified synchronously through the processing of the first image encoder and the second image encoder, which may cause local structural blurring in the high-dimensional data manifold of the differential feature map, thereby reducing the expression certainty of the differential feature map and affecting the accuracy of the classification result of the differential feature map obtained by the classifier.
Based on this, the applicant of the present application copes with the differenceClassified feature vector obtained after expansion of sub-feature map
Performing ordered hilbert completion on the vector, that is, performing local structure fuzzy correction on the classification feature vector to obtain an optimized classification feature vector, includes: carrying out local structure fuzzy correction on the classification characteristic vector according to the following formula to obtain an optimized classification characteristic vector; wherein the formula is:
wherein the content of the first and second substances,
represents the classification feature vector>
Representing the optimized classified feature vector, device for selecting or keeping>
A transposed vector representing the classification feature vector, be->
Represents the square of the two-norm of the classification feature vector, is determined>
Is an ordered vector of the feature values of the classification feature vector in order of magnitude and the classification feature vector->
Is in the form of a column vector>
Represents a vector dot-multiply,. Or->
Representing a matrix multiplication.
Here, by mapping the ordered vectors into the hilbert space defined by the self-inner product of the vectors, meaningful measurement of the numerical relationship of the feature set in the consistency space can be realized, on the basis of which a feature space with an orthorhombic structure is constructed by embedding the relative position with the feature vectors, and the high-dimensional manifold of the feature vectors is subjected to structural completion in the feature space based on vector query, so that the reduction of the expression certainty of the feature vectors due to the fuzzification structure can be avoided, and the accuracy of the classification result of the differential feature map obtained by the classifier can be improved.
Fig. 5 is a flowchart of substeps of step S230 in the wine anti-counterfeiting tracing method according to the embodiment of the present application, and as shown in fig. 5, the passing the optimized classification feature vector through a classifier to obtain the classification result includes: s310, performing full-connection coding on the optimized classified feature vectors by using a plurality of full-connection layers of the classifier to obtain coded classified feature vectors; and S320, passing the coding classification feature vector through a Softmax classification function of the classifier to obtain the classification result.
In a specific example of the present application, the classifier is used to process the optimized classified feature vector according to the following formula to obtain the classification result; wherein the formula is:
In summary, according to the wine anti-counterfeiting traceability method provided by the embodiment of the application, the product deposit evidence image of the wine product to be traced is obtained from the block chain network structure, and the product detection image of the wine product to be traced, which is acquired by the camera, is obtained; and adopting an artificial intelligence technology based on deep learning, taking the difference between the product evidence storage image and the product detection image in a high-dimensional characteristic space as the difference between the data to be traced and the real-time detection data, and determining whether the wine to be traced is a genuine product or not based on difference expression. Therefore, the accuracy of the judgment result of whether the wine to be traced is a genuine product or not can be improved, and the discrimination capability of the public on the fake wine is further improved.
Exemplary System
FIG. 6 is a block diagram of an anti-counterfeiting traceability system for wines according to an embodiment of the present application. As shown in fig. 6, the wine anti-counterfeiting traceability system 100 according to the embodiment of the present application comprises: the evidence storing image obtaining module 110 is used for obtaining a product evidence storing image of the wine product to be traced from the block chain network structure; the detection image acquisition module 120 is used for acquiring a product detection image of the wine product to be traced by the camera; an image encoding module 130, configured to pass the product evidence storage image and the product inspection image through a twin inspection model including a first image encoder and a second image encoder to obtain an evidence storage feature map and an inspection feature map, where the first image encoder and the second image encoder have the same network structure; a difference feature map calculation module 140, configured to calculate a difference feature map between the evidence storing feature map and the detection feature map; and the anti-counterfeiting traceability result generating module 150 is used for enabling the differential characteristic diagram to pass through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the wine to be traceable is a genuine product or not.
In one example, in the wine anti-counterfeiting traceability system 100, the first image encoder and the second image encoder are convolutional neural network models using a spatial attention mechanism.
In an example, in the wine anti-counterfeiting traceability system 100, the image coding module is configured to: using the layers of the first image encoder to perform respectively: performing convolution processing on input data to generate a first convolution characteristic diagram; pooling the first volumetric feature map to generate a first pooled feature map; performing a non-linear activation on the first pooled feature map to generate a first activated feature map; calculating a mean of the positions of the first activation profile along a channel dimension to generate a first spatial signature matrix; calculating Softmax-like function values of all positions in the first spatial feature matrix to obtain a first spatial score matrix; and calculating the first spatial feature matrix and the first spatial score matrix to multiply according to position points to obtain a first feature matrix; wherein, the first feature matrix output by the last layer of the first image encoder is the evidence storing feature map.
In an example, in the wine anti-counterfeiting traceability system 100, the image coding module is further configured to: using the layers of the second image encoder to perform respectively: performing convolution processing on the input data to generate a second convolution characteristic diagram; pooling the second convolved feature map to generate a second pooled feature map; performing nonlinear activation on the second pooled feature map to generate a second activated feature map; calculating the mean value of each position of the second activation feature map along the channel dimension to generate a second spatial feature matrix; calculating Softmax-like function values of all positions in the second spatial feature matrix to obtain a second spatial score matrix; and calculating the position-based point multiplication of the second spatial feature matrix and the second spatial score matrix to obtain a second feature matrix; wherein the second feature matrix output by the last layer of the second image encoder is the detected feature map.
According to the technical scheme, the method comprises the steps of firstly obtaining a product evidence storage image of the wine product to be traced from a block chain network structure, and obtaining a product detection image of the wine product to be traced, wherein the product detection image is acquired by a camera. Here, the block link network structure may be a federation link to determine the non-tamper-ability and authenticity of the product authentication image by the technology-specificity of the block link network itself.
Then, the product evidence storage image and the product detection image are passed through a twin detection model comprising a first image encoder and a second image encoder to obtain an evidence storage characteristic diagram and a detection characteristic diagram, wherein the first image encoder and the second image encoder have the same network structure. It should be understood that if there is no difference between the product deposit image and the product inspection image at the image source side, there should be a high degree of consistency and alignment between the deposit feature map and the inspection feature map extracted by the first image encoder and the second image encoder having the same network structure; conversely, if there is a difference between the two at the image source domain, such difference will also be captured and retained by the first image encoder and the second image encoder. In one particular example of the present application, the first image encoder and the second image encoder are convolutional neural network models with a spatial attention mechanism. It should be understood that the convolution neural network model can effectively extract local features of a high-dimensional image through convolution kernels, and the features of spatial dimensions can be made to have higher identifiability by combining a spatial attention mechanism, so that the accuracy of classification judgment is improved.
In an example, in the wine anti-counterfeiting traceability system 100, the differential feature map calculation module is further configured to: calculating a difference feature map between the evidence storing feature map and the detection feature map by using the following formula; wherein the formula is:
wherein the content of the first and second substances,
represents the differential characteristic map, and>
represents the evidence-depositing characteristic map, and>
represents the detection characteristicsSign, -based on the sign>
Representing subtraction by position.
Further, in the technical solution of the present application, a difference feature map between the evidence storing feature map and the detection feature map is further calculated to represent a difference between the product evidence storing image and the product detection image in a high-dimensional feature space. And then, the differential feature map is processed by a classifier to obtain a classification result, and the classification result is used for indicating whether the wine to be traced is a genuine product or not.
In an example, in the wine anti-counterfeiting traceability system 100, the anti-counterfeiting traceability result generating module includes: the characteristic diagram unfolding unit is used for unfolding the characteristic diagram of the difference characteristic diagram to obtain a classification characteristic vector; the correction unit is used for carrying out local structure fuzzy correction on the classification characteristic vector to obtain an optimized classification characteristic vector; and the classification result unit is used for enabling the optimized classification characteristic vector to pass through a classifier so as to obtain the classification result.
In an example, in the wine anti-counterfeiting traceability system 100, the feature map expanding unit is configured to: and expanding the differential feature map according to a row vector to obtain the classification feature vector.
Here, in the technical solution of the present application, the first image encoder and the second image encoder having the same network structure respectively perform high-dimensional feature extraction on the product deposit certificate image and the product inspection image, and represent a difference between the product deposit certificate image and the product inspection image in a high-dimensional feature space, that is, a substantial difference between the two images, by using a difference feature map between the two images. However, in the process of feature extraction, noise (represented as outliers in the feature map) existing in the source domain of the product certification image and the product detection image is also amplified synchronously through the processing of the first image encoder and the second image encoder, which may cause local structural blurring in the high-dimensional data manifold of the differential feature map, thereby reducing the expression certainty of the differential feature map and affecting the accuracy of the classification result of the differential feature map obtained by the classifier.
In an example, in the wine anti-counterfeiting traceability system 100, the correcting unit is further configured to: carrying out local structure fuzzy correction on the classification characteristic vector according to the following formula to obtain an optimized classification characteristic vector; wherein the formula is:
wherein the content of the first and second substances,
represents the classification feature vector>
Representing the optimized classification feature vector, device for combining or screening>
A transposed vector representing the classification feature vector, be->
Represents the square of the two-norm of the classification feature vector, is->
Is an ordered vector of eigenvalues of the classification eigenvector in order of magnitude, and said classification eigenvector->
Is in the form of a column vector>
Represents a vector point multiply, <' >>
Representing a matrix multiplication.
Here, by mapping the ordered vectors into the hilbert space defined by the self-inner product of the vectors, a meaningful measurement of the numerical relationship of the feature set in the consistency space can be realized, on the basis of which a feature space with an orthorhombic structure is constructed by embedding the relative position of the feature vectors, and the structural completion in the feature space is performed on the high-dimensional manifold of the feature vectors based on the vector query, so that the reduction of the expression certainty of the feature vectors due to the fuzzification structure can be avoided, and the accuracy of the classification result obtained by the classifier of the differential feature map can be improved.
In an example, in the wine anti-counterfeiting traceability system 100, the classification result unit includes: a full-concatenation coding subunit, configured to perform full-concatenation coding on the optimized classification feature vector using a plurality of full-concatenation layers of the classifier to obtain a coded classification feature vector; and the classification result generating unit is used for enabling the encoding classification feature vector to pass through a Softmax classification function of the classifier to obtain the classification result.
Here, it can be understood by those skilled in the art that the detailed functions and operations of the units and modules in the wine anti-counterfeiting traceability system 100 have been described in detail in the above description of the wine anti-counterfeiting traceability method with reference to fig. 1 to 5, and therefore, the repeated description thereof will be omitted.
The basic principles of the present application have been described above with reference to specific embodiments, but it should be noted that advantages, effects, etc. mentioned in the present application are only examples and are not limiting, and the advantages, effects, etc. must not be considered to be possessed by various embodiments of the present application. Furthermore, the foregoing disclosure of specific details is for the purpose of illustration and description and is not intended to be limiting, since the foregoing disclosure is not intended to be exhaustive or to limit the disclosure to the precise details disclosed.
The block diagrams of devices, apparatuses, systems referred to in this application are only given as illustrative examples and are not intended to require or imply that the connections, arrangements, configurations, etc. must be made in the manner shown in the block diagrams. These devices, apparatuses, devices, systems may be connected, arranged, configured in any manner, as will be appreciated by those skilled in the art. Words such as "including," "comprising," "having," and the like are open-ended words that mean "including, but not limited to," and are used interchangeably herein. The words "or" and "as used herein mean, and are used interchangeably with, the word" and/or, "unless the context clearly dictates otherwise. The word "such as" is used herein to mean, and is used interchangeably with, the phrase "such as but not limited to".
It should also be noted that in the devices, apparatuses, and methods of the present application, the components or steps may be decomposed and/or recombined. These decompositions and/or recombinations are to be considered as equivalents of the present application.
The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the application. Thus, the present application is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
The foregoing description has been presented for purposes of illustration and description. Furthermore, the description is not intended to limit embodiments of the application to the form disclosed herein. While a number of example aspects and embodiments have been discussed above, those of skill in the art will recognize certain variations, modifications, alterations, additions and sub-combinations thereof.
Claims (10)
1. An anti-counterfeiting traceability method for wines is characterized by comprising the following steps:
obtaining a product deposit evidence image of the wine product to be traced from the block chain network structure;
acquiring a product detection image of the wine product to be traced, which is acquired by a camera;
passing the product evidence storage image and the product detection image through a twin detection model comprising a first image encoder and a second image encoder to obtain an evidence storage characteristic diagram and a detection characteristic diagram, wherein the first image encoder and the second image encoder have the same network structure;
calculating a difference characteristic diagram between the evidence storing characteristic diagram and the detection characteristic diagram; and
and passing the differential characteristic diagram through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the liquor to be traced is a genuine product or not.
2. The wine anti-counterfeiting tracing method according to claim 1, wherein the first image encoder and the second image encoder are convolutional neural network models using a spatial attention mechanism.
3. The wine anti-counterfeiting tracing method according to claim 2, wherein the step of passing the product certificate storage image and the product detection image through a twin detection model comprising a first image encoder and a second image encoder to obtain a certificate storage characteristic diagram and a detection characteristic diagram comprises the steps of: using the layers of the first image encoder to perform respectively:
performing convolution processing on input data to generate a first convolution characteristic diagram;
pooling the first volumetric feature map to generate a first pooled feature map;
performing nonlinear activation on the first pooled feature map to generate a first activated feature map;
calculating a mean of the positions of the first activation profile along a channel dimension to generate a first spatial signature matrix;
calculating Softmax-like function values of all positions in the first spatial feature matrix to obtain a first spatial score matrix; and
calculating the position-based point multiplication of the first spatial feature matrix and the first spatial score matrix to obtain a first feature matrix;
wherein, the first feature matrix output by the last layer of the first image encoder is the evidence storing feature map.
4. The wine anti-counterfeiting tracing method according to claim 3, wherein the step of passing the product evidence storage image and the product detection image through a twin detection model comprising a first image encoder and a second image encoder to obtain an evidence storage characteristic diagram and a detection characteristic diagram comprises the steps of: using the layers of the second image encoder to perform respectively:
performing convolution processing on the input data to generate a second convolution characteristic diagram;
pooling the second convolved feature map to generate a second pooled feature map;
performing nonlinear activation on the second pooled feature map to generate a second activated feature map;
calculating the mean value of each position of the second activation feature map along the channel dimension to generate a second spatial feature matrix;
calculating Softmax-like function values of all positions in the second spatial feature matrix to obtain a second spatial score matrix; and
calculating the position-based point multiplication of the second spatial feature matrix and the second spatial score matrix to obtain a second feature matrix;
wherein the second feature matrix output by the last layer of the second image encoder is the detected feature map.
5. The wine anti-counterfeiting tracing method according to claim 4, wherein the step of calculating the difference characteristic diagram between the evidence storing characteristic diagram and the detection characteristic diagram comprises the following steps: calculating a difference feature map between the evidence storing feature map and the detection feature map by using the following formula;
wherein the formula is:
wherein the content of the first and second substances,
represents the differential feature map, is based on the characteristic map, and is based on the characteristic map>
Represents the evidence-depositing characteristic map, and>
the detection characteristic diagram is shown to represent,
representing subtraction by position.
6. The wine anti-counterfeiting traceability method according to claim 5, wherein the step of passing the differential feature map through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the wine to be traced is a genuine product or not, comprises the steps of:
carrying out characteristic diagram expansion on the differential characteristic diagram to obtain a classification characteristic vector;
carrying out local structure fuzzy correction on the classified feature vectors to obtain optimized classified feature vectors; and
and passing the optimized classified feature vector through a classifier to obtain the classification result.
7. The wine anti-counterfeiting tracing method according to claim 6, wherein the expanding the differential feature map to obtain a classification feature vector comprises: and expanding the differential feature map according to a row vector to obtain the classification feature vector.
8. The wine anti-counterfeiting tracing method according to claim 7, wherein the step of performing local structure fuzzy correction on the classification feature vector to obtain an optimized classification feature vector comprises the following steps: carrying out local structure fuzzy correction on the classification characteristic vector according to the following formula to obtain an optimized classification characteristic vector;
wherein the formula is:
wherein the content of the first and second substances,
represents the classification feature vector>
Representing the optimized classified feature vector, device for combining or screening>
A transposed vector representing the classification feature vector, be->
Represents the square of the two-norm of the classification feature vector, is->
Is an ordered vector of the feature values of the classification feature vector in order of magnitude and the classification feature vector->
Is in the form of a column vector>
Represents a vector dot-multiply,. Or->
Representing a matrix multiplication.
9. The wine anti-counterfeiting tracing method according to claim 8, wherein the step of passing the optimized classification feature vector through a classifier to obtain the classification result comprises the steps of:
performing full-joint coding on the optimized classification feature vector by using a plurality of full-joint layers of the classifier to obtain a coding classification feature vector; and
and passing the encoding classification feature vector through a Softmax classification function of the classifier to obtain the classification result.
10. The utility model provides a drinks anti-fake traceability system which characterized in that includes:
the evidence storing image obtaining module is used for obtaining a product evidence storing image of the wine product to be traced from the block chain network structure;
the detection image acquisition module is used for acquiring a product detection image of the wine product to be traced by the camera;
the image coding module is used for enabling the product evidence storage image and the product detection image to pass through a twin detection model comprising a first image coder and a second image coder to obtain an evidence storage characteristic diagram and a detection characteristic diagram, wherein the first image coder and the second image coder have the same network structure;
the difference characteristic diagram calculation module is used for calculating a difference characteristic diagram between the evidence storing characteristic diagram and the detection characteristic diagram; and
and the anti-counterfeiting traceability result generation module is used for enabling the differential characteristic graph to pass through a classifier to obtain a classification result, and the classification result is used for indicating whether the wine to be traceable is a genuine product or not.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310126237.3A CN115983874B (en) | 2023-02-17 | 2023-02-17 | Wine anti-counterfeiting tracing method and system thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310126237.3A CN115983874B (en) | 2023-02-17 | 2023-02-17 | Wine anti-counterfeiting tracing method and system thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115983874A true CN115983874A (en) | 2023-04-18 |
| CN115983874B CN115983874B (en) | 2023-06-30 |
Family
ID=85959907
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310126237.3A Active CN115983874B (en) | 2023-02-17 | 2023-02-17 | Wine anti-counterfeiting tracing method and system thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115983874B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116664961A (en) * | 2023-07-31 | 2023-08-29 | 东莞市将为防伪科技有限公司 | Intelligent identification method and system for anti-counterfeit label based on signal code |
| CN116797248A (en) * | 2023-08-22 | 2023-09-22 | 厦门瞳景智能科技有限公司 | Data traceability management method and system based on block chain |
| CN117251699A (en) * | 2023-11-17 | 2023-12-19 | 北京无极慧通科技有限公司 | Medical big data analysis method and system based on artificial intelligence |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108985413A (en) * | 2018-07-23 | 2018-12-11 | 程昔恩 | A kind of anti-false true-guaranteeing method and device of ceramic product |
| CN109102305A (en) * | 2018-08-06 | 2018-12-28 | 程昔恩 | A kind of article anti-counterfeit and source tracing method realized using block chain and its intelligent contract |
| CN110866461A (en) * | 2019-10-29 | 2020-03-06 | 上海躲猫猫信息技术有限公司 | Commodity automatic identification tracing anti-counterfeiting method and system based on texture partition |
| CN111461743A (en) * | 2020-03-26 | 2020-07-28 | 北京马上游科技有限责任公司 | NFC-based block chain Pu' er tea anti-counterfeiting tracing implementation method |
| CN113610540A (en) * | 2021-07-09 | 2021-11-05 | 北京农业信息技术研究中心 | River crab anti-counterfeiting tracing method and system |
| WO2022121290A1 (en) * | 2020-12-09 | 2022-06-16 | 中国农业科学院农业资源与农业区划研究所 | Trusted fruit tracing method and apparatus based on fruit pattern map and blockchain |
| CN114758162A (en) * | 2022-06-14 | 2022-07-15 | 北京市农林科学院信息技术研究中心 | Commodity anti-counterfeiting identification method and device, electronic equipment and storage medium |
| CN114971653A (en) * | 2022-05-23 | 2022-08-30 | 中山大学 | Ceramic tracing and identifying method based on block chain and trusted data space |
| CN115239515A (en) * | 2022-07-28 | 2022-10-25 | 德玛克(长兴)精密机械有限公司 | Precise intelligent processing and manufacturing system for mechanical parts and manufacturing method thereof |
| CN115511890A (en) * | 2022-11-23 | 2022-12-23 | 深圳市吉斯凯达智慧科技有限公司 | Analysis system for large-flow data of special-shaped network interface |
-
2023
- 2023-02-17 CN CN202310126237.3A patent/CN115983874B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108985413A (en) * | 2018-07-23 | 2018-12-11 | 程昔恩 | A kind of anti-false true-guaranteeing method and device of ceramic product |
| CN109102305A (en) * | 2018-08-06 | 2018-12-28 | 程昔恩 | A kind of article anti-counterfeit and source tracing method realized using block chain and its intelligent contract |
| CN110866461A (en) * | 2019-10-29 | 2020-03-06 | 上海躲猫猫信息技术有限公司 | Commodity automatic identification tracing anti-counterfeiting method and system based on texture partition |
| CN111461743A (en) * | 2020-03-26 | 2020-07-28 | 北京马上游科技有限责任公司 | NFC-based block chain Pu' er tea anti-counterfeiting tracing implementation method |
| WO2022121290A1 (en) * | 2020-12-09 | 2022-06-16 | 中国农业科学院农业资源与农业区划研究所 | Trusted fruit tracing method and apparatus based on fruit pattern map and blockchain |
| CN113610540A (en) * | 2021-07-09 | 2021-11-05 | 北京农业信息技术研究中心 | River crab anti-counterfeiting tracing method and system |
| CN114971653A (en) * | 2022-05-23 | 2022-08-30 | 中山大学 | Ceramic tracing and identifying method based on block chain and trusted data space |
| CN114758162A (en) * | 2022-06-14 | 2022-07-15 | 北京市农林科学院信息技术研究中心 | Commodity anti-counterfeiting identification method and device, electronic equipment and storage medium |
| CN115239515A (en) * | 2022-07-28 | 2022-10-25 | 德玛克(长兴)精密机械有限公司 | Precise intelligent processing and manufacturing system for mechanical parts and manufacturing method thereof |
| CN115511890A (en) * | 2022-11-23 | 2022-12-23 | 深圳市吉斯凯达智慧科技有限公司 | Analysis system for large-flow data of special-shaped network interface |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116664961A (en) * | 2023-07-31 | 2023-08-29 | 东莞市将为防伪科技有限公司 | Intelligent identification method and system for anti-counterfeit label based on signal code |
| CN116664961B (en) * | 2023-07-31 | 2023-12-05 | 东莞市将为防伪科技有限公司 | Intelligent identification method and system for anti-counterfeit label based on signal code |
| CN116797248A (en) * | 2023-08-22 | 2023-09-22 | 厦门瞳景智能科技有限公司 | Data traceability management method and system based on block chain |
| CN116797248B (en) * | 2023-08-22 | 2024-01-30 | 厦门瞳景智能科技有限公司 | Data traceability management method and system based on block chain |
| CN117251699A (en) * | 2023-11-17 | 2023-12-19 | 北京无极慧通科技有限公司 | Medical big data analysis method and system based on artificial intelligence |
| CN117251699B (en) * | 2023-11-17 | 2024-02-02 | 北京无极慧通科技有限公司 | Medical big data analysis method and system based on artificial intelligence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115983874B (en) | 2023-06-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115983874A (en) | Wine anti-counterfeiting tracing method and system | |
| US10902543B2 (en) | Neural network based insertion of watermark into images and tampering detection thereof | |
| Wang et al. | GETNET: A general end-to-end 2-D CNN framework for hyperspectral image change detection | |
| Wang et al. | Vehicle type recognition in surveillance images from labeled web-nature data using deep transfer learning | |
| Zhang et al. | Image region forgery detection: A deep learning approach. | |
| CN103238159B (en) | System and method for image authentication | |
| Saber et al. | A survey on image forgery detection using different forensic approaches | |
| CN104933721B (en) | Stitching image altering detecting method based on color filter array characteristic | |
| Mohamadian et al. | Detection of duplication forgery in digital images in uniform and non-uniform regions | |
| Zanardelli et al. | Image forgery detection: a survey of recent deep-learning approaches | |
| CN110457996B (en) | Video moving object tampering evidence obtaining method based on VGG-11 convolutional neural network | |
| CN116664961B (en) | Intelligent identification method and system for anti-counterfeit label based on signal code | |
| CN113610540A (en) | River crab anti-counterfeiting tracing method and system | |
| CN114387641A (en) | False video detection method and system based on multi-scale convolutional network and ViT | |
| Manjunatha et al. | Deep learning-based technique for image tamper detection | |
| CN111275070B (en) | Signature verification method and device based on local feature matching | |
| CN111107107A (en) | Network behavior detection method and device, computer equipment and storage medium | |
| CN106709915B (en) | Image resampling operation detection method | |
| Isaac et al. | Copy-Move forgery detection based on Harris Corner points and BRISK | |
| CN116822623A (en) | Method, device, equipment and storage medium for generating countermeasures network joint training | |
| CN116935180A (en) | Information acquisition method and system for information of information code anti-counterfeiting label based on artificial intelligence | |
| CN116778346A (en) | Pipeline identification method and system based on improved self-attention mechanism | |
| CN116912574A (en) | Multi-scale target perception classification method and system based on twin network | |
| CN114782796B (en) | Intelligent verification method and device for anti-counterfeiting of object image | |
| Agarwal et al. | Blind forensics of images using higher order local binary pattern |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |