CN115601872B

CN115601872B - Method and device for identifying currency authenticity

Info

Publication number: CN115601872B
Application number: CN202211215679.7A
Authority: CN
Inventors: 梁振斌; 游可; 侯岩; 张涛
Original assignee: Industrial and Commercial Bank of China Ltd ICBC
Current assignee: Industrial and Commercial Bank of China Ltd ICBC
Priority date: 2022-09-30
Filing date: 2022-09-30
Publication date: 2025-08-22
Anticipated expiration: 2042-09-30
Also published as: CN115601872A

Abstract

This application provides a currency authenticity identification method and device, which relates to the field of artificial intelligence and can also be used in the financial field. The method comprises: constructing a currency information knowledge graph based on collected images of real currency; and using the currency information knowledge graph to verify the basic information and texture information of the currency to be verified, thereby obtaining a currency authenticity identification result. This application can construct a currency information knowledge graph and use it to identify currency authenticity.

Description

Method and device for identifying authenticity of currency

Technical Field

The application relates to the field of artificial intelligence, which can be used in the financial field, in particular to a method and a device for identifying the authenticity of currency.

Background

The identification of the authenticity of paper money or coins is an important link of banking counter business. In the years of inadequate popularity of internet technology, banks typically access cash through counter business. On one hand, business personnel identify true problem coins through experience and related cognition, and on the other hand, the true or false is verified by mainly relying on a banknote validator. Nowadays, off-line network points of each big bank or inside or outside are provided with automatic teller machines (ATM for short). Through ATM, customers can access cash themselves. In daily life, due to factors such as folds, damages, dirty marks and the like of paper money, the phenomenon that the ATM cannot deposit normally sometimes occurs, even a embarrassing scene that money just taken out cannot be stored is caused, the deposit experience of a customer is reduced sharply, and the customer is forced to surge to counter business in a similar way, so that the workload of business personnel is increased to a certain extent.

Especially when a customer uses a foreign currency to conduct a banking related business, the authenticity of the currency can only be handled empirically by counter business personnel. Under the background, an intelligent, convenient and quick intelligent true problem coin identification system is urgently needed to rapidly assist business personnel to complete related business and improve the service efficiency of cash business.

Disclosure of Invention

Aiming at the problems in the prior art, the application provides a method and a device for identifying the authenticity of currency, which can construct a currency information knowledge graph and identify the authenticity of the currency according to the currency information knowledge graph.

In order to solve the technical problems, the application provides the following technical scheme:

in a first aspect, the present application provides a method for identifying authenticity of currency, comprising:

constructing a currency information knowledge graph according to the collected real currency image;

And verifying the basic information and the texture information of the money to be checked by using the money information knowledge graph to obtain a money authenticity identification result.

Further, the construction of the currency information knowledge graph according to the collected real currency image includes:

Extracting real currency attributes according to the real currency image, wherein the real currency attributes comprise currency, denomination, number, color grade, real plane texture characteristics and real three-dimensional texture characteristics;

Generating a relation among the real currencies according to the real currency attributes;

And generating the currency information knowledge graph according to the real currency, the real currency attributes and the relationships among the real currencies.

Further, the verifying the basic information of the money to be checked by using the money information knowledge graph comprises the following steps:

According to the currency type and the denomination of the currency to be tested, searching the real currency corresponding to the currency type and the denomination in the currency information knowledge graph to obtain the serial number and the color grade of the real currency corresponding to the currency type and the denomination;

and comparing the serial number and the color grade of the real currency corresponding to the currency and the denomination with the serial number and the color grade of the currency to be checked to obtain the basic information verification result of the currency to be checked.

Further, the texture information comprises plane texture information, and the verification of the basic information and the texture information of the money to be checked by using the money information knowledge graph comprises the following steps:

Fusing the planar texture features to be tested of the currency to be tested with the real planar texture features of the real currency corresponding to the currency and the denomination to obtain planar fusion features to be judged;

Fusing the real plane texture features of the real currency corresponding to the currency and the denomination to obtain real plane fusion features;

And calculating the deviation between the plane fusion feature to be judged and the real plane fusion feature, and generating a plane texture verification result corresponding to the plane texture information.

Further, the texture information comprises three-dimensional texture information, and the verification of the basic information and the texture information of the money to be checked by using the money information knowledge graph comprises the following steps:

Fusing the three-dimensional texture features of the currency to be tested with the real three-dimensional texture features of the real currency corresponding to the currency and the denomination to obtain three-dimensional fusion features to be judged;

the real three-dimensional texture features of the real currency corresponding to the currency and the denomination are fused, and the real three-dimensional fusion features are obtained;

and calculating information entropy between the stereo fusion feature to be judged and the real stereo fusion feature, and generating a stereo texture verification result corresponding to the stereo texture information.

Further, the method for identifying the authenticity of the currency further comprises the following steps:

Performing early warning processing according to the basic information verification result and the plane texture verification result;

And if the basic information verification result does not pass and/or the plane texture verification result does not pass, performing high-risk early warning processing.

Performing early warning processing according to the basic information verification result, the plane texture verification result and the three-dimensional texture verification result;

if the basic information verification result does not pass, the plane texture verification result and the three-dimensional texture verification result do not pass, high-risk early warning processing is carried out;

If the basic information verification result passes, but the plane texture verification result and the three-dimensional texture verification result do not pass, performing intermediate early warning processing;

And if the basic information verification result and the plane texture verification result pass, but the three-dimensional texture verification result does not pass, performing low-risk early warning processing.

In a second aspect, the present application provides a money discrimination apparatus comprising:

the knowledge graph construction unit is used for constructing a currency information knowledge graph according to the acquired real currency image;

And the identification result generation unit is used for verifying the basic information and the texture information of the money to be checked by using the money information knowledge graph to obtain a money true-false identification result.

Further, the knowledge graph construction unit includes:

The real currency attribute extraction module is used for extracting real currency attributes according to the real currency image, wherein the real currency attributes comprise currency, face value, number, color grade, real plane texture characteristics and real three-dimensional texture characteristics;

the real relation extracting module is used for generating the relation among the real currencies according to the real currency attributes;

And the knowledge graph construction module is used for generating the currency information knowledge graph according to the real currency, the real currency attributes and the relation among the real currencies.

Further, the identification result generating unit includes:

The real currency selecting module is used for searching the real currency corresponding to the currency type and the face value in the currency information knowledge graph according to the currency type and the face value of the currency to be tested, and obtaining the serial number and the color grade of the real currency corresponding to the currency type and the face value;

And the basic information verification module is used for comparing the serial number and the color grade of the real currency corresponding to the currency and the denomination with the serial number and the color grade of the currency to be verified to obtain a basic information verification result of the currency to be verified.

Further, the texture information includes plane texture information, and the recognition result generating unit includes:

The to-be-judged plane feature generation module is used for fusing the to-be-tested plane texture features of the to-be-tested currency and the real plane texture features of the real currency corresponding to the currency and the denomination to obtain to-be-judged plane fusion features;

The real plane feature generation module is used for fusing real plane texture features of real currency corresponding to the currency and the denomination to obtain real plane fusion features;

And the plane texture verification module is used for calculating the deviation between the plane fusion feature to be judged and the real plane fusion feature and generating a plane texture verification result corresponding to the plane texture information.

Further, the texture information includes stereoscopic texture information, and the recognition result generating unit includes:

The to-be-judged three-dimensional characteristic generation module is used for fusing the to-be-tested three-dimensional texture characteristic of the to-be-tested currency and the real three-dimensional texture characteristic of the real currency corresponding to the currency and the denomination to obtain to-be-judged three-dimensional fusion characteristic;

The real three-dimensional feature generation module is used for fusing real three-dimensional texture features of real currency corresponding to the currency and the denomination to obtain real three-dimensional fusion features;

and the three-dimensional texture verification module is used for calculating the information entropy between the three-dimensional fusion feature to be judged and the real three-dimensional fusion feature and generating a three-dimensional texture verification result corresponding to the three-dimensional texture information.

Further, the currency authenticity identification device further comprises:

The basic plane early warning unit is used for carrying out early warning processing according to the basic information verification result and the plane texture verification result;

Further, the currency authenticity identification device further comprises:

the basic plane three-dimensional early warning unit is used for carrying out early warning processing according to the basic information verification result, the plane texture verification result and the three-dimensional texture verification result;

In a third aspect, the application provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the currency authenticity identification method when executing the program.

In a fourth aspect, the present application provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method for identifying authenticity of a banknote.

In a fifth aspect, the application provides a computer program product comprising computer programs/instructions which, when executed by a processor, implement the steps of the method for identifying the authenticity of a banknote.

Aiming at the problems in the prior art, the method and the device for identifying the true and false of the currency can fully acquire the image characteristics of the true currency, establish the corresponding knowledge graph and data set, and find the effective evidence for distinguishing the true and false of each currency to be tested by adopting a relation model searching algorithm, so that the workload of related business personnel can be reduced to a certain extent, the handling efficiency of the bank counter business is accelerated, and the service experience of the bank counter business is improved.

Drawings

In order to more clearly illustrate the embodiments of the application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a flow chart of a method for identifying authenticity of currency in an embodiment of the application;

FIG. 2 is a flow chart of constructing a knowledge graph of currency information in an embodiment of the application;

FIG. 3 is a flowchart of verifying basic information of a coin to be checked according to an embodiment of the present application;

FIG. 4 is a flowchart of a method for verifying texture information of a coin under test according to an embodiment of the present application;

FIG. 5 is a second flowchart of verifying texture information of a coin under test according to an embodiment of the present application;

FIG. 6 is a block diagram of a money discrimination apparatus according to an embodiment of the present application;

FIG. 7 is a block diagram of a knowledge graph construction unit in an embodiment of the present application;

FIG. 8 is a diagram showing one of the structure of the recognition result generating unit in the embodiment of the present application;

FIG. 9 is a second block diagram of a knowledge graph construction unit in an embodiment of the application;

FIG. 10 is a third diagram of a knowledge graph construction unit according to an embodiment of the present application;

FIG. 11 is a diagram of an organization of a currency authenticity identification system based on image identification in an embodiment of the present application;

FIG. 12 is a schematic diagram of a basic knowledge system of a currency in an embodiment of the application;

FIG. 13 is a flowchart of different scene information acquisition in an embodiment of the application;

FIG. 14 is a schematic view showing the effect of processing the image information of money according to the embodiment of the present application;

FIG. 15 is a second schematic view showing the effect of processing the currency image information according to the embodiment of the present application;

FIG. 16 is a diagram of a currency key pattern and texture information according to an embodiment of the present application;

FIG. 17 is a schematic diagram of image fusion cancellation in an embodiment of the application;

FIG. 18 is a diagram showing the relationship between the overall comparison deviation and the number in the embodiment of the present application;

FIG. 19 is a flow chart of a currency pre-warning process in accordance with an embodiment of the present application;

Fig. 20 is a schematic structural diagram of an electronic device in an embodiment of the application.

Detailed Description

The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.

The method and the device for identifying the authenticity of the currency can be used in the financial field and any field except the financial field, and the application field of the method and the device for identifying the authenticity of the currency is not limited.

The technical scheme of the application obtains, stores, uses and processes the data and the like, which meet the relevant regulations of national laws and regulations.

In one embodiment, referring to fig. 1, in order to construct a currency information knowledge graph and identify the authenticity of a currency according to the knowledge graph, the present application provides a currency authenticity identification method, including:

S101, constructing a currency information knowledge graph according to an acquired real currency image;

and S102, verifying the basic information and the texture information of the money to be checked by using the money information knowledge graph to obtain a money authenticity identification result.

It will be appreciated that the present application is an efficient method of identifying currency authenticity using image recognition techniques. The method can reduce the error rate generated by relevant business personnel when distinguishing the authenticity of the currency, and can provide an effective currency recognition method for clients. The system corresponding to the method can fully utilize the image characteristics of the currency, construct an original data set (corresponding to a knowledge graph) according to the existing release currency, and find effective evidence for distinguishing the authenticity of each currency by adopting a relation model searching algorithm. By deploying the system, the workload of business personnel can be reduced to a certain extent, the handling efficiency of the bank counter business is accelerated, and the service experience of the bank counter business is improved.

The main functions of the image-recognition-based currency authenticity identification system corresponding to the currency authenticity identification method provided by the application are as follows:

Firstly, image information (corresponding to the image of the real currency) of the real currency is collected widely, and important parameters (corresponding to the attribute of the real currency) such as denomination, weight, texture and the like are attached to each currency according to the information, so that a relation model of the currency is built and stored in a database (corresponding to a knowledge graph). As the currency information in the database is real currency information, an effective and accurate basis can be provided for the true and false judgment of the currency to be checked.

Secondly, the newly issued currency information is imported into a database by utilizing an incremental storage technology, old currency information recovered from various channels such as a counter and an ATM (automatic teller machine) is archived and backed up, so that the access times of a search engine are reduced, and the comparison efficiency is improved.

Third, the deployment of the system provides counter service and convenience service. By providing counter business personnel with intelligent recognition glasses and/or other hardware devices carrying the system, the business personnel can easily recognize the authenticity of the currency, and the working efficiency is improved. Of course, the method provided by the present application may be deployed on the server in a manner of a software program and/or a virtual device, which is not limited to this.

The image-recognition-based currency authenticity recognition system is mainly divided into the following software functional components (the organization structure diagram can be seen in figure 11)

1. Information acquisition component 101

2. Data management component 102

3. Intelligent glasses identification component 103

4. ATM intelligent recognition component 104

5. APP Intelligent recognition component 105

6. Intelligent early warning alarm assembly 106

In order to achieve the above object, the execution main body of the method provided by the present application may execute the method by adopting the following technical steps:

Step 1, acquiring real currency image information;

Step 2, constructing a currency information data set;

step 3, establishing a currency information relation model database;

step 4, collecting image information of the money to be checked;

Step 5, extracting key mark information of the money to be checked;

Step 6, extracting the pattern and texture information of the money to be checked;

step 7, extracting the depth information of the money to be checked;

Step 8, finishing currency authentication;

And 9, alarming and early warning.

As can be seen from the above description, the method and the device for identifying true and false currencies provided by the application can fully collect image features of true currencies, establish corresponding knowledge maps and data sets, and find effective evidence for identifying true and false currencies for each currency to be tested by adopting a relational model searching algorithm, so that workload of related business personnel can be reduced to a certain extent, handling efficiency of bank counter business can be accelerated, and service experience of the bank counter business can be improved.

In one embodiment, referring to fig. 2, the construction of the currency information knowledge graph according to the collected real currency image includes:

S201, extracting real currency attributes according to the real currency image, wherein the real currency attributes comprise currency, denomination, number, color grade, real plane texture characteristics and real three-dimensional texture characteristics;

s202, generating a relation among the real currencies according to the real currency attributes;

And S203, generating the currency information knowledge graph according to the real currency, the real currency attributes and the relation among the real currencies.

It will be appreciated that in step 1 described above, the specific method of acquiring image information of real currency may include, but is not limited to, counting currency during the issuing of the currency and/or the cashing of the currency by the bank, and image acquisition of the currency by the information acquirer in the "image recognition based currency authenticity identification system" during the counting of the currency. The information collector comprises, but is not limited to, an image collector, a weight meter, a multifunctional camera and the like.

And the information collector is used for fully collecting the information of the image of the real currency, so that the image information (comprising the image of the real currency and the corresponding attribute of the real currency) of the real currency is collected, and the manual intervention is reduced. Because the image information of the currency is significant, once the image information is leaked, the result is not supposed, so that the encryption transmission and storage of the data are carried out by adopting an encryption algorithm such as RSA in the whole process in the acquisition process, and the encryption processing is carried out at the source end from the moment of image information generation. The embodiment of the application reduces errors caused by manual operation by providing an automatic information collector, does not influence the existing work rhythm of a bank, and ensures the smooth proceeding of the collection work.

In the step 2, the method for constructing the currency information data set is specifically to store the data in a database by using the currency image information acquired in the step 1. Since the encryption means is adopted in the information transmission process in the step 1, the currency image information stored in the database is encrypted data, and the construction of the data set cannot be directly performed. In the implementation, the key authentication U disk of three related service personnel can be inserted into three corresponding positions on the corresponding equipment at the same time, so that the equipment is started to execute the data set construction algorithm. The data set construction can be realized by utilizing various common data set construction and statistics methods such as classification, collection, arrangement, combination and the like. So that different kinds of money, different denominations and different (manufacturing) grades of money are stored in order. Wherein the color forming level can be preset. It should be noted that the real currency attributes stored in the data set include, but are not limited to, currency, denomination, number, color grade, real planar texture features and real stereoscopic texture features, where the real planar texture features represent planar (surface) texture features of the real currency, and the real stereoscopic texture features represent stereoscopic (concave-convex) texture features of the real currency.

Further, in the foregoing step 3, the specific method for establishing the currency information relationship model database (actually, establishing the currency information knowledge graph) is as follows:

And (3) drawing relations among currencies according to the currency image information data set obtained in the step (2) through a plurality of common drawing methods such as mining, analyzing, constructing, drawing and the like, so as to construct a relation model among the currencies. The model is roughly classified according to the number of sets, year of release, denomination, material, and the like of money.

The basic knowledge system of a certain currency is shown in fig. 12. When each set of currency is subjected to fixed-plate printing, the currencies with the same materials and denominations have the same color grade. For paper money, each piece of money with the same denomination is provided with a unique number, and the number is continuous and uninterrupted. So that the position of each banknote in the whole relation map and the relation between the banknote and the banknote adjacent to the banknote number can be known. For coins, the coins with the same denomination are cast with very similar metal components, and the coins with the same denomination have very similar properties although the coins are not numbered with the unique attribute. The embodiment of the application can greatly accelerate the information searching speed by constructing the knowledge graph, and particularly can play the advantages when the currency image information presents a massive mode.

In summary, three elements of knowledge graph construction, namely, entities, relationships and attributes, are in the embodiment of the present application the real currency, the relationships between the real currencies and the real currency attributes. All three elements can be obtained by the steps described above.

From the above description, the currency authenticity identification method provided by the application can construct a currency information knowledge graph according to the collected real currency image.

In one embodiment, referring to fig. 3, the verification of the basic information of the money to be inspected by using the money information knowledge graph includes:

S301, searching real currency corresponding to the currency type and the denomination in the currency information knowledge graph according to the currency type and the denomination of the currency to be tested, and obtaining the serial number and the color grade of the real currency corresponding to the currency type and the denomination;

s302, comparing the serial number and the color grade of the real currency corresponding to the currency and the denomination with the serial number and the color grade of the currency to be checked to obtain the basic information verification result of the currency to be checked.

It can be understood that the process of collecting the image information of the money to be inspected (corresponding to the money to be inspected) in the aforementioned step 4 is as follows:

When business personnel or users provide money to be checked, the three ways can be adopted, and different modes are required to be adopted for acquiring the image information of the money to be checked according to the three situations. Firstly, when a business person of a bank counter detects the money to be checked, only the money is required to be placed right in front of the sight line, and the image information of the money to be checked can be collected by using intelligent identification glasses on which a money true and false identification system based on image identification is mounted. Secondly, when the user detects by using an ATM, only the money is put into the ATM, and the laser scanner is used to scan out the planar color image and the stereoscopic depth image of the money to be detected in the ATM equipped with the "image recognition-based money authenticity recognition system", and the weight information of the money can be obtained. Thirdly, when a user utilizes the mobile phone APP to conduct currency recognition, currency image acquisition can be conducted through a camera of the mobile phone APP, and when the user mobile phone APP is provided with the depth camera, a corresponding three-dimensional depth image can be obtained. According to different application scenes, the embodiment of the application performs conditional currency image acquisition by means of the existing field device, so that on one hand, the additional investment for system construction can be reduced, and on the other hand, the existing currency counting and storage business process can be not influenced as much as possible. The algorithm flow chart is shown in fig. 13.

Further, the step 5 of extracting key mark information of the money to be checked refers to mark detection according to the money image information collected in the step 4. First, a series of operations such as graying, binarizing, and finding a digital outline are performed on collected money image information by using a character recognition algorithm in an image recognition algorithm, and money attributes such as a denomination, a year of release, a number, and an issuing bank of money are extracted.

The graying means that the image is subjected to gray processing, and as shown in fig. 14 (left), the original RGB image can be calculated for each pixel point in the image by using formula (1), so as to obtain a gray value of each pixel point. Since the original RGB image is an information set having three dimensions, it is difficult to effectively compare corresponding information in the comparison analysis. The graying information is obtained by performing a dimension reduction process on the three-dimensional information, and the value range of Gray is usually [0,255]. The processed image is shown in fig. 14 (middle). The formula is merely an example, and the present application is not limited thereto.

Gray=R×0.3+G×0.59+B×0.11 (1)

In the formula (1), R is the red pixel value of the pixel point, G is the green pixel value of the pixel point, and B is the blue pixel value of the pixel point.

The binarization is that the whole image is described by 0 or 1 on the basis of gray scale, and the processing mode can better display the outline characteristics of the image. A threshold value ζ can be generally set as a binarization coefficient for dynamically adjusting the binarized image effect. For example, under the condition that ζ=127.5, a binarized image can be obtained as shown in fig. 14 (right side).

After the algorithm processing, the result is finally output by a computer, and a sign information block diagram of the front side and the back side of a certain paper currency can be obtained, as shown in fig. 15. The embodiment of the application can conveniently acquire the basic image information of the money to be checked by utilizing the processing mode, and can find the corresponding currency information in the currency information knowledge graph in the step 3 by utilizing the basic image information, particularly the serial number information, thereby realizing one-to-one comparison of two groups of currency information and providing accurate comparison basis.

From the above description, the method for identifying the true or false of the money provided by the application can utilize the money information knowledge graph to verify the basic information of the money to be checked.

In one embodiment, referring to FIG. 4, the texture information includes plane texture information, and the verification of the basic information and the texture information of the money to be inspected by using the money information knowledge graph includes:

S401, fusing the planar texture features to be tested of the currency to be tested with the real planar texture features of the real currency corresponding to the currency type and the denomination to obtain planar fusion features to be judged;

S402, fusing the real plane texture features of the real currency corresponding to the currency and the denomination to obtain real plane fusion features;

S403, calculating deviation between the plane fusion feature to be judged and the real plane fusion feature, and generating a plane texture verification result corresponding to the plane texture information.

It can be understood that the process of extracting the texture information of the money to be inspected in the aforementioned step 6 is as follows:

and (3) searching in a currency information knowledge graph according to the currency attributes such as the currency issuing line, the issuing year and the denomination obtained in the step (5), and judging the key pattern information of the country to which the currency belongs and the currency for issuing the denomination in the year. When the information of the money issue and the information of the money output cannot be found from the database by using the serial number information of the money in the step 5, the extracted key pattern information and the texture information need to be fused and compared with the same key information of the neighboring money, so that the difference is found. The currency pattern and texture information are shown in fig. 16. By using the fusion method of the grid division, the fusion time can be greatly shortened. Once abnormality is found, the suspected coin can be judged, and deviation analysis is carried out according to the integrated binary histogram value obtained after fusion and the integrated binary histogram value of the original multiple images of the adjacent currencies in the currency information knowledge graph, wherein a deviation calculation formula is as follows.

Where yj represents the metric value of the binary histogram calculated for a certain currency to be detected, C1 and C2 are the metrics of the binary histograms of adjacent currencies, and D1 and D2 represent the dimensions of adjacent currencies that are involved in comparison, which are generally considered to be one-dimensional. When the maximum deviation value is larger than the prescribed value beta, the coin is considered to be a problem coin, and when the maximum deviation value is smaller than the beta, the coin is considered to be a doubtful coin, and further judgment is needed. The method can reduce the probability of misjudgment of the currency due to pollution marks and the like to a certain extent, and can adapt to the extremely fine color forming difference of the currency in the production process.

From the above description, the method for identifying the true or false money provided by the application can utilize the money information knowledge graph to verify the basic information and the texture information of the money to be checked.

In one embodiment, referring to FIG. 5, the texture information includes three-dimensional texture information, and the verification of the basic information and the texture information of the money to be inspected by using the money information knowledge graph includes:

s501, merging the three-dimensional texture features of the currency to be checked with the real three-dimensional texture features of the real currency corresponding to the currency and the denomination to obtain three-dimensional fusion features to be checked;

s502, merging real three-dimensional texture features of real currency corresponding to currencies and denominations to obtain real three-dimensional merged features;

And S503, calculating information entropy between the stereo fusion feature to be judged and the real stereo fusion feature, and generating a stereo texture verification result corresponding to the stereo texture information.

It can be understood that, the step 7 of extracting the depth information of the currency to be checked means that after a series of steps from the step 1 to the step 6, the authenticity of the suspected currency still cannot be determined, and further determining the authenticity of the currency according to the depth information (three-dimensional texture feature) in the currency information is required. According to the money discrimination rule, the texture information on the real money is not flat but has a certain degree of unevenness, and the unevenness is also perceived to be noticeable to the touch. The embodiment of the application adopts a depth camera to collect depth information (three-dimensional texture characteristics) of currency, namely, the concave-convex characteristic information is collected. The depth image of currency is different from the common visible light image, and is a gray level image which cannot be resolved by naked eyes, and gray level values on the image represent depth information. Preliminary processing is performed by a commonly used mathematical method, and the processing includes, but is not limited to, averaging, maximum value, minimum value, deviation value, variance value and the like, so that the overall digital depth information of the picture is represented, and whether the texture depth information is consistent or approximate in overall measurement can be obtained by comparing the depth information of the currency adjacent to the currency (adjacent on the currency information knowledge graph).

If the measurement deviation is larger, the image to be detected and one or more images close to the image in the information base are further subjected to depth information fusion elimination processing to find out local inconsistent positions, so that the authenticity of the currency is judged.

As shown in fig. 17, the leftmost depth image information of a real banknote in the figure, the middle depth image information of a problem banknote and the rightmost fused result information can be seen from fig. 17, the fused image still has obvious image characteristics, so that the banknote to be detected can be judged to be the problem banknote.

In theory, the judgment basis of the fusion comparison is mainly realized by measuring the information entropy in the image, and the calculation formula is as follows, namely, the fused pixel information is summed, so that the corresponding information entropy H (A) is obtained.

H(A)=-∑_aP_A(a)log₂P_A(a) (3)

A represents an event, H (A) represents information entropy of occurrence of the event A, alpha represents loss of image error after fusion, and P _A (alpha) represents probability of the event error being alpha in image fusion. Since the processing of the image is in binary representation, log ₂P_A (alpha) is used as a dimension-reduction coefficient, thereby reducing fluctuation of the calculated value. When the information entropy is higher, namely the error loss of the fused image is smaller than alpha, the similarity between the fused image and the original image is extremely high, and the fused image can be judged to be a real coin. When the information entropy is lower, namely the error loss of the fused image is larger than or equal to alpha, the similarity between the fused image and the original image is extremely low, and the problem coin can be judged. Texture information with convexity provided by currency printing can be well utilized by comparing depth images. The method is a key means of currency authentication, and can effectively avoid major errors of authentication results. Fig. 18 is a graph showing the relationship between the overall comparison deviation and the comparison number, curve 1 is the lower deviation limit, curve 2 is the coin to be inspected, and curve 3 is the upper deviation limit. The specific method is that fig. 18 is a relation diagram between the overall comparison deviation and the comparison number, a curve 1 is a deviation lower limit, a curve 2 is a coin to be checked, and a curve 3 is a deviation upper limit. When the number of the inventory currencies to be detected can be compared, a vertical straight line l can be made in fig. 18, the straight line intersects with the upper limit to obtain an upper limit gray value G1, and intersects with the lower limit to obtain a lower limit gray value G2, that is, when the calculated gray value of the to-be-detected currencies is between [ G1, G2], the to-be-detected currencies cannot be determined to be inconsistent with the requirements.

In one embodiment, the method for identifying authenticity of currency further includes:

Further, the step 8 of performing the currency authentication means that the system finally gives an authentication result after the steps 1 to 7. For the system, the discrimination result is given in the form of probability P. Assuming that the number of comparison sheets of currency is N and the total comparison weight sum is 1, P＝a₁×P₁+a₂×P₂+a₃×P₃……,a₁+a₂+a₃+…＝1, is provided, wherein a is the comparison weight of each picture, and the comparison weight is reduced by a multiple k according to the proximity relation, namely a meets the relationship of an equal ratio series. P ₁、P₂. Comparing the resulting similarity probabilities for each graph with the graph to be tested.

And when P is smaller than the set value gamma and is larger than or equal to xi, the user is prompted to "the currency is possibly a problem currency, and the currency is flattened and re-detected". When P is smaller than xi, the currency is directly prompted to be a problem currency, and the problem currency is processed by a bank. The judgment flow chart is shown in fig. 19.

Furthermore, the alarm and early warning in the step 9 refers to comprehensively analyzing the true and false states and circulation states of the currencies in different regions according to the historical data generated in the steps 1 to 8 after the system is operated for a period of time.

In order to more clearly illustrate the method provided by the present application, two examples are presented below.

Example 1

The intelligent money studying and judging system is provided for the counter business personnel small A, and intelligent recognition glasses are provided for the intelligent money studying and judging system to judge the authenticity of the 100 RMB in the hand.

The application relates to a currency true and false identification system based on image identification, which adopts field equipment to provide currency identification service for users according to the existing scene judgment, and comprises the following specific steps:

and 1', acquiring image information of real currency, namely according to the need of counting the currency in the process of issuing the currency and cashing the currency by a bank, and enabling the currency to flow through an information acquisition device carrying the system in the counting process. The collector utilizes the loaded weighing device, the page turning device and the multifunctional camera to fully collect information of the currency. Therefore, the real currency information is automatically collected, and manual intervention is reduced.

Some sources of the obtained currency information are shown in table 1, which is only an example for protecting the privacy of the currency sources, and has no authenticity, and x and y represent numbers.

TABLE 1 Currency Source information Table

And 2', constructing a currency information data set, namely storing the data in a database by utilizing the currency information acquired in the step 1'. Since step 1' adopts encryption means in the information transmission process, the information set in the database is encrypted data, and the data set construction cannot be directly performed.

And 3', establishing a currency information relation model database, namely displaying the relation among currencies through mining, analyzing, constructing and drawing according to the currency information data set obtained in the step 2', and constructing a relation model among currencies.

And 4', collecting image information of the money to be checked, namely that the counter business personnel small A is wearing intelligent recognition glasses to recognize 100-element banknotes in the hand.

And 5', extracting key mark information of the money to be inspected, namely carrying out mark detection on the key mark information according to the data information acquired in the step 4. First, a series of operations such as gradation, binarization, finding a digital outline, and cutting are performed on the collected money image information by using a character recognition algorithm among image recognition algorithms, and the denomination, the year of release, the number, and the issuing bank of the money are extracted. The invention can conveniently acquire the basic information of the money to be checked by utilizing the processing mode, and can find the corresponding currency information in the relation model database in the step 3 by utilizing the basic information, particularly the serial number information, thereby realizing one-to-one comparison of two groups of currency ratio information and providing accurate comparison basis. The identification mark of the small a on the currency can be known according to the algorithm as shown in fig. 15, and the numbered currency is not searched from the database, so that the currency can be judged to circulate in the market before being collected.

And 6', extracting the pattern and texture information of the money to be checked, namely easily judging the country where the money belongs and the key pattern information of the money with the denomination issued in the year according to the issuing row, the issuing year and the denomination of the money obtained in the step 5. When the number information of the currency cannot be used to find the information of the issuing and the leaving of the currency from the database in the step 5, fusion comparison analysis is required to be performed on the extracted key pattern information and the texture information and the same key information of the adjacent currency, so that the difference is found. By using the mode fusion method of grid division, the fusion time can be greatly shortened, once abnormality is found, the suspected currency can be judged, and deviation analysis is carried out according to the obtained integral binary histogram value after fusion and the integral binary histogram value of the original images of a plurality of adjacent currencies, wherein the deviation calculation formula is as follows.

When the maximum deviation value is larger than the prescribed value beta, the coin is considered to be a problem coin, and when the maximum deviation value is smaller than the beta, the coin is considered to be a doubtful coin, and further judgment is needed. The method can reduce the probability of misjudgment of the currency due to pollution marks and the like to a certain extent, and can adapt to the extremely fine color forming difference of the currency in the production process. Here, it can be seen that the key pattern and texture information extraction of the small A to the money is shown in FIG. 6, the calculated deviation value is 2.91, the set requirement is met, and the true money can be judged.

And 7', extracting the depth information of the currency to be checked, namely after a series of operations of the steps 1 to 6 and the like, if the small A still does not trust the suspected currency to be true, further judging whether the currency is true or false according to the depth information in the currency information. According to the money discrimination rule, the texture information on the real money is not flat but has a certain degree of unevenness, and the unevenness is also perceived to be noticeable to the touch. The application adopts the depth camera to collect the depth information of the currency, namely, collect the concave-convex characteristic information. The depth image is different from the common visible light image, and is a gray image which cannot be resolved by naked eyes, and gray values on the image represent depth information. The overall depth information of the picture can be represented by calculating an average value, a maximum value, a minimum value, a deviation value and a variance value, and whether the texture depth information is consistent or approximate in overall measurement can be obtained by comparing the currency depth information adjacent to the currency. If the measurement deviation is large, two compared depth images are further fused to find out local inconsistent positions, so that the authenticity of the currency is judged. The fusion comparison is judged by measuring the information entropy in the image, and the calculation formula is as follows.

H(A)=-∑_aP_A(a)log₂P_A(a) (2)

When the information entropy is higher, namely the error loss of the fused image is smaller than alpha, the similarity between the fused image and the original image is extremely high, and the fused image can be judged to be a real coin. When the information entropy is lower, namely the error loss of the fused image is larger than or equal to alpha, the similarity between the fused image and the original image is extremely low, and the counterfeit money can be judged. By comparing the depth images, texture information with convexity provided by currency printing can be well used as a key means for currency identification, and major errors of identification results can be effectively avoided. By calculation, H (a) =99.9999%, the money in the small a hand can be judged as a true money.

Step 8', finish currency authentication, in step 1 to step 7, the system gives an authentication result finally through a series of authentication means. For the system, the discrimination result is given in the form of probability P. And when P is smaller than the set value gamma and is larger than or equal to xi, the user is prompted to "the currency is possibly a problem currency, and the currency is flattened and re-detected". When P is smaller than xi, the currency is directly prompted to be a problem currency, and the problem currency is processed by a bank. In this way, psychological stress on the user can be reduced, so that the user is not frightened by the suddenly remembered alarm. The counter business personnel, small a, recognizes the currency as true through a series of operations and feeds back to the user, who indicates that the business capabilities of small a are highly appreciated.

And 9', alarming and early warning, namely comprehensively analyzing the true and false states and circulation states of the currencies in different regions according to the historical data generated in the steps 1 to 8 after the system is operated for a period of time.

Example 2

The intelligent money research and judgment system is provided for the user small B, the intelligent recognition ATM is actively utilized to carry out money judgment operation, and certain country of money is held by hand, and the denomination is 100000.

step 1", acquiring image information of real currency, wherein a part of sources of the acquired currency information are shown in table 2, and in order to protect the confidentiality of the sources of the currency, the sources of the currency are shown as examples, and the sources of the currency are not real, wherein x and y represent the quantity.

TABLE 2 Currency Source information Table

And 2 'constructing a currency information data set, namely storing the data in a database by utilizing the currency information acquired in the step 1'.

And 3', establishing a currency information relation model database, namely displaying the relation among currencies through mining, analyzing, constructing and drawing according to the currency information data set obtained in the step 2", and constructing a relation model among currencies.

And 4' acquiring image information of the money to be checked, namely, the user small B uses the intelligent recognition ATM to perform recognition operation on the money.

And step 5', extracting key mark information of the money to be inspected, namely carrying out mark detection on the key mark information according to the data information acquired in the step 4 ". The currency provided by the small B is known to be foreign currency according to the algorithm, the area of the small B is x, the currency unit is x, and the denomination is x. The circulation information of the numbered currency is not searched in the database through searching the information discovery of the database.

And 6, extracting the pattern and texture information of the money to be checked, namely easily judging the country to which the money belongs and the key pattern information of the money with the denomination issued in the year according to the issuing row, the issuing year and the denomination of the money obtained in the step 5. When the number information of the currency cannot be used to find the information of the issue and the delivery of the currency from the database in the step 5", fusion comparison analysis is required to be performed on the extracted key pattern information and the texture information and the same key information of the adjacent currency, so that the difference is found. By using the mode fusion method of grid division, the fusion time can be greatly shortened, once abnormality is found, the suspected currency can be judged, and deviation analysis is carried out according to the obtained integral binary histogram value after fusion and the integral binary histogram value of the original images of a plurality of adjacent currencies, wherein the deviation calculation formula is as follows.

When the maximum deviation value is larger than the prescribed value beta, the coin is considered to be a problem coin, and when the maximum deviation value is smaller than the beta, the coin is considered to be a doubtful coin, and further judgment is needed. The method can reduce the probability of misjudgment of the currency due to pollution marks and the like to a certain extent, and can adapt to the extremely fine color forming difference of the currency in the production process. Here, the system calculates the deviation value of 10.91 for the money held by the small B, and the deviation value does not meet the set requirement, so that the money can be judged as the problem money.

And 7' extracting the depth information of the currency to be checked, namely after a series of operations from the step 1' to the step 6 ', if the small B still does not trust the suspected currency to be false, further judging the authenticity of the currency according to the depth information in the currency information. According to the money discrimination rule, the texture information on the real money is not flat but has a certain degree of unevenness, and the unevenness is also perceived to be noticeable to the touch. The application adopts the depth camera to collect the depth information of the currency, namely, collect the concave-convex characteristic information. The depth image is different from the common visible light image, and is a gray image which cannot be resolved by naked eyes, and gray values on the image represent depth information. The overall depth information of the picture can be represented by calculating an average value, a maximum value, a minimum value, a deviation value and a variance value, and whether the texture depth information is consistent or approximate in overall measurement can be obtained by comparing the currency depth information adjacent to the currency. If the measurement deviation is large, two compared depth images are further fused to find out local inconsistent positions, so that the authenticity of the currency is judged. The fusion comparison is judged by measuring the information entropy in the image, and the calculation formula is as follows.

H(A)=-∑_aP_A(a)log₂P_A(a) (2)

When the information entropy is higher, namely the error loss of the fused image is smaller than alpha, the similarity between the fused image and the original image is extremely high, and the fused image can be judged to be a real coin. When the information entropy is lower, namely the error loss of the fused image is larger than or equal to alpha, the similarity between the fused image and the original image is extremely low, and the counterfeit money can be judged. By comparing the depth images, texture information with convexity provided by currency printing can be well used as a key means for currency identification, and major errors of identification results can be effectively avoided. Knowing H (a) = 39.8793% by calculation, the currency in the small B hand can be judged to be the problem currency.

Step 8", finish currency authentication, in step 1 through step 7, the system gives out an authentication result finally through a series of authentication means. For the system, the discrimination result is given in the form of probability P. And when P is smaller than the set value gamma and is larger than or equal to xi, the user is prompted to "the currency is possibly a problem currency, and the currency is flattened and re-detected". When P is smaller than xi, the currency is directly prompted to be a problem currency, and the problem currency is processed by a bank. In this way, psychological stress on the user can be reduced, so that the user is not frightened by the suddenly remembered alarm. The intelligent studying and judging system considers the currency held by the small B as the problem currency, feeds the information back to the user, and prompts the user to actively send the currency to the bank for processing.

And 9' alarming and early warning, namely comprehensively analyzing the true and false states and circulation states of the currencies in different regions according to the historical data generated in the steps 1 to 8 after the system is operated for a period of time.

Based on the same inventive concept, the embodiment of the present application also provides a currency authenticity identification device, which can be used to implement the method described in the above embodiment, as described in the following embodiment. Since the principle of solving the problem of the currency authenticity identifying device is similar to that of the currency authenticity identifying method, the implementation of the currency authenticity identifying device can be referred to the implementation of the software performance reference-based determination method, and the repetition is omitted. As used below, the term "unit" or "module" may be a combination of software and/or hardware that implements the intended function. While the system described in the following embodiments is preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.

In one embodiment, referring to fig. 6, in order to construct a knowledge graph of currency information and identify authenticity of currency according to the knowledge graph, the present application provides a currency authenticity identification device, which includes a knowledge graph construction unit 601 and an identification result generation unit 602.

A knowledge graph construction unit 601, configured to construct a currency information knowledge graph according to the collected real currency image;

The identification result generating unit 602 is configured to verify the basic information and the texture information of the money to be checked by using the money information knowledge graph, so as to obtain a money authenticity identification result.

In one embodiment, referring to fig. 7, the knowledge graph construction unit 601 includes a real attribute extraction module 701, a real relationship extraction module 702, and a knowledge graph construction module 703.

The real currency attribute extraction module 701 is configured to extract real currency attributes according to the real currency image, where the real currency attributes include currency, denomination, number, color grade, real plane texture feature and real stereoscopic texture feature;

a real relation extracting module 702, configured to generate a relation between real currencies according to the real currency attribute;

the knowledge graph construction module 703 is configured to generate the currency information knowledge graph according to the real currency, the real currency attributes, and the relationships among the real currencies.

In one embodiment, referring to fig. 8, the recognition result generating unit 602 includes a real currency selecting module 801 and a basic information verifying module 802.

The real currency selecting module 801 is configured to search real currencies corresponding to currencies and denominations in the currency information knowledge graph according to the currencies and denominations of the currencies to be tested, and obtain numbers and color grades of the real currencies corresponding to the currencies and denominations;

the basic information verification module 802 is configured to compare the serial number and the color grade of the real currency corresponding to the currency and the denomination with the serial number and the color grade of the currency to be verified, and obtain a basic information verification result of the currency to be verified.

In one embodiment, referring to fig. 9, the texture information includes plane texture information, and the recognition result generating unit 602 includes a to-be-determined plane feature generating module 901, a real plane feature generating module 902, and a plane texture verifying module 903.

The to-be-judged plane feature generation module 901 is used for fusing the to-be-tested plane texture features of the to-be-tested currency and the real plane texture features of the real currency corresponding to the currency and the denomination to obtain to-be-judged plane fusion features;

The real plane feature generation module 902 is configured to fuse real plane texture features of real currency corresponding to the currency and the denomination to obtain real plane fusion features;

the plane texture verification module 903 is configured to calculate a deviation between the plane fusion feature to be determined and the real plane fusion feature, and generate a plane texture verification result corresponding to the plane texture information.

In one embodiment, referring to fig. 10, the texture information includes stereo texture information, and the recognition result generating unit includes a to-be-determined stereo feature generating module 1001, a real stereo feature generating module 1002, and a stereo texture verifying module 1003.

The to-be-judged three-dimensional feature generation module 1001 is configured to fuse the to-be-tested three-dimensional texture feature of the to-be-tested currency and the real three-dimensional texture feature of the real currency corresponding to the currency and the denomination to obtain a to-be-judged three-dimensional fusion feature;

the real three-dimensional feature generation module 1002 is configured to fuse real three-dimensional texture features of real currency corresponding to the currency and the denomination to obtain real three-dimensional fusion features;

the stereo texture verification module 1003 is configured to calculate an information entropy between the stereo fusion feature to be determined and the real stereo fusion feature, and generate a stereo texture verification result corresponding to the stereo texture information.

In one embodiment, the currency authenticity identification device further comprises:

In order to construct a currency information knowledge graph and identify currency authenticity according to the knowledge graph from a hardware level, the application provides an embodiment of an electronic device for realizing all or part of contents in the currency authenticity identification method, wherein the electronic device specifically comprises the following contents:

The system comprises a Processor (Processor), a Memory (Communications Interface), a communication interface (Communications Interface) and a bus, wherein the Processor, the Memory and the communication interface are in communication with each other through the bus, the communication interface is used for realizing information transmission between the currency authenticity identification device and related equipment such as a core service system, a client terminal and a related database, and the logic controller can be a desk computer, a tablet computer, a mobile terminal and the like. In this embodiment, the logic controller may refer to the embodiment of the currency authenticity identification method and the embodiment of the currency authenticity identification device, and the contents thereof are incorporated herein and will not be repeated.

It is understood that the client terminal may include a smart phone, a tablet electronic device, a network set top box, a portable computer, a desktop computer, a Personal Digital Assistant (PDA), an in-vehicle device, a smart wearable device, etc. Wherein, intelligent wearing equipment can include intelligent glasses, intelligent wrist-watch, intelligent bracelet etc..

In practical applications, part of the method for identifying authenticity of currency may be performed on the electronic device side as described above, or all operations may be performed in the client device. Specifically, the selection may be made according to the processing capability of the client device, and restrictions on the use scenario of the client. The application is not limited in this regard. If all operations are performed in the client device, the client device may further include a processor.

The client device may have a communication module (i.e. a communication unit) and may be connected to a remote server in a communication manner, so as to implement data transmission with the server. The server may include a server on the side of the task scheduling center, and in other implementations may include a server on an intermediate platform, such as a server on a third party server platform having a communication link with the task scheduling center server. The server may include a single computer device, a server cluster formed by a plurality of servers, or a server structure of a distributed device.

Fig. 20 is a schematic block diagram of a system configuration of an electronic device 9600 according to an embodiment of the present application. As shown in fig. 20, the electronic device 9600 can include a central processor 9100 and a memory 9140, the memory 9140 being coupled to the central processor 9100. It is noted that this fig. 20 is exemplary, and that other types of structures may be used in addition to or in place of the structures to implement telecommunications functions or other functions.

In one embodiment, the currency authenticity identification method functionality may be integrated into the central processor 9100. The central processor 9100 may be configured to perform the following control:

In another embodiment, the currency authenticity identification device may be configured separately from the cpu 9100, for example, the data transmission device may be configured as a chip connected to the cpu 9100, and the function of the currency authenticity identification method may be implemented by control of the cpu.

As shown in fig. 20, the electronic device 9600 may further include a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is noted that the electronic device 9600 does not necessarily include all the components shown in fig. 20, and furthermore, the electronic device 9600 may include components not shown in fig. 20, and reference is made to the prior art.

As shown in fig. 20, the central processor 9100, sometimes referred to as a controller or operational control, may include a microprocessor or other processor device and/or logic device, which central processor 9100 receives inputs and controls the operation of the various components of the electronic device 9600.

The memory 9140 may be, for example, one or more of a buffer, a flash memory, a hard drive, a removable media, a volatile memory, a non-volatile memory, or other suitable device. The information about failure may be stored, and a program for executing the information may be stored. And the central processor 9100 can execute the program stored in the memory 9140 to realize information storage or processing, and the like.

The input unit 9120 provides input to the central processor 9100. The input unit 9120 is, for example, a key or a touch input device. The power supply 9170 is used to provide power to the electronic device 9600. The display 9160 is used for displaying display objects such as images and characters. The display may be, for example, but not limited to, an LCD display.

The memory 9140 may be a solid state memory such as Read Only Memory (ROM), random Access Memory (RAM), SIM card, etc. But also a memory which holds information even when powered down, can be selectively erased and provided with further data, an example of which is sometimes referred to as EPROM or the like. The memory 9140 may also be some other type of device. The memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application/function storage portion 9142, the application/function storage portion 9142 storing application programs and function programs or a flow for executing operations of the electronic device 9600 by the central processor 9100.

The memory 9140 may also include a data store 9143, the data store 9143 for storing data, such as contacts, digital data, pictures, sounds, and/or any other data used by an electronic device. The driver storage portion 9144 of the memory 9140 may include various drivers of the electronic device for communication functions and/or for performing other functions of the electronic device (e.g., messaging applications, address book applications, etc.).

The communication module 9110 is a transmitter/receiver 9110 that transmits and receives signals via an antenna 9111. The communication module (transmitter/receiver) 9110 is coupled to the central processor 9100 to provide an input signal and receive an output signal, which may be the same as in the case of a conventional mobile communication terminal.

Based on different communication technologies, a plurality of communication modules 9110, such as a cellular network module, a bluetooth module, and/or a wireless lan module, may be provided in the same electronic device. The communication module (transmitter/receiver) 9110 is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide audio output via the speaker 9131 and to receive audio input from the microphone 9132 to implement usual telecommunications functions. The audio processor 9130 can include any suitable buffers, decoders, amplifiers and so forth. In addition, the audio processor 9130 is also coupled to the central processor 9100 so that sound can be recorded locally through the microphone 9132 and sound stored locally can be played through the speaker 9131.

An embodiment of the present application also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements all the steps of the method for identifying whether a piece of execution subject is a server or a client, for example, the processor implements the steps of:

It will be apparent to those skilled in the art that embodiments of the present application may be provided as a method, apparatus, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (devices), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

While the principles and embodiments of the present application have been described in detail in the foregoing application of the principles and embodiments of the present application, the above examples are provided for the purpose of aiding in the understanding of the principles and concepts of the present application and may be varied in many ways by those of ordinary skill in the art in light of the teachings of the present application, and the above descriptions should not be construed as limiting the application.

Claims

1. A method for identifying the authenticity of currency, comprising:

Build a currency information knowledge graph based on the collected real currency images;

The currency information knowledge graph is used to verify the basic information and texture information of the currency to be tested, and obtain a currency authenticity identification result, wherein the texture information includes: plane texture information;

The method of using the currency information knowledge graph to verify the basic information and texture information of the currency to be verified includes:

If no information on the issuance and release of the currency to be verified is detected in the currency information knowledge graph, the texture features of the plane to be verified of the currency to be verified are fused with the real plane texture features of multiple adjacent real currencies in the currency information knowledge graph to obtain the fused features of the plane to be judged;

Fusing the real plane texture features of multiple real currencies adjacent to the currency information knowledge graph to obtain a real plane fusion feature; wherein the to-be-determined plane fusion feature and the real plane fusion feature are both metric values of a two-dimensional histogram;

The deviation between the plane fusion feature to be judged and the real plane fusion feature is calculated to generate a plane texture verification result corresponding to the plane texture information.

2. The currency authenticity identification method according to claim 1, wherein constructing a currency information knowledge graph based on the collected real currency images comprises:

Extracting real currency attributes based on the real currency image; the real currency attributes include currency type, denomination, serial number, fineness grade, real plane texture features, and real three-dimensional texture features;

generating a relationship between real currencies according to the real currency attributes;

The currency information knowledge graph is generated according to the real currency, the real currency attributes and the relationship between the real currencies.

3. The currency authenticity identification method according to claim 2, wherein the step of verifying basic information of the currency to be verified by using the currency information knowledge graph comprises:

According to the currency type and denomination of the currency to be verified, the real currency of the corresponding currency type and denomination in the currency information knowledge graph is retrieved to obtain the serial number and fineness grade of the real currency of the corresponding currency type and denomination;

The serial number and fineness of the real currency of the corresponding currency type and denomination are compared with the serial number and fineness of the currency to be verified to obtain the basic information verification result of the currency to be verified.

4. The currency authenticity identification method according to claim 1, wherein the texture information includes three-dimensional texture information; and the step of verifying the basic information and texture information of the currency to be verified by using the currency information knowledge graph comprises:

Fusing the 3D texture features of the currency to be verified with the real 3D texture features of the real currency of the corresponding currency type and denomination to obtain a 3D fusion feature to be judged;

Fusing the real 3D texture features of real currency of corresponding currency type and denomination to obtain real 3D fusion features;

The information entropy between the to-be-determined stereo fusion feature and the real stereo fusion feature is calculated to generate a stereo texture verification result corresponding to the stereo texture information.

5. The method for identifying currency authenticity according to claim 1, further comprising:

If the basic information verification result fails and/or the plane texture verification result fails, a high-risk warning process is performed.

6. The method for identifying currency authenticity according to claim 4, further comprising:

Performing early warning processing according to the basic information verification result, the plane texture verification result, and the three-dimensional texture verification result;

If the basic information verification result fails, the plane texture verification result and the three-dimensional texture verification result all fail, a high-risk warning process is performed;

If the basic information verification result passes, but the plane texture verification result and the three-dimensional texture verification result both fail, an intermediate warning process is performed;

If both the basic information verification result and the plane texture verification result pass, but the three-dimensional texture verification result fails, a low-risk warning process is performed.

7. A currency authenticity identification device, comprising:

A knowledge graph construction unit, used to construct a currency information knowledge graph based on the collected real currency images;

An identification result generating unit is used to verify the basic information and texture information of the currency to be verified by using the currency information knowledge graph to obtain a currency authenticity identification result, wherein the texture information includes: plane texture information;

The recognition result generating unit is specifically configured to:

If no information on the issuance and release of the currency to be verified is detected in the currency information knowledge, the texture features of the plane to be verified of the currency to be verified are fused with the real plane texture features of multiple adjacent real currencies in the currency information knowledge graph to obtain the fused features of the plane to be judged;

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the currency authenticity identification method according to any one of claims 1 to 6 when executing the program.

9. A computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of the currency authenticity identification method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program/instruction, characterized in that when the computer program/instruction is executed by a processor, the steps of the currency authenticity identification method according to any one of claims 1 to 6 are implemented.