CN116167807A

CN116167807A - Bill anti-counterfeiting method and device, electronic equipment and storage medium

Info

Publication number: CN116167807A
Application number: CN202310206078.8A
Authority: CN
Inventors: 李潇焓; 吴延生; 刘翌杰; 李文俊
Original assignee: Industrial and Commercial Bank of China Ltd ICBC
Current assignee: Industrial and Commercial Bank of China Ltd ICBC
Priority date: 2023-02-27
Filing date: 2023-02-27
Publication date: 2023-05-26

Abstract

The disclosure provides a bill anti-counterfeiting method, a bill anti-counterfeiting device, electronic equipment and a storage medium, and can be applied to the technical field of information security, the financial field or other fields. The bill anti-counterfeiting method comprises the following steps: generating anti-counterfeiting information according to the transaction key information; generating a carrier image according to at least one format information of the target bill; generating an original image of the anti-counterfeiting mark according to the carrier image and the anti-counterfeiting information by adopting a first network model; generating anti-counterfeiting verification information by adopting a second network model according to an image to be verified, which is extracted from the target bill, wherein the image to be verified comprises an anti-counterfeiting mark printing image and an anti-counterfeiting mark copying image; and determining the authenticity of the target bill according to the anti-counterfeiting information and the anti-counterfeiting verification information, wherein the first network model is obtained by training according to a data set comprising an original image of the anti-counterfeiting mark and a printed image of the anti-counterfeiting mark, and the second network model is obtained by training according to a copy image comprising the anti-counterfeiting mark.

Description

Bill anti-counterfeiting method and device, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of information security technologies, and in particular, to a bill anti-counterfeiting method, a device, an electronic device, and a storage medium.

Background

The traditional bank bill anti-counterfeiting method generally adopts modes of special paper, special ink, special printing equipment or special seal and the like, so that the problem of bank bill counterfeiting can be effectively prevented, but the existing bill anti-counterfeiting method has the problems of high raw material cost, capability of being identified by naked eyes and low universality.

Disclosure of Invention

In view of the above problems, the present disclosure provides a bill anti-counterfeiting method, apparatus, electronic device, readable storage medium and computer program product, which can effectively solve the problems of high manufacturing cost and poor versatility of bank bill anti-counterfeiting in the prior art.

According to a first aspect of the present disclosure there is provided a document security method, the method comprising: generating anti-counterfeiting information according to the transaction key information, wherein the anti-counterfeiting information has a set capacity; generating a carrier image according to at least one format information of the target bill; generating an original image of the anti-counterfeiting mark according to the carrier image and the anti-counterfeiting information by adopting a first network model, wherein the original image of the anti-counterfeiting mark is associated with at least one format information of the target bill; generating anti-counterfeiting verification information by adopting a second network model according to an image to be verified, which is extracted from the target bill, wherein the image to be verified comprises an anti-counterfeiting mark printing image and an anti-counterfeiting mark copying image; and determining the authenticity of the target bill according to the anti-counterfeiting information and the anti-counterfeiting verification information, wherein the first network model is obtained by training according to a data set containing the anti-counterfeiting mark original image and the anti-counterfeiting mark printing image, and the second network model is obtained by training according to the data set containing the anti-counterfeiting mark copying image.

In some exemplary embodiments of the disclosure, the generating the anti-counterfeiting information according to the transaction key information includes: determining key transaction contents according to the transaction key information; and generating anti-counterfeiting information according to the key transaction content.

In some exemplary embodiments of the present disclosure, the method further comprises: after generating the anti-counterfeiting information, preprocessing the anti-counterfeiting information comprises the following steps: scrambling the anti-counterfeiting information; encrypting the anti-counterfeiting information subjected to disorder treatment; and encoding the anti-counterfeiting information after encryption processing.

In some exemplary embodiments of the present disclosure, the first network model includes a wavelet coding network, a wavelet decoding network, and a discriminant network, and the training process for training the first network model includes: after the carrier image and the preprocessed anti-counterfeiting information are spliced, the carrier image and the preprocessed anti-counterfeiting information are used as input data of the wavelet coding network, and an original image of the anti-counterfeiting mark is generated; identifying the original image of the anti-counterfeiting mark and the carrier image by utilizing the identification network to obtain a first identification result; the anti-fake mark printing image is used as input data of a wavelet decoding network to generate reduction anti-fake information, and the anti-fake mark printing image is obtained according to the original image of the anti-fake mark; identifying the restored anti-counterfeiting information and the preprocessed anti-counterfeiting information by using the identification network to obtain a second identification result; and adjusting the parameter value of the first network model according to the loss function value until a preset training termination condition is met, wherein the loss function value comprises a first loss function value, a second loss function value and a third loss function value, the first loss function value and the second loss function value are associated with the anti-fake mark original image and the anti-fake mark printing image, and the third loss function value is associated with the anti-fake mark printing image.

In some exemplary embodiments of the present disclosure, the training process to train the second network model includes: the anti-counterfeiting mark copy image is used as input data of the wavelet decoding network, and reduction anti-counterfeiting information is generated; identifying the restored anti-counterfeiting information and the preprocessed anti-counterfeiting information by using the identification network to obtain a third identification result; and adjusting the parameter value of the wavelet decoding network according to the third loss function value until a preset training termination condition is met.

In some exemplary embodiments of the present disclosure, adjusting the parameter values of the first network model according to the loss function values includes: and adjusting the weight value of the loss function of the first network model according to the loss function value, wherein in training, the weight value of the third loss function is adjusted to be a set weight value, and the weight value of the first loss function and the weight value of the second loss function are adjusted to be increased along with the training process until the set weight value is reached and kept unchanged.

In some exemplary embodiments of the present disclosure, the training process for training the first network model further includes: processing the original image of the anti-counterfeiting mark by a noise layer to obtain a printing image of the anti-counterfeiting mark; and/or printing the original image of the anti-counterfeiting mark to a target bill, and extracting the image printed to the target bill to obtain a printing image of the anti-counterfeiting mark.

In some exemplary embodiments of the present disclosure, generating an original image of a security mark from the carrier image and the security information using a first network model includes: dimension expansion is carried out on the anti-counterfeiting information, and anti-counterfeiting expansion information is generated; and splicing the anti-counterfeiting expansion information and the carrier image, inputting the spliced anti-counterfeiting expansion information and the carrier image into a wavelet coding network of the first network, and generating an original image of the anti-counterfeiting mark.

In some exemplary embodiments of the present disclosure, generating anti-counterfeit verification information from an image to be verified extracted from the target ticket using a second network model includes: extracting the image to be verified by adopting a second network model to generate reduction anti-counterfeiting information; decoding the reduced anti-counterfeiting information; decrypting the decoded and restored anti-counterfeiting information; and performing anti-scrambling processing on the decrypted restored anti-counterfeiting information to generate anti-counterfeiting verification information.

In some exemplary embodiments of the present disclosure, determining authenticity of the target ticket from the security information and the security verification information includes: if the consistency of the anti-counterfeiting information and the anti-counterfeiting verification information meets a set threshold, determining that the target bill is true; and if the consistency of the anti-counterfeiting information and the anti-counterfeiting verification information does not meet a set threshold value, determining that the target bill is false.

In a second aspect of embodiments of the present disclosure, there is provided a document security device, the device comprising: the anti-counterfeiting information generation module is configured to generate anti-counterfeiting information according to the transaction key information, wherein the anti-counterfeiting information has a set capacity; the carrier image generation module is configured to generate a carrier image according to at least one format information of the target bill; the anti-counterfeiting mark original image generation module is configured to generate an anti-counterfeiting mark original image according to the carrier image and the anti-counterfeiting information by adopting a first network model, wherein the anti-counterfeiting mark original image is associated with at least one format information of the target bill, and the first network model is obtained by training according to a data set containing the anti-counterfeiting mark original image and an anti-counterfeiting mark printing image; the anti-fake verification information generation module is configured to generate anti-fake verification information according to an image to be verified, which is extracted from the target bill, by adopting a second network model, wherein the image to be verified comprises an anti-fake mark printing image and an anti-fake mark copying image, and the second network model is obtained by training the first network model according to a data set containing the anti-fake mark copying image; and the authenticity determining module is configured to determine the authenticity of the target bill according to the anti-counterfeiting information and the anti-counterfeiting verification information.

In some exemplary embodiments of the present disclosure, the security information generation module is configured to: determining key transaction contents according to the transaction key information; and generating anti-counterfeiting information according to the key transaction content.

In some exemplary embodiments of the present disclosure, the ticket security device further comprises a preprocessing module configured to: after generating the anti-counterfeiting information, preprocessing the anti-counterfeiting information, including: scrambling the anti-counterfeiting information; encrypting the anti-counterfeiting information subjected to disorder treatment; and encoding the anti-counterfeiting information after encryption processing.

In some exemplary embodiments of the present disclosure, the anti-counterfeit identification original image generation module is configured to: dimension expansion is carried out on the anti-counterfeiting information, and anti-counterfeiting expansion information is generated; and splicing the anti-counterfeiting expansion information and the carrier image, inputting the spliced anti-counterfeiting expansion information and the carrier image into a wavelet coding network of the first network, and generating an original image of the anti-counterfeiting mark.

In some exemplary embodiments of the present disclosure, the anti-counterfeiting authentication information generation module is configured to: extracting the image to be verified by adopting a second network model to generate reduction anti-counterfeiting information; decoding the reduced anti-counterfeiting information; decrypting the decoded and restored anti-counterfeiting information; and performing anti-scrambling processing on the decrypted restored anti-counterfeiting information to generate anti-counterfeiting verification information.

In some exemplary embodiments of the present disclosure, the authenticity determination module is configured to: if the consistency of the anti-counterfeiting information and the anti-counterfeiting verification information meets a set threshold, determining that the target bill is true; and if the consistency of the anti-counterfeiting information and the anti-counterfeiting verification information does not meet a set threshold value, determining that the target bill is false.

A third aspect of the present disclosure provides an electronic device, comprising: one or more processors; and a storage device for storing executable instructions which, when executed by the processor, implement a method according to the above.

A fourth aspect of the present disclosure provides a computer readable storage medium having stored thereon executable instructions which, when executed by a processor, implement a method according to the above.

A fifth aspect of the present disclosure provides a computer program product comprising a computer program which, when executed by a processor, implements a method according to the above.

According to the embodiment of the disclosure, the carrier image and the anti-counterfeiting information are processed by adopting the first network model obtained through training, so that the original image of the anti-counterfeiting mark is generated, the anti-counterfeiting information can be concealed, and the anti-counterfeiting capacity of the bill is improved. The second network model obtained through training is adopted to process the image to be verified, which is extracted from the target bill, and anti-fake verification information is generated, so that the target bill is accurately verified, in addition, the first network model is obtained through training according to a data set comprising an original anti-fake mark image and an anti-fake mark printing image, and therefore the first network model has a good identification effect on the anti-fake mark printing image; the second network model is obtained by training the first network model according to the data set containing the anti-counterfeiting mark copying image, and is trained on the basis of the first network model and trained by adopting the anti-counterfeiting mark copying image, so that the second network model further has good recognition rates for the anti-counterfeiting mark copying image and the anti-counterfeiting mark printing image respectively, the problem that the anti-counterfeiting bill is forged by using the copied bill as the azimuth mark copying image can be prevented, and the anti-counterfeiting capability of the bill is effectively improved.

Drawings

The foregoing and other objects, features and advantages of the disclosure will be more apparent from the following description of embodiments of the disclosure with reference to the accompanying drawings, in which:

FIG. 1 schematically illustrates a schematic diagram of a system architecture to which a ticket anti-counterfeiting method of embodiments of the present disclosure may be applied;

FIG. 2 schematically illustrates a flow chart of a ticket anti-counterfeiting method according to an embodiment of the present disclosure;

fig. 3 schematically illustrates a flowchart of a ticket anti-counterfeiting method according to an embodiment of the present disclosure in operation S210;

FIG. 4 schematically illustrates a flow chart of a ticket security method for preprocessing security information after the security information is generated in accordance with an embodiment of the present disclosure;

FIG. 5A schematically illustrates a training process diagram of a ticket anti-counterfeiting method in training a first network model according to an embodiment of the present disclosure;

FIG. 5B schematically illustrates another training process diagram of a ticket anti-counterfeiting method in training a first network model according to an embodiment of the present disclosure;

FIG. 6 schematically illustrates a training process diagram of a ticket anti-counterfeiting method in training a second network model according to an embodiment of the present disclosure;

FIG. 7 schematically illustrates a flow chart of a ticket anti-counterfeiting method according to an embodiment of the present disclosure in adjusting parameter values of a first network model;

Fig. 8 schematically illustrates a flowchart of a ticket anti-counterfeiting method according to an embodiment of the present disclosure in operation S230;

fig. 9 schematically illustrates a flowchart of a ticket anti-counterfeiting method according to an embodiment of the present disclosure in operation S240;

fig. 10 schematically illustrates a flowchart of a ticket anti-counterfeiting method according to an embodiment of the present disclosure in operation S250;

FIG. 11A schematically illustrates a process diagram of a ticket anti-counterfeiting method according to an embodiment of the present disclosure;

FIG. 11B schematically illustrates a process diagram of a ticket security method in preprocessing security information according to an embodiment of the disclosure;

FIG. 11C schematically illustrates a schematic diagram of an encoding process of a ticket anti-counterfeiting method in a pretreatment according to an embodiment of the disclosure;

FIG. 11D schematically illustrates a schematic diagram of a first network model of a ticket proof method according to an embodiment of the disclosure;

FIG. 11E schematically illustrates a process diagram of a ticket anti-counterfeiting method after extraction of a verification image from a target ticket using a second network model in accordance with an embodiment of the present disclosure;

FIG. 11F schematically illustrates a process diagram of processing reduced security information according to a ticket security method in accordance with an embodiment of the present disclosure;

FIG. 11G schematically illustrates a process diagram of a ticket proof method in decoding reduced security information according to an embodiment of the disclosure;

Fig. 12 schematically illustrates a block diagram of a ticket proof device according to an embodiment of the present disclosure;

fig. 13 schematically illustrates a block diagram of an electronic device adapted to implement a ticket anti-counterfeiting method according to an embodiment of the present disclosure.

Detailed Description

Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be understood that the description is only exemplary and is not intended to limit the scope of the present disclosure. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the present disclosure. It may be evident, however, that one or more embodiments may be practiced without these specific details. In addition, in the following description, descriptions of well-known structures and techniques are omitted so as not to unnecessarily obscure the concepts of the present disclosure.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The terms "comprises," "comprising," and/or the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.

All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. It should be noted that the terms used herein should be construed to have meanings consistent with the context of the present specification and should not be construed in an idealized or overly formal manner.

Where expressions like at least one of "A, B and C, etc. are used, the expressions should generally be interpreted in accordance with the meaning as commonly understood by those skilled in the art (e.g.," a system having at least one of A, B and C "shall include, but not be limited to, a system having a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.).

In the technical scheme of the disclosure, the acquisition, storage, application and the like of the related personal information of the user all conform to the regulations of related laws and regulations, necessary security measures are taken, and the public order harmony is not violated.

In the technical scheme of the disclosure, related operations such as acquisition, storage, application and the like of the personal information of the user are all authorized by the user.

In the disclosed embodiments, the term "transaction key information" may refer to, for example, key information associated with a transaction, or a unique index associated with a transaction from which other information associated with the transaction may be obtained from a bank database.

The terms "first network model", "second network model" may be, for example, neural networks that are trained on specific data sets, such as wavelet convolutional neural networks.

The term "original image of the security mark" refers to, for example, image information containing the security mark, which may be electronic information stored in a computer, with detailed information content of the original image of the security mark.

The term "anti-counterfeit mark print image" may refer to, for example, an image that includes an anti-counterfeit mark and is generated by printing, and the anti-counterfeit mark print image may be, for example, electronic information obtained by scanning a printed image having an anti-counterfeit mark by a specific scanning device. The electronic information of the printed image of the anti-counterfeiting mark and the original image of the anti-counterfeiting mark can be identical or have certain difference, and the difference is within a certain range, for example, the similarity is more than 98%.

The term "anti-counterfeit label copy image" may refer to, for example, an image that includes an anti-counterfeit label and is generated by copying an anti-counterfeit label print image, and for example, the anti-counterfeit label copy image may be electronic information obtained by scanning or copying an anti-counterfeit label print image formed by printing by a specific scanning device or copying device. The copy image of the security mark has a certain difference from the original image of the security mark and the print image of the security mark, respectively, and the difference can be distinguished and distinguished by a second network model as described below.

In the related art, documents with certain circulation or certification properties for recording information such as transaction contents are easy to be counterfeited, so that certain loss is caused, in order to improve the anti-counterfeiting performance of the documents (such as bank notes), paper, ink, special printing equipment or special seals of specific materials are generally adopted, the anti-counterfeiting notes have the defects of high raw material cost and low universality, the anti-counterfeiting contents are identifiable by naked eyes, and the anti-counterfeiting contents are easy to forge. For example, a problem arises in that counterfeit notes cannot be distinguished from counterfeit notes by performing imitation or copying of specific security information.

With the development of digital image watermarking technology, the digital watermarking technology is used for related aspects such as copyright protection, tracing, safety authentication and the like, and in order to solve the problems of the prior art, the visually indistinguishable anti-counterfeiting information is embedded in a carrier image by utilizing the digital image watermarking technology, so that the distinction cannot be judged by naked eyes before and after the embedding, the anti-counterfeiting capability and the difficulty of cracking the anti-counterfeiting information are improved, and the embedded anti-counterfeiting information is identified by a trained network model, so that the anti-counterfeiting effect of related files such as bills is realized.

In order to solve the above-mentioned problems, the present disclosure provides a bill anti-counterfeiting method, apparatus, electronic device, readable storage medium and computer program product, which can effectively hide anti-counterfeiting information, and can identify a target bill after processing (e.g. printing or copying), thereby judging the authenticity of the bill, improving the anti-counterfeiting capability of the bill and reducing the anti-counterfeiting technical cost. The bill anti-counterfeiting method comprises the following steps: generating anti-counterfeiting information according to the transaction key information, wherein the anti-counterfeiting information has a set capacity; generating a carrier image according to at least one format information of the target bill; generating an original image of the anti-counterfeiting mark according to the carrier image and the anti-counterfeiting information by adopting a first network model, wherein the original image of the anti-counterfeiting mark is associated with at least one format information of the target bill; generating anti-counterfeiting verification information by adopting a second network model according to an image to be verified, which is extracted from the target bill, wherein the image to be verified comprises an anti-counterfeiting mark printing image and an anti-counterfeiting mark copying image; and determining the authenticity of the target bill according to the anti-counterfeiting information and the anti-counterfeiting verification information, wherein the first network model is trained according to a data set containing an original image of the anti-counterfeiting mark and a printed image of the anti-counterfeiting mark, and the second network model is trained according to the data set containing a copied image of the anti-counterfeiting mark.

Fig. 1 schematically shows a schematic diagram of a system architecture to which a ticket anti-counterfeiting method of an embodiment of the present disclosure can be applied. It should be noted that fig. 1 is only an example of a system architecture to which embodiments of the present disclosure may be applied to assist those skilled in the art in understanding the technical content of the present disclosure, but does not mean that embodiments of the present disclosure may not be used in other devices, systems, environments, or scenarios. It should be noted that, the bill anti-counterfeiting method provided by the embodiment of the disclosure can be used in the information security technical field and the financial field in the information security related aspect, and also can be used in any field except the financial field, and the bill anti-counterfeiting method and the bill anti-counterfeiting device provided by the embodiment of the disclosure are not limited in application field.

As shown in fig. 1, an exemplary system architecture 100 to which the ticket anti-counterfeiting method may be applied may include

terminal devices

101, 102, 103, a network 104, and a server 105. The network 104 is used as a medium to provide communication links between the

terminal devices

101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.

The user may interact with the server 105 via the network 104 using the

terminal devices

101, 102, 103 to receive or send messages or the like. Various communication client applications, such as mail client applications, file processing class applications, shopping class applications, web browser applications, search class applications, instant messaging tools, mailbox clients, social platform software, etc., may be installed on the

terminal devices

101, 102, 103, as just examples.

The

terminal devices

101, 102, 103 may be various electronic devices having a display screen and supporting functions of data input, file transmission, data analysis, data processing, web browsing, etc., including but not limited to smartphones, tablet computers, laptop and desktop computers, etc.

The server 105 may be a server providing various services, such as a background management server (by way of example only) providing support for a user to utilize data acquired by the

terminal devices

101, 102, 103 or a browsed website. The background management server may analyze and process the received data such as the user request, and feed back the processing result (e.g., the web page, information, or data obtained or generated according to the user request) to the terminal device. The file or the like transmitted by the user may be analyzed or processed, and the terminal device may be controlled based on the processing result, for example, access to the terminal device may be restricted.

It should be noted that the bill anti-counterfeiting method provided by the embodiment of the present disclosure may be generally performed by the server 105. Accordingly, the ticket security devices provided by embodiments of the present disclosure may be generally disposed in the server 105. The ticket anti-counterfeiting method provided by the embodiment of the present disclosure may also be performed by a server or a server cluster that is different from the server 105 and is capable of communicating with the

terminal devices

101, 102, 103 and/or the server 105. Accordingly, the ticket anti-counterfeiting device provided by the embodiments of the present disclosure may also be provided in a server or a server cluster that is different from the server 105 and is capable of communicating with the

terminal devices

101, 102, 103 and/or the server 105.

It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

The bill anti-counterfeiting method of the disclosed embodiment will be described in detail below with reference to fig. 2 to 11G.

Fig. 2 schematically illustrates a flow chart of a ticket anti-counterfeiting method according to an embodiment of the present disclosure.

As shown in fig. 2, the flow 200 of the ticket anti-counterfeiting method of the present disclosure includes operations S210 to S250.

In operation S210, anti-counterfeiting information is generated according to the transaction key information, the anti-counterfeiting information having a set capacity size.

The transaction key information may refer to, for example, key information associated with a transaction, or a unique index associated with a transaction from which other information associated with the transaction may be obtained from a bank database.

For example, in a bank database storage system, each transaction that occurs for each customer has a unique index, which is a string of one or more fields that identifies the uniqueness of the transaction. When inquiring the transaction, the detailed information corresponding to the transaction in the background database can be obtained at the client through inquiring the transaction according to the unique index, so that operations such as verification and the like can be performed on the authenticity and the validity of the transaction.

The transaction key information includes transaction content associated with the transaction, such as information of transaction party, transaction time, transaction account, transaction currency, transaction content, etc. Specific content can be queried through transaction key information, and unique anti-counterfeiting information associated with the transaction can be generated according to the queried specific transaction content.

In operation S220, a carrier image is generated according to at least one format information of the target ticket.

The target ticket illustratively has one or more formatting information, where the formatting information may characterize the formatting content of the target ticket, for example, and may be information unrelated to the actual transaction content. For example, the format information includes contents such as a text format, a set decorative pattern, or a LOGO (LOGO) pattern of the target ticket.

And extracting at least one piece of format information of the target bill to generate a carrier image. For example, the LOGO of the target bill may be extracted as a carrier image, or the text format, decorative pattern, or the like of the target bill may be extracted as a carrier image.

According to the embodiment of the disclosure, the carrier pattern is generated by selecting the format information of the target bill, so that the anti-counterfeiting safety is improved. The format information of the target bill is only used for distinguishing the appearance of the bill and the like, is irrelevant to the transaction content on the bill, has no influence on the transaction information recorded by the bill when the format information is changed, is not easy to notice, can be used as a carrier image for embedding the anti-counterfeiting information, can be more accurate (for example, can embed the anti-counterfeiting information with larger capacity) when the number and the variety of the format information acquired from the target bill are increased as the carrier image, and can increase the difficulty when a plurality of carrier images are cracked, thereby improving the security of the target bill. In addition, the distinction between the image generated by embedding the anti-counterfeiting information into the carrier image and the original image cannot be observed and distinguished by naked eyes, so that the camouflage of the anti-counterfeiting information is realized, and the anti-counterfeiting capability of the bill is improved.

In operation S230, an original image of the anti-counterfeit label is generated according to the carrier image and the anti-counterfeit information using the first network model, and the original image of the anti-counterfeit label is associated with at least one format information of the target ticket. The first network model is trained from a dataset comprising an original image of the security mark and a printed image of the security mark.

In some exemplary embodiments of the present disclosure, after the first network model is trained, the carrier image and the anti-counterfeiting information may be fused to generate an anti-counterfeiting mark original image, which may be, for example, electronic information recorded in a storage device, according to which the electronic information of the anti-counterfeiting mark original image may be printed to generate an anti-counterfeiting mark print image, or the anti-counterfeiting mark original image may be displayed on a display device through the display device. In the embodiment of the disclosure, the original image of the anti-counterfeiting mark and the carrier image cannot be distinguished within a range visible to human eyes, that is, when the original image of the anti-counterfeiting mark and the carrier image are displayed through the display device, the original image of the anti-counterfeiting mark and the carrier image embedded with the anti-counterfeiting information cannot be distinguished by human eyes.

Illustratively, the original image of the security device is associated with at least one format information of the target document, e.g., the original image of the security device is identical to a logo of the target document or the original image of the security device is identical to the format content of the target document. By adopting the scheme, the anti-counterfeiting capacity of the bill can be improved, for example, when an anti-counterfeiting cracking person cracks based on the anti-counterfeiting capacity of the bill, under the condition that which format information is embedded anti-counterfeiting information is uncertain, the cracking difficulty is increased, and when the format information on the target bill is more, the cracking difficulty is further increased, so that the embodiment of the disclosure can improve the safety of the bill.

In an exemplary embodiment of the present disclosure, the first network model is trained from a dataset comprising a security device original image and a security device printed image. Therefore, the first network model can accurately distinguish the anti-fake mark printing image from the anti-fake mark original image, and meanwhile correct anti-fake verification information can be extracted from the anti-fake mark printing image, so that effective verification is achieved.

In some exemplary embodiments of the present disclosure, the original image of the security mark refers to, for example, image information including the security mark, which may be electronic information stored in a computer, and the detailed information content of the original image of the security mark may be displayed, for example, by a display device. The anti-counterfeit mark print image may be, for example, an image including the anti-counterfeit mark and generated by printing, and the information included in the anti-counterfeit mark print image may be, for example, electronic information obtained by scanning the printed image with the anti-counterfeit mark by a specific scanning device. The electronic information of the printed image of the anti-counterfeiting mark and the original image of the anti-counterfeiting mark can be identical, or certain differences exist, and the differences are within a certain range. The anti-counterfeit mark copy image may be, for example, an image that includes an anti-counterfeit mark and is generated by copying an anti-counterfeit mark print image, and for example, information included in the anti-counterfeit mark copy image may be electronic information obtained by copying or other copying means of the anti-counterfeit mark print image by a specific scanner or copying device. The copy image of the security mark has a certain difference from the original image of the security mark and the print image of the security mark, respectively, and the difference can be distinguished and distinguished by a second network model as described below.

In operation S240, anti-counterfeit verification information is generated according to an image to be verified extracted from the target ticket using the second network model, the image to be verified including an anti-counterfeit mark print image and an anti-counterfeit mark copy image. The second network model is trained by the first network model according to a data set containing the anti-counterfeiting mark copy image.

In an exemplary embodiment of the disclosure, the second network model is obtained by training the first network model according to a data set including the copy image of the anti-counterfeit label, and by continuing training the first network model, the second network model can identify the copy image including the anti-counterfeit label, for example, when the print image of the anti-counterfeit label and the copy image of the anti-counterfeit label are present, the trained second network model can identify.

For example, when the authenticity of a certain target bill cannot be determined, an image to be verified is extracted from the target bill, and the image to be verified may be an image extracted from one or more format information of the target bill. And inputting the image to be verified into the trained second network model to generate anti-counterfeiting verification information. The anti-counterfeit verification information may be, for example, information contained on an extracted anti-counterfeit label print image or an anti-counterfeit label copy image.

In operation S250, the authenticity of the target ticket is determined according to the anti-counterfeit information and the anti-counterfeit verification information.

For example, the target ticket may be determined to be genuine when the anti-counterfeit information and the anti-counterfeit verification information satisfy the set conditions, and may be determined to be fake otherwise.

According to the embodiment of the disclosure, the first network model is trained according to the data set comprising the anti-counterfeiting mark original image and the anti-counterfeiting mark printing image, so that the first network model has a good identification effect on the anti-counterfeiting mark printing image, the generated anti-counterfeiting mark original image and the carrier image cannot be distinguished under the condition of human eyes, and the camouflage degree of anti-counterfeiting information is improved. The second network model is obtained by training the first network model according to the data set containing the anti-counterfeiting mark copying image, and is trained on the basis of the first network model, and the anti-counterfeiting mark copying image is trained, so that the second network model further has good recognition rate on the anti-counterfeiting mark copying image and the anti-counterfeiting mark printing image, namely, when the anti-counterfeiting mark printing image with the anti-counterfeiting mark is copied, the second network model can be accurately distinguished, the problem of bill counterfeiting through copying can be prevented, and the anti-counterfeiting capacity of the bill is effectively improved.

Fig. 3 schematically shows a flowchart of a ticket anti-counterfeiting method according to an embodiment of the present disclosure in operation S210.

The following describes the flow of operation S210 in detail with reference to fig. 3, and as shown in fig. 3, the flow of generating the anti-counterfeiting information according to the key transaction information includes operations S211 to S212.

In operation S211, key transaction contents are determined according to the transaction key information.

For example, the transaction critical information is a transaction unique index for which customer a performs a payment transaction for a particular account, the bank data server records the transaction unique index associated with the payment transaction, and records a plurality of critical transaction contents for the unique index.

For example, the transaction content includes information such as transaction account number, transaction currency, transaction time, transaction card number, and the like. The account number may be a number set by the banking system for each account opening account, and the length may be set to a maximum of 34 digits, each digit being a number between 0 and 9, for example. The transaction currency may refer to the type of settlement currency for the transaction, such as: the RMB, japanese, dollar, etc. different currency types are distinguished by different numbers, the number length can be fixed to 3 bits, each bit is a number between 0 and 9. The transaction time may refer to the specific time that the transaction occurs, for example, the format may be set to 1999-10-10 12:00:01.123456, and the length may be 26 bits. The transaction card number may be media information of the physical card on which the transaction occurs, and the card number length may be set to a maximum of 34 bits, each bit being a number between 0 and 9.

TABLE-1

Table 1 illustrates unique index information associated with a transaction.

In operation S212, anti-counterfeiting information is generated according to the key transaction contents.

After determining the key transaction content, for example, a specific field type and length can be determined from the key transaction content according to a set manner to generate anti-counterfeiting information M0, where the anti-counterfeiting information M0 is used to be embedded into a carrier image of the bill. The carrier image has a set size, and the anti-counterfeiting information is set to a set capacity size, so that the technical difficulty is not increased and the usability of the technology is improved under the condition that the anti-counterfeiting property of the anti-counterfeiting information is improved. For example, when generating the security information, the capacity of the security information is constructed with the minimum number of bytes, for example, 6 bits after the account number is used, the transaction time stamp only retains information of year, month, day, time and minute, 6 bits after the transaction card number is used, and the like. According to the specific type and length of each field, the number of bits needed by each field is calculated, and the field of the obtained anti-counterfeiting information occupies 100 bits, and the details are shown in table 2.

TABLE 2

Fig. 4 schematically illustrates a flow chart of a ticket security method according to an embodiment of the present disclosure for preprocessing security information after the security information is generated.

As shown in fig. 4, in some embodiments of the present disclosure, after generating the security information, the process 300 of preprocessing the security information includes operations S310 to S330.

In operation S310, scrambling processing is performed on the security information.

For example, the scrambling process may generate a string of M and a string of M based on a particular random seed k1 by a pseudo-random number generator Pse-RNG ₀ Pseudo-random integer sequence N of the same length _k1 (i.e., 1 to 100), then with N _k1 For indexing, M ₀ The elements in the matrix are rearranged to obtain scrambled anti-counterfeiting information M ₁ . The specific formula is as follows:

N _k1 ＝Pse-RNG(k1) (1)

M ₁ (N _k1 )＝M ₀ (2)

according to the embodiment of the disclosure, the anti-counterfeiting information is scrambled and encrypted under the condition that the bit number of the effective information in the anti-counterfeiting information is unchanged.

In operation S320, encryption processing is performed on the security information after the disorder processing.

For example, an exclusive or encryption technique may be employed to first generate a series of pseudorandom 0/1 sequences N of the same length as M1 based on a particular random seed k2 using a pseudorandom number generator Pse-RNG _k2 And then N is _k2 And M is as follows ₁ Performing exclusive OR operation

The encryption can be completed, thereby obtaining the encrypted anti-counterfeiting information M ₂ The specific formula is as follows:

N _k2 ＝Pse-RNG(k2)， (3)

according to the embodiment of the disclosure, encryption processing of information can be realized under the condition that the bit number of effective information is unchanged.

In operation S330, the encrypted anti-counterfeiting information is encoded.

For example, the encoding of the anti-counterfeiting information after the encryption processing may be channel error correction encoding, which means that the transmitted signal is subjected to error correction and error detection encoding in the channel transmission process, and is mainly divided into two types of block codes and convolutional codes, and in this embodiment, for example, a common BCH block code may be selected. A thread group code having a code length of n and an information element length of 1 is generally denoted as (n, 1). For the primitive BCH code, it can be noted as (2 ^m -1, 1), for the requirement of error correction t bits, the supervisory bits of BCH need to satisfy the condition: (2 ^m -1-1.ltoreq.mt), the error correction capability and the coding efficiency are not compatible. In order to balance the coding efficiency and the error correction capability, for example, BCH codes of (31, 21), i.e. a code length of 31, and effective information bits of 21, can be used to correct 2 random error bits. In view of the encrypted security information M ₂ Length 100, so we need to encode it at least 5 times. To complete 5 BCH encodings (31, 21), we need to zero-padding the end to 21×5=105 bits, then block-encode (s 1-s 5) in sequence, by:

M ₃ ＝BCH(M ₂ ) (5)

After the above processing, the final anti-counterfeiting information M is obtained ₃ And inputting the image into the first network model to generate an original image of the anti-counterfeiting mark.

In the embodiment of the disclosure, the security of the anti-counterfeiting information can be effectively improved by preprocessing the anti-counterfeiting information, and the specific content of the anti-counterfeiting information cannot be directly obtained even after the anti-counterfeiting information in the original image of the anti-counterfeiting mark or the printed image of the anti-counterfeiting mark is extracted, so that the data security is improved.

Fig. 5A schematically illustrates a training process diagram of a ticket anti-counterfeiting method in training a first network model according to an embodiment of the disclosure.

In an embodiment of the present disclosure, the first network model includes a wavelet encoding network, a wavelet decoding network, and a discriminant network.

As shown in fig. 5A, the training process 400 for training the first network model includes operations S410 through S450.

In operation S410, after the carrier image and the preprocessed anti-counterfeiting information are spliced, the carrier image and the preprocessed anti-counterfeiting information are used as input data of the wavelet coding network, and an original image of the anti-counterfeiting mark is generated.

In operation S420, the identification network is used to identify the original image of the anti-counterfeit mark and the carrier image, so as to obtain a first identification result.

The first recognition result is used for comparing the similarity degree between the original image of the anti-counterfeiting mark and the carrier image, and parameters of the wavelet coding network are adjusted according to the first recognition result.

In operation S430, the anti-counterfeit mark print image is used as the input data of the wavelet decoding network to generate the restored anti-counterfeit information, and the anti-counterfeit mark print image is obtained according to the original image of the anti-counterfeit mark.

In operation S440, the discrimination network is used to identify and restore the anti-counterfeiting information and the preprocessed anti-counterfeiting information, thereby obtaining a second identification result.

In some embodiments of the present disclosure, the reduced anti-counterfeiting information may be, for example, information extracted from information of the printed image of the anti-counterfeiting mark, where the reduced anti-counterfeiting information has a certain relationship with the anti-counterfeiting information. For example, if the anti-counterfeit information is embedded into the carrier image to generate an original anti-counterfeit image, and the original anti-counterfeit image is printed to generate a printed anti-counterfeit image, the restored anti-counterfeit information obtained from the printed anti-counterfeit image has a consistency relationship with the anti-counterfeit information embedded into the carrier image, for example, the consistency is higher than 99%.

The second recognition result is used for comparing and restoring the similarity degree of the anti-counterfeiting information and the preprocessed anti-counterfeiting information, and adjusting parameters of the wavelet coding network and/or the wavelet decoding network according to the second recognition result, so that the first network model can accurately extract the anti-counterfeiting information in the anti-counterfeiting mark printing image.

In operation S450, the parameter values of the first network model are adjusted according to the loss function value until a preset training termination condition is satisfied.

The loss function values include a first loss function value, a second loss function value, and a third loss function value, the first loss function value and the second loss function value being associated with the original image of the security mark and the printed image of the security mark, the third loss function value being associated with the printed image of the security mark.

Illustratively, the first loss function may be a content loss function Lr, the second loss function may be a perceptual loss function Lp, and the third loss function may be a cross entropy loss function Ls. The first loss function value and the second loss function value are associated with the original image of the anti-counterfeiting mark and the printing image of the anti-counterfeiting mark, so that the anti-counterfeiting mark image printed on the target bill is not abnormal, and the image quality of the anti-counterfeiting mark image is ensured. And the third loss function value is associated with the anti-counterfeiting mark printing image to realize the robustness extraction of the anti-counterfeiting information.

Fig. 5B schematically illustrates another training process diagram of a ticket anti-counterfeiting method in training a first network model according to an embodiment of the present disclosure.

As shown in fig. 5B, the ticket anti-counterfeiting method according to the embodiment of the present disclosure further includes operations S460 and S470 in the training process 400 of training the first network model.

In operation S460, the original image of the anti-counterfeit mark is processed by the noise layer, and the printed image of the anti-counterfeit mark is obtained.

By processing the original image of the anti-counterfeiting mark through a noise layer, image distortion in a real environment, such as chromaticity and saturation degradation, shielding, printing scanning, noise, distortion, motion blurring and the like, is effectively simulated, so that effective extraction of information in a target bill is realized.

In operation S470, the original image of the anti-counterfeit mark is printed to the target bill, and the image printed to the target bill is extracted to obtain the printed image of the anti-counterfeit mark.

Illustratively, by employing the operation of operation S470, the reliability of the trained first network model and second network model in the real environment may be made higher.

In the embodiment of the present disclosure, the execution order of the operations S460 and S470 is not limited, and may be executed sequentially, or executed simultaneously, or alternatively executed.

Fig. 6 schematically illustrates a training process diagram of a ticket anti-counterfeiting method in training a second network model according to an embodiment of the disclosure.

As shown in fig. 6, the training process 500 for training the second network model includes operations S510 through S530.

In operation S5, the reduced anti-counterfeit information is generated using the anti-counterfeit label copy image as input data to the wavelet decoding network.

In operation S520, the discrimination network is used to identify and restore the anti-counterfeiting information and the pre-processed anti-counterfeiting information, thereby obtaining a third identification result.

In operation S530, the parameter values of the wavelet decoding network are adjusted according to the third loss function value until a preset training termination condition is satisfied.

According to the embodiment of the disclosure, the trained first network model is continuously trained by adopting the anti-counterfeiting mark copying image, so that the second network model can more accurately distinguish the anti-counterfeiting mark printing image from the anti-counterfeiting mark copying image, and the second network model can not accurately extract anti-counterfeiting information from the anti-counterfeiting mark copying image on the basis of greatly changing the performance part, so that the anti-counterfeiting information can be successfully and accurately extracted from the anti-counterfeiting mark printing image, and the forged target bill can be effectively distinguished.

Fig. 7 schematically illustrates a flow chart of a ticket anti-counterfeiting method according to an embodiment of the present disclosure in adjusting parameter values of a first network model.

As shown in fig. 7, in a flowchart S600 of adjusting parameter values of a first network model, a bill anti-counterfeiting method according to an embodiment of the present disclosure includes: and adjusting the weight value of the loss function of the first network model according to the loss function value, wherein in training, the weight value of the third loss function is adjusted to be a set weight value, and the weight value of the first loss function and the weight value of the second loss function are adjusted to be increased along with the training process until the set weight value is reached and kept unchanged.

Illustratively, the first network model may include a first loss function that may be a content loss function Lr, a second loss function that may be a perceptual loss function Lp, and a third loss function that may be a cross entropy loss function Ls. The loss function weight value thereof can be expressed by the following formula, for example.

L＝λ _r L _r +λ _p L _p +λ _s L _s (6)

Illustratively, the weight of the loss function may be dynamically adjusted, and the weight λ of the cross entropy loss function is the weight λ of the cross entropy loss function during network training _s The weights lambda of other perceptual loss functions remain unchanged _p And content loss function lambda _r Setting zero at the initial stage of network training, and linearly increasing along with the progress of the network training until reaching a preset threshold value, and keeping unchanged.

Fig. 8 schematically shows a flowchart of a ticket anti-counterfeiting method according to an embodiment of the present disclosure in operation S230.

As shown in fig. 8, the flow of the ticket anti-counterfeiting method in operation S230 of the embodiment of the present disclosure includes operations S231 to S232.

In operation S231, the anti-counterfeiting information is dimensionally expanded to generate anti-counterfeiting expansion information.

By dimension expansion of the anti-counterfeiting information, the anti-counterfeiting information can be spliced with the carrier image better, and the display effect of the carrier image is not negatively influenced.

In operation S232, the anti-counterfeiting expansion information and the carrier image are spliced and input to the wavelet coding network of the first network, and an original image of the anti-counterfeiting mark is generated.

Illustratively, in the process of operation S230, the training of the wavelet encoded network in the first network model is completed, and the anti-counterfeiting expansion information and the carrier image are input to generate an anti-counterfeiting mark original image, which can be used for printing onto the target bill, for example.

Fig. 9 schematically illustrates a flowchart of a ticket anti-counterfeiting method according to an embodiment of the present disclosure in operation S240.

As shown in fig. 9, the flow of operation S240 includes operations S241 to S244.

In operation S241, the image to be verified is extracted using the second network model, and the reduced anti-counterfeiting information is generated.

The image to be verified is illustratively extracted by adopting a wavelet decoding network in the trained second network model, for example, the image to be verified can be extracted for the area containing the anti-counterfeiting mark image, so as to generate the restored anti-counterfeiting information.

In operation S242, the reduced security information is decoded.

Illustratively, the operation is the inverse of channel error correction coding, similar to channel error correction coding in the preprocessing of the security information, and mainly completes the recovery of the security information M' ₃ Performing channel error correction decoding to obtain restored anti-counterfeiting information M 'after the channel error correction decoding' ₂ According to the channel error correction coding process in the anti-fake information generation module, M' ₂ The s5 fragment of (2) retains only the first 16 bits.

In operation S243, the reduced anti-counterfeit information after the decoding process is decrypted.

Illustratively, the present operation is used to recover the security information M 'after error correction decoding of the channel, as opposed to encryption in the security information pre-process' ₂ Decrypting to obtain decrypted restored anti-counterfeiting information M' ₁ . Specifically, a pseudo random number generator Pse-RNG is utilized to generate a string of M ' and M ' based on a specific random seed k2 ' ₂ Pseudo-random 0/1 sequence N of the same length _k2 And then N is _k2 With M' ₂ The decryption can be completed by exclusive OR operation, thereby obtaining the decrypted restored anti-counterfeiting information M' ₁ The formula is as follows

N _k2 ＝Pse-RNG(k2)， (7)

In operation S244, the recovered anti-counterfeit information after the decryption process is subjected to a scrambling process to generate anti-counterfeit verification information.

Illustratively, the present operation is used to recover the anti-counterfeiting information M 'after error correction decoding and decryption of the channel, as opposed to scrambling in the anti-counterfeiting information pre-process' ₁ Performing inverse scrambling to obtain original restored anti-counterfeiting information M' ₀ . Specifically, a pseudo random number generator Pse-RNG is utilized to generate a string of M ' and M ' based on a specific random seed k1 ' ₁ Pseudo-random integer sequence N of the same length _k1 (i.e., 1 to 100), then with N _k1 For indexing, M' ₁ The elements in the matrix are rearranged, so that the restored anti-counterfeiting information M 'after being scrambled is obtained' ₀ (i.e., anti-counterfeit authentication information) as follows:

N _k1 ＝Pse-RNG(k1)， (9)

M′ ₀ ＝M′ ₁ (N _k1 ).(10)

finally, according to the anti-counterfeiting information M ₀ And finally processed restored anti-counterfeiting information M' ₀ (i.e., anti-counterfeit authentication information) to determine the authenticity of the target ticket.

Fig. 10 schematically shows a flowchart of a ticket anti-counterfeiting method according to an embodiment of the present disclosure in operation S250.

As shown in fig. 10, the flow of operation S250 includes operation S251 and operation S252.

In operation S251, if the consistency of the anti-counterfeit information and the anti-counterfeit verification information satisfies the set threshold, the target ticket is determined to be authentic.

The security information may be, for example, data stored in a server, which may be retrieved by a call. For example, the threshold is set to 99%, and when the coincidence of the security information and the security verification information extracted from the target ticket exceeds 99%, the target ticket can be recognized as a genuine ticket.

In operation S252, if the consistency of the anti-counterfeit information and the anti-counterfeit verification information does not satisfy the set threshold, the target ticket is determined to be false.

For example, the threshold is set to 99%, and when the coincidence of the security information and the security verification information extracted from the target document does not exceed 99%, the target document can be recognized as a counterfeit document, for example, a copy document or a counterfeit document.

Fig. 11A schematically illustrates a process diagram of a ticket anti-counterfeiting method according to an embodiment of the present disclosure. Fig. 11B schematically illustrates a process diagram of a ticket security method in preprocessing security information according to an embodiment of the disclosure. Fig. 11C schematically illustrates a schematic diagram of a coding process of a ticket anti-counterfeiting method in pretreatment according to an embodiment of the disclosure. Fig. 11D schematically illustrates a structural diagram of a first network model of a ticket anti-counterfeiting method according to an embodiment of the present disclosure. Fig. 11E schematically illustrates a process diagram of a ticket anti-counterfeiting method after extraction of a verification image from a target ticket using a second network model, in accordance with an embodiment of the present disclosure. Fig. 11F schematically illustrates a process diagram of processing reduced security information according to a ticket security method according to an embodiment of the disclosure. Fig. 11G schematically illustrates a process diagram of a bill anti-counterfeiting method in decoding reduced anti-counterfeiting information according to an embodiment of the present disclosure.

The process schematic diagrams of fig. 11A to 11G are described in detail in the specific operation of the bill anti-counterfeiting method, and are not described herein.

Fig. 12 schematically shows a block diagram of a ticket proof device according to an embodiment of the present disclosure.

As shown in fig. 12, a ticket anti-counterfeiting device 700 according to an embodiment of the present disclosure includes an anti-counterfeiting information generation module 701, a carrier image generation module 702, an anti-counterfeiting mark original image generation module 703, an anti-counterfeiting verification information generation module 704, and an authenticity determination module 705.

The anti-counterfeiting information generating module 701 is configured to generate anti-counterfeiting information according to the transaction key information, wherein the anti-counterfeiting information has a set capacity. In an embodiment, the anti-counterfeiting information generation module 701 may be configured to perform the operation S210 described above, which is not described herein.

The carrier image generation module 702 is configured to generate a carrier image according to at least one format information of the target ticket. In an embodiment, the carrier image generating module 702 may be used to perform the operation S220 described above, which is not described herein.

The anti-counterfeiting mark original image generating module 703 is configured to generate an anti-counterfeiting mark original image according to the carrier image and the anti-counterfeiting information by adopting a first network model, wherein the anti-counterfeiting mark original image is associated with at least one format information of the target bill, and the first network model is obtained by training according to a data set comprising the anti-counterfeiting mark original image and the anti-counterfeiting mark printing image. In an embodiment, the anti-counterfeit label original image generation module 703 may be used to perform the operation S230 described above, which is not described herein.

The anti-counterfeiting verification information generating module 704 is configured to generate anti-counterfeiting verification information according to an image to be verified, which is extracted from the target bill, by using a second network model, wherein the image to be verified comprises an anti-counterfeiting mark printing image and an anti-counterfeiting mark copying image, and the second network model is obtained by training the first network model according to a data set containing the anti-counterfeiting mark copying image. In an embodiment, the anti-counterfeit verification information generation module 704 may be configured to perform the operation S240 described above, which is not described herein.

The authenticity determination module 705 is configured to determine authenticity of the target ticket according to the anti-counterfeiting information and the anti-counterfeiting verification information. In an embodiment, the authenticity determination module 705 may be configured to perform the operation S250 described above, which is not described herein.

In some exemplary embodiments of the present disclosure, the security information generation module 701 is configured to: determining key transaction contents according to the transaction key information; and generating anti-counterfeiting information according to the key transaction content.

In some exemplary embodiments of the present disclosure, the anti-counterfeit identification original image generation module 703 is configured to: dimension expansion is carried out on the anti-counterfeiting information, and anti-counterfeiting expansion information is generated; and splicing the anti-counterfeiting expansion information and the carrier image, inputting the spliced anti-counterfeiting expansion information and the carrier image into a wavelet coding network of the first network, and generating an original image of the anti-counterfeiting mark.

In some exemplary embodiments of the present disclosure, the anti-counterfeiting authentication information generation module 704 is configured to: extracting the image to be verified by adopting a second network model to generate reduction anti-counterfeiting information; decoding the reduced anti-counterfeiting information; decrypting the decoded and restored anti-counterfeiting information; and performing anti-scrambling processing on the decrypted restored anti-counterfeiting information to generate anti-counterfeiting verification information.

In some exemplary embodiments of the present disclosure, the authenticity determination module 705 is configured to: if the consistency of the anti-counterfeiting information and the anti-counterfeiting verification information meets a set threshold, determining that the target bill is true; and if the consistency of the anti-counterfeiting information and the anti-counterfeiting verification information does not meet a set threshold value, determining that the target bill is false.

According to an embodiment of the present disclosure, any of the anti-counterfeit information generation module 701, the carrier image generation module 702, the anti-counterfeit identification original image generation module 703, the anti-counterfeit verification information generation module 704, and the authenticity determination module 705 may be combined in one module to be implemented, or any of the modules may be split into a plurality of modules. Alternatively, at least some of the functionality of one or more of the modules may be combined with at least some of the functionality of other modules and implemented in one module. According to embodiments of the present disclosure, at least one of the anti-counterfeiting information generation module 701, the carrier image generation module 702, the anti-counterfeiting identification original image generation module 703, the anti-counterfeiting verification information generation module 704, and the authenticity determination module 705 may be implemented at least in part as hardware circuitry, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system-on-chip, a system-on-substrate, a system-on-package, an Application Specific Integrated Circuit (ASIC), or as hardware or firmware in any other reasonable manner of integrating or packaging the circuitry, or as any one of or a suitable combination of any of the three implementations of software, hardware, and firmware. Alternatively, at least one of the anti-counterfeit information generation module 701, the carrier image generation module 702, the anti-counterfeit identification original image generation module 703, the anti-counterfeit verification information generation module 704, and the authenticity determination module 705 may be at least partially implemented as a computer program module, which when executed, performs the corresponding functions.

Fig. 13 schematically illustrates a block diagram of an electronic device adapted to implement a ticket anti-counterfeiting method according to an embodiment of the present disclosure. The electronic device shown in fig. 13 is merely an example and should not impose any limitations on the functionality and scope of use of embodiments of the present disclosure.

As shown in fig. 13, an electronic device 800 according to an embodiment of the present disclosure includes a processor 801 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 802 or a program loaded from a storage section 808 into a Random Access Memory (RAM) 803. The processor 801 may include, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor and/or an associated chipset and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), or the like. The processor 801 may also include on-board memory for caching purposes. The processor 801 may include a single processing unit or multiple processing units for performing the different actions of the method flows according to embodiments of the disclosure.

In the RAM 803, various programs and data required for the operation of the electronic device 800 are stored. The processor 801, the ROM 802, and the RAM 803 are connected to each other by a bus 804. The processor 801 performs various operations of the method flow according to the embodiments of the present disclosure by executing programs in the ROM 802 and/or the RAM 803. Note that the program may be stored in one or more memories other than the ROM 802 and the RAM 803. The processor 801 may also perform various operations of the method flows according to embodiments of the present disclosure by executing programs stored in the one or more memories.

According to an embodiment of the present disclosure, the electronic device 800 may also include an input/output (I/O) interface 805, the input/output (I/O) interface 805 also being connected to the bus 804. The electronic device 800 may also include one or more of the following components connected to the I/O interface 805: an input portion 806 including a keyboard, mouse, etc.; an output portion 807 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and a speaker; a storage section 808 including a hard disk or the like; and a communication section 809 including a network interface card such as a LAN card, a modem, or the like. The communication section 809 performs communication processing via a network such as the internet. The drive 810 is also connected to the I/O interface 805 as needed. A removable medium 811 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 810 as needed so that a computer program read out therefrom is mounted into the storage section 808 as needed.

The present disclosure also provides a computer-readable storage medium that may be embodied in the apparatus/device/system described in the above embodiments; or may exist alone without being assembled into the apparatus/device/system. The computer-readable storage medium carries one or more programs which, when executed, implement methods in accordance with embodiments of the present disclosure.

According to embodiments of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, which may include, for example, but is not limited to: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this disclosure, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. For example, according to embodiments of the present disclosure, the computer-readable storage medium may include ROM 802 and/or RAM 803 and/or one or more memories other than ROM 802 and RAM 803 described above.

Embodiments of the present disclosure also include a computer program product comprising a computer program containing program code for performing the methods shown in the flowcharts. The program code, when executed in a computer system, causes the computer system to perform the methods provided by embodiments of the present disclosure.

The above-described functions defined in the system/apparatus of the embodiments of the present disclosure are performed when the computer program is executed by the processor 801. The systems, apparatus, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the disclosure.

In one embodiment, the computer program may be based on a tangible storage medium such as an optical storage device, a magnetic storage device, or the like. In another embodiment, the computer program may also be transmitted, distributed, and downloaded and installed in the form of a signal on a network medium, and/or from a removable medium 811 via a communication portion 809. The computer program may include program code that may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.

In such an embodiment, the computer program may be downloaded and installed from a network via the communication section 809, and/or installed from the removable media 811. The above-described functions defined in the system of the embodiments of the present disclosure are performed when the computer program is executed by the processor 801. The systems, devices, apparatus, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the disclosure.

According to embodiments of the present disclosure, program code for performing computer programs provided by embodiments of the present disclosure may be written in any combination of one or more programming languages, and in particular, such computer programs may be implemented in high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages. Programming languages include, but are not limited to, such as Java, c++, python, "C" or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of remote computing devices, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., connected via the Internet using an Internet service provider).

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

Those skilled in the art will appreciate that the features recited in the various embodiments of the disclosure and/or in the claims may be provided in a variety of combinations and/or combinations, even if such combinations or combinations are not explicitly recited in the disclosure. In particular, the features recited in the various embodiments of the present disclosure and/or the claims may be variously combined and/or combined without departing from the spirit and teachings of the present disclosure. All such combinations and/or combinations fall within the scope of the present disclosure.

The embodiments of the present disclosure are described above. However, these examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the embodiments cannot be used advantageously in combination. The scope of the disclosure is defined by the appended claims and equivalents thereof. Various alternatives and modifications can be made by those skilled in the art without departing from the scope of the disclosure, and such alternatives and modifications are intended to fall within the scope of the disclosure.

Claims

1. A ticket anti-counterfeiting method, comprising:

generating anti-counterfeiting information according to the transaction key information, wherein the anti-counterfeiting information has a set capacity;

Generating a carrier image according to at least one format information of the target bill;

generating an original image of the anti-counterfeiting mark according to the carrier image and the anti-counterfeiting information by adopting a first network model, wherein the original image of the anti-counterfeiting mark is associated with at least one format information of the target bill;

generating anti-counterfeiting verification information by adopting a second network model according to an image to be verified, which is extracted from the target bill, wherein the image to be verified comprises an anti-counterfeiting mark printing image and an anti-counterfeiting mark copying image; and

determining the authenticity of the target bill according to the anti-counterfeiting information and the anti-counterfeiting verification information,

wherein the first network model is trained according to a data set comprising the original image of the anti-counterfeiting mark and the printed image of the anti-counterfeiting mark,

the second network model is obtained by training the first network model according to a data set containing the anti-counterfeiting mark copying image.

2. The method of claim 1, wherein generating the anti-counterfeiting information according to the transaction critical information comprises:

determining key transaction contents according to the transaction key information; and

and generating anti-counterfeiting information according to the key transaction content.

3. The method of claim 2, further comprising:

after generating the anti-counterfeiting information, preprocessing the anti-counterfeiting information, including:

scrambling the anti-counterfeiting information;

encrypting the anti-counterfeiting information subjected to disorder treatment; and

and encoding the anti-counterfeiting information after encryption processing.

4. The method of claim 3, wherein the first network model comprises a wavelet encoding network, a wavelet decoding network, and a discriminant network,

the training process for obtaining the first network model comprises the following steps:

after the carrier image and the preprocessed anti-counterfeiting information are spliced, the carrier image and the preprocessed anti-counterfeiting information are used as input data of the wavelet coding network, and an original image of the anti-counterfeiting mark is generated;

identifying the original image of the anti-counterfeiting mark and the carrier image by utilizing the identification network to obtain a first identification result;

the anti-fake mark printing image is used as input data of a wavelet decoding network to generate reduction anti-fake information, and the anti-fake mark printing image is obtained according to the original image of the anti-fake mark;

identifying the restored anti-counterfeiting information and the preprocessed anti-counterfeiting information by using the identification network to obtain a second identification result; and

Adjusting the parameter value of the first network model according to the loss function value until a preset training termination condition is met,

the loss function values comprise a first loss function value, a second loss function value and a third loss function value, the first loss function value and the second loss function value are associated with the anti-fake mark original image and the anti-fake mark printing image, and the third loss function value is associated with the anti-fake mark printing image.

5. The method of claim 4, wherein,

the training process for obtaining the second network model comprises the following steps:

the anti-counterfeiting mark copy image is used as input data of the wavelet decoding network, and reduction anti-counterfeiting information is generated;

identifying the restored anti-counterfeiting information and the preprocessed anti-counterfeiting information by using the identification network to obtain a third identification result; and

and adjusting the parameter value of the wavelet decoding network according to the third loss function value until a preset training termination condition is met.

6. The method of claim 5, wherein adjusting the parameter values of the first network model according to the loss function values comprises:

adjusting a loss function weight value of the first network model according to the loss function value,

In the training, the weight value of the third loss function is adjusted to be a set weight value, and the weight value of the first loss function and the weight value of the second loss function are adjusted to be increased along with the training process until the set weight value is reached and kept unchanged.

7. The method of claim 4, wherein,

the training process for obtaining the first network model through training further comprises the following steps:

processing the original image of the anti-counterfeiting mark by a noise layer to obtain a printing image of the anti-counterfeiting mark; and/or

And printing the original image of the anti-counterfeiting mark to a target bill, and extracting the image printed to the target bill to obtain a printing image of the anti-counterfeiting mark.

8. The method of claim 1, wherein generating an original image of the security mark from the carrier image and the security information using a first network model comprises:

dimension expansion is carried out on the anti-counterfeiting information, and anti-counterfeiting expansion information is generated; and

and splicing the anti-counterfeiting expansion information and the carrier image, inputting the spliced anti-counterfeiting expansion information and the carrier image into a wavelet coding network of the first network, and generating an original image of the anti-counterfeiting mark.

9. The method of claim 1, wherein generating anti-counterfeit authentication information from the image to be authenticated extracted from the target ticket using a second network model comprises:

Extracting the image to be verified by adopting a second network model to generate reduction anti-counterfeiting information;

decoding the reduced anti-counterfeiting information;

decrypting the decoded and restored anti-counterfeiting information; and

and performing anti-scrambling treatment on the decrypted restored anti-counterfeiting information to generate anti-counterfeiting verification information.

10. The method of claim 1, wherein determining authenticity of the target ticket based on the anti-counterfeit information and the anti-counterfeit verification information comprises:

if the consistency of the anti-counterfeiting information and the anti-counterfeiting verification information meets a set threshold, determining that the target bill is true; and

and if the consistency of the anti-counterfeiting information and the anti-counterfeiting verification information does not meet a set threshold value, determining that the target bill is false.

11. A ticket security device comprising:

the anti-counterfeiting information generation module is configured to generate anti-counterfeiting information according to the transaction key information, wherein the anti-counterfeiting information has a set capacity;

the carrier image generation module is configured to generate a carrier image according to at least one format information of the target bill;

the anti-counterfeiting mark original image generation module is configured to generate an anti-counterfeiting mark original image according to the carrier image and the anti-counterfeiting information by adopting a first network model, wherein the anti-counterfeiting mark original image is associated with at least one format information of the target bill, and the first network model is obtained by training according to a data set containing the anti-counterfeiting mark original image and an anti-counterfeiting mark printing image;

The anti-fake verification information generation module is configured to generate anti-fake verification information according to an image to be verified, which is extracted from the target bill, by adopting a second network model, wherein the image to be verified comprises an anti-fake mark printing image and an anti-fake mark copying image, and the second network model is obtained by training the first network model according to a data set containing the anti-fake mark copying image; and

and the authenticity determining module is configured to determine the authenticity of the target bill according to the anti-counterfeiting information and the anti-counterfeiting verification information.

12. An electronic device, comprising:

one or more processors;

storage means for storing executable instructions which when executed by the processor implement the method according to any one of claims 1 to 10.

13. A computer readable storage medium having stored thereon executable instructions which, when executed by a processor, implement the method according to any of claims 1 to 10.

14. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 10.