CN114626860A - Dynamic identity identification method and device for online commodity payment - Google Patents

Dynamic identity identification method and device for online commodity payment Download PDF

Info

Publication number
CN114626860A
CN114626860A CN202210513978.2A CN202210513978A CN114626860A CN 114626860 A CN114626860 A CN 114626860A CN 202210513978 A CN202210513978 A CN 202210513978A CN 114626860 A CN114626860 A CN 114626860A
Authority
CN
China
Prior art keywords
password
authentication
image
dynamic
face
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202210513978.2A
Other languages
Chinese (zh)
Other versions
CN114626860B (en
Inventor
郑咏希
陶俊清
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Wuhan Heyue Digital Technology Co ltd
Original Assignee
Wuhan Heyue Digital Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Wuhan Heyue Digital Technology Co ltd filed Critical Wuhan Heyue Digital Technology Co ltd
Priority to CN202210513978.2A priority Critical patent/CN114626860B/en
Publication of CN114626860A publication Critical patent/CN114626860A/en
Application granted granted Critical
Publication of CN114626860B publication Critical patent/CN114626860B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q20/00—Payment architectures, schemes or protocols
    • G06Q20/38—Payment protocols; Details thereof
    • G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
    • G06Q20/401—Transaction verification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/25—Fusion techniques
    • G06F18/253—Fusion techniques of extracted features
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q20/00—Payment architectures, schemes or protocols
    • G06Q20/38—Payment protocols; Details thereof
    • G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
    • G06Q20/401—Transaction verification
    • G06Q20/4014—Identity check for transactions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q20/00—Payment architectures, schemes or protocols
    • G06Q20/38—Payment protocols; Details thereof
    • G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
    • G06Q20/401—Transaction verification
    • G06Q20/4014—Identity check for transactions
    • G06Q20/40145—Biometric identity checks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/40—Image enhancement or restoration using histogram techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/70—Denoising; Smoothing
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
    • H04L9/32—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials
    • H04L9/3226—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials using a predetermined code, e.g. password, passphrase or PIN
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Accounting & Taxation (AREA)
  • Data Mining & Analysis (AREA)
  • Computer Security & Cryptography (AREA)
  • Finance (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Image Analysis (AREA)
  • Collating Specific Patterns (AREA)

Abstract

The invention relates to the technical field of information security, and discloses a dynamic identity identification method and a dynamic identity identification device for online commodity payment, wherein the method comprises the following steps: the method comprises the steps of generating an authentication password based on a commodity payment request, sending the authentication password to an authentication server, receiving a dynamic encryption random password fed back by the authentication server, analyzing the dynamic encryption random password to obtain a dynamic random number, carrying out password authentication based on the dynamic random number and the authentication server to obtain a password authentication result, generating a face recognition interface based on the password authentication result, obtaining a face image to be recognized, carrying out denoising and histogram equalization processing on the face image to be recognized to obtain a standard recognition image, extracting local features in the standard recognition image by using an improved LBP algorithm, carrying out histogram feature fusion to obtain an original fusion feature, and carrying out identity recognition on the original fusion feature by using a deep belief network to obtain an identity recognition result. The invention can solve the problem of low safety and accuracy of identity recognition during online commodity payment.

Description

Dynamic identity identification method and device for online commodity payment
Technical Field
The invention relates to the technical field of information security, in particular to a dynamic identity identification method and device for online commodity payment, electronic equipment and a computer readable storage medium.
Background
With the development of computer networks, people increasingly choose to purchase commodities on line, and the most important and most critical step in online shopping is a commodity payment stage, wherein the commodity payment requires identity authentication of users.
Currently, two authentication methods are mainly used for online payment: 1. the basic authentication mode of inputting a user name/password has the biggest problem that the user name and the password are transmitted in a network in a plaintext mode and are easy to suffer from replay attack and dictionary attack, so that higher security requirements are difficult to meet; 2. the identity authentication is carried out by using a face recognition mode, however, the face recognition is carried out by using more mobile equipment ends during online commodity payment, and the face recognition accuracy is not high due to the fact that the face recognition is often interfered by various internal and external factors such as sampling, expression, illumination, shielding and the like.
Disclosure of Invention
The invention provides a dynamic identification method, a dynamic identification device, electronic equipment and a computer readable storage medium for online commodity payment, and mainly aims to solve the problem that the safety and the accuracy of identification are not high when online commodity payment is carried out.
In order to achieve the above object, the present invention provides a dynamic identity recognition method for online commodity payment, which comprises:
acquiring a commodity payment request, generating an authentication password based on the commodity payment request and sending the authentication password to an authentication server;
receiving a dynamic encryption random password fed back by the authentication server based on the authentication password;
analyzing the dynamic encryption random password to obtain a dynamic random number, and performing password authentication based on the dynamic random number and the authentication server to obtain a password authentication result;
generating a face recognition interface based on the password authentication result, and acquiring a face image to be recognized from the face recognition interface;
denoising the face image to be recognized by using a mean value filtering formula to obtain an original recognition image, wherein the mean value filtering formula is as follows:
Figure 9030DEST_PATH_IMAGE001
wherein,
Figure 395012DEST_PATH_IMAGE002
for presetting neighborhoods
Figure 909169DEST_PATH_IMAGE003
Internal removal
Figure 773220DEST_PATH_IMAGE004
The total number of remaining pixel points other than the point,
Figure 305702DEST_PATH_IMAGE005
in order to remove the noise of the pixel point,
Figure 331427DEST_PATH_IMAGE006
before de-noisingThe pixel point of (2);
performing histogram equalization processing on the original recognition image to obtain a standard recognition image, extracting local features in the standard recognition image by using an improved LBP algorithm, and performing histogram feature fusion on the local features to obtain original fusion features;
and carrying out identity recognition on the original fusion characteristics by utilizing a pre-trained deep belief network to obtain an identity recognition result.
Optionally, the generating an authentication password based on the commodity payment request and sending the authentication password to an authentication server includes:
analyzing and extracting the unique identification code IMEI and the commodity payment information in the commodity payment request;
and encrypting the unique identification code IMEI and the commodity payment information by using a preset server public key to obtain the authentication password.
Optionally, the analyzing the dynamic encrypted random password to obtain a dynamic random number, and performing password authentication based on the dynamic random number and the authentication server to obtain a password authentication result, includes:
decrypting the dynamic encrypted random password by using a preset user private key to obtain the dynamic random number and a random number hash value;
carrying out hash processing on the dynamic random number to obtain a verification hash value;
comparing whether the verification hash value and the random number hash value are equal or not;
if the verification hash value is not equal to the random number hash value, the password authentication result is authentication failure;
and if the verification hash value is not equal to the random number hash value, performing hash processing on a preset communication secret and the dynamic random number, sending a hash processing result to the authentication server and receiving a password authentication result fed back by the authentication server, wherein the password authentication result comprises authentication success or authentication failure.
Optionally, the generating a face recognition interface based on the password authentication result, and acquiring a face image to be recognized from the face recognition interface includes:
when the password authentication result is that the authentication is successful, generating the face recognition interface;
and acquiring a face video stream by using the face recognition interface, reading face images in the face video stream frame by frame, and performing face correction to obtain the face image to be recognized.
Optionally, the performing histogram equalization processing on the original recognition image to obtain a standard recognition image includes:
calculating a gray level histogram of the original identification image;
and carrying out gray mean value conversion on the gray level histogram by using a preset conversion function to obtain the standard identification image.
Optionally, the performing gray scale mean conversion on the gray scale histogram by using a preset transformation function includes:
performing gray level mean value conversion on the gray level histogram by using the following gray level conversion formula:
Figure 67301DEST_PATH_IMAGE007
wherein,
Figure 984311DEST_PATH_IMAGE008
the gray levels of the image are identified for the standard,
Figure 856452DEST_PATH_IMAGE009
a formula for converting a gray scale is expressed,
Figure 53078DEST_PATH_IMAGE010
the formula of the rounding is shown as,
Figure 525516DEST_PATH_IMAGE011
represents the gray level histogram, an
Figure 465791DEST_PATH_IMAGE012
，
Figure 458017DEST_PATH_IMAGE013
Representing a range of gray levels in the original recognition image.
Optionally, the extracting, by using an improved LBP algorithm, a local feature in the standard recognition image, and performing histogram feature fusion on the local feature to obtain an original fusion feature includes:
dividing the standard identification image into a plurality of image blocks by using a preset pixel acquisition area;
carrying out inner layer and outer layer sampling processing on each image block, calculating LBP values of pixel points in the outer layer and the inner layer, and carrying out weighted average on the LBP values in the outer layer and the inner layer to obtain local characteristics of each image block;
and connecting the local features of each image block in series to obtain the original fusion features.
Optionally, before the identifying the original fusion features by using the pre-trained deep belief network, the method further includes:
acquiring a face training image set, extracting local features of each image in the face training image set by using the improved LBP algorithm, and performing histogram feature fusion to obtain original training features of each image;
performing feature fusion on the original training features and corresponding images in the face training image set to obtain a standard training feature set of all images;
acquiring an original deep belief network, training RBM layers in the original deep belief network layer by utilizing the standard training feature set, and solving an energy value of each RBM layer;
and reversely adjusting parameters of RBM layers in the original deep belief network by using BP (back propagation) based on the energy values until the energy value of each RBM layer meets a preset energy threshold, and stopping training to obtain the trained deep belief network.
Optionally, the energy value of each RBM layer is calculated using the following energy formula:
Figure 356703DEST_PATH_IMAGE014
wherein,
Figure 319367DEST_PATH_IMAGE015
for the said amount of energy to be taken into account,
Figure 797753DEST_PATH_IMAGE016
representing the visible nodes in the RBM layer,
Figure 910066DEST_PATH_IMAGE017
representing an implicit node in the RBM layer,
Figure 432183DEST_PATH_IMAGE018
indicates the number of the visible nodes,
Figure 364367DEST_PATH_IMAGE019
the number of the implied nodes is indicated,
Figure 177602DEST_PATH_IMAGE020
is shown as
Figure 393689DEST_PATH_IMAGE021
The number of the visible nodes is one,
Figure 634177DEST_PATH_IMAGE022
is shown as
Figure 53657DEST_PATH_IMAGE023
An implicit node is defined as a node that is,
Figure 405004DEST_PATH_IMAGE024
is shown as
Figure 475597DEST_PATH_IMAGE021
A visual node and
Figure 152566DEST_PATH_IMAGE023
the weight between the implicit nodes is such that,
Figure 59342DEST_PATH_IMAGE025
a preset threshold value for the visible node,
Figure 948801DEST_PATH_IMAGE026
a preset threshold for the hidden node.
In order to solve the above problem, the present invention further provides a dynamic identification device for online commodity payment, the device comprising:
the dynamic password acquisition module is used for acquiring a commodity payment request, generating an authentication password based on the commodity payment request, sending the authentication password to an authentication server, and receiving a dynamic encryption random password fed back by the authentication server based on the authentication password;
the password authentication module is used for analyzing the dynamic encryption random password to obtain a dynamic random number, and performing password authentication with the authentication server based on the dynamic random number to obtain a password authentication result;
the face image acquisition module is used for generating a face recognition interface based on the password authentication result and acquiring a face image to be recognized from the face recognition interface;
the local feature fusion module is used for carrying out denoising processing and histogram equalization processing on the face image to be recognized to obtain a standard recognition image, extracting local features in the standard recognition image by utilizing an improved LBP algorithm, and carrying out histogram feature fusion on the local features to obtain original fusion features;
and the identity recognition module is used for carrying out identity recognition on the original fusion characteristics by utilizing a pre-trained deep belief network to obtain an identity recognition result.
In order to solve the above problem, the present invention also provides an electronic device, including:
a memory storing at least one instruction; and
and the processor executes the instructions stored in the memory to realize the dynamic identification method for the online commodity payment.
In order to solve the above problem, the present invention further provides a computer-readable storage medium, which stores at least one instruction, where the at least one instruction is executed by a processor in an electronic device to implement the above dynamic identification method for online commodity payment.
Compared with the background art: the basic authentication mode of inputting a user name/password has the biggest problem that the user name and the password are transmitted in a clear text mode in a network and are easy to suffer from replay attack and dictionary attack, so that higher security requirements are difficult to meet. In order to improve the security of identity recognition during commodity payment, the embodiment of the invention generates an authentication password based on a commodity payment request and sends the authentication password to an authentication server, receives a dynamic encryption random password fed back by the authentication server based on the authentication password, analyzes the dynamic encryption random password to obtain a dynamic random number, performs dynamic password authentication based on the dynamic random number and the authentication server to obtain a password authentication result, and improves the security of identity authentication, secondly, a face recognition interface is generated based on the password authentication result, because the improved LBP algorithm focuses more on the local features in the standard recognition image and performs histogram feature fusion on the local features, the accuracy rate of face recognition can be improved, meanwhile, the identity is verified by combining the dynamic password with the face recognition, so that the accuracy and the safety of the identity recognition are further improved. Therefore, the dynamic identification method, the device, the electronic equipment and the computer readable storage medium for online commodity payment provided by the invention can solve the problem that the safety and the accuracy of identification are not high when online commodity payment is carried out.
Drawings
Fig. 1 is a schematic flow chart of a dynamic identity recognition method for online commodity payment according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of one step of the embodiment of FIG. 1;
FIG. 3 is a schematic flow chart of another step of the embodiment of FIG. 1;
FIG. 4 is a functional block diagram of an apparatus for dynamically identifying an identity of an online merchandise payment according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device for implementing the dynamic identification method for online commodity payment according to an embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The embodiment of the application provides an identity dynamic identification method for online commodity payment. The executing body of the dynamic identification method for online commodity payment includes, but is not limited to, at least one of electronic devices such as a server and a terminal, which can be configured to execute the method provided by the embodiment of the present application. In other words, the dynamic identification method for online commodity payment may be performed by software or hardware installed in a terminal device or a server device, and the software may be a block chain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like.
Example 1:
fig. 1 is a schematic flow chart of a dynamic identity identification method for online commodity payment according to an embodiment of the present invention. In this embodiment, the method for dynamically identifying the identity of the online commodity payment includes:
s1, acquiring the commodity payment request, generating an authentication password based on the commodity payment request and sending the authentication password to the authentication server.
In the embodiment of the present invention, the commodity payment request may be an online commodity payment request generated by a mobile device such as a mobile phone and a tablet, and includes: the IMEI identification code of the mobile equipment, the pass secret phrase SPP, user information, commodity order information and the like. The IMEI and the SPP are stored in the authentication server in advance, and the mobile equipment stores the SPP. Illustratively, user a makes a request for payment of goods sent by an online purchase on a certain e-commerce platform. The authentication server can be a payment platform authentication server, and since the payment security is the most preferred guarantee for online shopping, authentication with the authentication server is required.
In detail, the generating an authentication password based on the commodity payment request and sending the authentication password to an authentication server includes:
analyzing and extracting the unique identification code IMEI and the commodity payment information in the commodity payment request;
and encrypting the unique identification code IMEI and the commodity payment information by using a preset server public key to obtain the authentication password.
It should be explained that, the mobile device side and the authentication server side of the present invention perform key exchange in advance, for example, public keys are exchanged respectively when the mobile device side and the authentication server side register in two directions, that is, the mobile device side sends the user public key to the authentication server side, and the authentication server side sends the server public key to the mobile device side.
For example, the unique identification code IMEI and the commodity order number G in the commodity payment request are extracted, and encrypted by using the server public key KSR, and the generated password is:
Figure 155791DEST_PATH_IMAGE027
wherein
Figure 990280DEST_PATH_IMAGE028
is shown as
Figure 384352DEST_PATH_IMAGE021
The number of authentication passwords is such that,
Figure 343081DEST_PATH_IMAGE029
is the server public key.
And S2, receiving the dynamic encryption random password fed back by the authentication server based on the authentication password.
In the embodiment of the invention, the authentication server uses the server private key KSS to carry out decryption operation
Figure 873419DEST_PATH_IMAGE030
Obtaining IMEI and commodity order number G, inquiring database to compare IMEI, if IMEI does not exist, returning unauthenticated information, if IMEI exists, generating a random number based on the commodity order number
Figure 626611DEST_PATH_IMAGE031
To IMEI and
Figure 22826DEST_PATH_IMAGE031
performing hash processing
Figure 519667DEST_PATH_IMAGE032
And generating dynamic encrypted random password by using public key KCR of mobile equipment terminal
Figure 170091DEST_PATH_IMAGE033
。
Understandably, the mobile device end receives the dynamic encrypted random password
Figure 94185DEST_PATH_IMAGE033
。
S3, analyzing the dynamic encrypted random password to obtain a dynamic random number, and carrying out password authentication based on the dynamic random number and the authentication server to obtain a password authentication result.
In detail, the analyzing the dynamic encrypted random password to obtain a dynamic random number, and performing password authentication based on the dynamic random number and the authentication server to obtain a password authentication result, includes:
decrypting the dynamic encrypted random password by using a preset user private key to obtain the dynamic random number and a random number hash value;
carrying out hash processing on the dynamic random number to obtain a verification hash value;
comparing whether the verification hash value and the random number hash value are equal or not;
if the verification hash value is not equal to the random number hash value, the password authentication result is authentication failure;
and if the verification hash value is not equal to the random number hash value, performing hash processing on a preset communication secret and the dynamic random number, sending a hash processing result to the authentication server and receiving a password authentication result fed back by the authentication server, wherein the password authentication result comprises authentication success or authentication failure.
In an alternative embodiment of the invention, the mobile device receives the dynamic encrypted random password
Figure 462849DEST_PATH_IMAGE033
Then, firstly, the user private key KCS is used for decryption to obtain the dynamic random number
Figure 12648DEST_PATH_IMAGE031
And
Figure 783158DEST_PATH_IMAGE032
calculating
Figure 612574DEST_PATH_IMAGE034
Comparison of
Figure 468534DEST_PATH_IMAGE032
And
Figure 572757DEST_PATH_IMAGE034
if not, the password authentication result is authentication failure, and the authentication is ended; if the two are equal, the identity of the server is verified, and the identity of the server is calculated
Figure 181461DEST_PATH_IMAGE035
Sending the response number to the authentication server, and temporarily storing the response number by the authentication server
Figure 447358DEST_PATH_IMAGE035
Then take out SPP in user database to calculate
Figure 790614DEST_PATH_IMAGE036
And received
Figure 432948DEST_PATH_IMAGE035
And comparing, if the mobile user identity authentication is the same as the authentication result, successfully authenticating the mobile user identity authentication, and returning authentication success information, otherwise, returning authentication failure information.
In another optional embodiment of the present invention, after performing password authentication based on the dynamic random number and the authentication server to obtain a password authentication result, the method further includes:
counting the verification failure times of the password authentication result as authentication failure;
if the verification failure times are smaller than a preset first failure threshold value, regenerating an authentication password and sending the authentication password to an authentication server side;
if the verification failure times are larger than or equal to the first failure threshold value but smaller than a preset second failure threshold value, limiting the sending time of the authentication password;
and if the verification failure times are larger than or equal to the second failure threshold value, forbidding to send an authentication password to the authentication server.
In an optional embodiment of the present invention, if the number of authentication failures is greater than or equal to the first failure threshold and less than the preset second failure threshold, the user may enter a delay state, in which any authentication password is no longer functional, until the delay state is completed, the user may input the password again for verification, and if the number of authentication failures is greater than or equal to the second failure threshold, the user is locked, the authentication server no longer receives any password of the user, and the user is notified to handle the unlocking service by a short message or an email.
And S4, generating a face recognition interface based on the password authentication result, and acquiring a face image to be recognized from the face recognition interface.
In the embodiment of the invention, the face recognition interface is used for acquiring the face image of the user and performing the second authentication.
In detail, referring to fig. 2, the generating a face recognition interface based on the password authentication result and acquiring a face image to be recognized from the face recognition interface includes:
s40, when the password authentication result is that the authentication is successful, generating the face recognition interface;
s41, collecting a face video stream by using the face recognition interface, reading the face image in the face video stream frame by frame and carrying out face correction to obtain the face image to be recognized.
In an optional embodiment of the invention, coordinates of center positions of left and right eyes in the face image can be respectively selected and connected, an included angle between the connecting line of the center positions of the two eyes and a horizontal coordinate axis x is an angle a to be corrected, and the face image to be recognized is obtained by correcting the face by taking the coordinate position C of a center pixel point of the face as the center of a circle and taking a as a rotation angle.
S5, denoising and histogram equalization are carried out on the face image to be recognized to obtain a standard recognition image, local features in the standard recognition image are extracted by utilizing an improved LBP algorithm, and histogram feature fusion is carried out on the local features to obtain original fusion features.
In the embodiment of the present invention, the histogram equalization processing is a method for correcting the gray distribution of an image. The method makes the gray histogram of the transformed image uniformly distributed between 0 and 255 by carrying out nonlinear change on the gray of the image. The operation not only can widen the dynamic range of the gray level change of the image, but also can enhance the definition of the image and highlight the detail information in the image.
In detail, the denoising and histogram equalization processing are performed on the face image to be recognized to obtain a standard recognition image, and the method includes:
denoising the face image to be recognized by using a mean value filtering formula to obtain an original recognition image;
and calculating a gray level histogram of the original identification image, and performing gray level mean value conversion on the gray level histogram by using a preset transformation function to obtain the standard identification image.
In an optional embodiment of the present invention, a neighborhood S is selected for a pixel (x, y) in an image f (m, n), and a gray average is calculated for all pixels in the neighborhood S and is used as a gray value of the pixel (x, y).
In an optional embodiment of the present invention, the following mean filtering formula is used to perform denoising processing:
Figure 178050DEST_PATH_IMAGE001
wherein,
Figure 878764DEST_PATH_IMAGE037
for presetting neighborhood in the face image to be recognized
Figure 443737DEST_PATH_IMAGE038
Internal removal
Figure 624183DEST_PATH_IMAGE039
The total number of remaining pixel points other than the point,
Figure 223792DEST_PATH_IMAGE040
in order to remove the noise of the pixel point,
Figure 80758DEST_PATH_IMAGE041
the pixel points before denoising.
In an optional embodiment of the present invention, the performing gray-level mean conversion on the gray-level histogram by using a preset transformation function includes:
performing gray level mean value conversion on the gray level histogram by using the following gray level conversion formula:
Figure 398607DEST_PATH_IMAGE007
wherein,
Figure 117164DEST_PATH_IMAGE042
the gray levels of the image are identified for the standard,
Figure 758230DEST_PATH_IMAGE043
a formula for converting a gray scale is expressed,
Figure 536830DEST_PATH_IMAGE044
the formula of the rounding is expressed,
Figure 76396DEST_PATH_IMAGE045
represents the gray level histogram, an
Figure 598644DEST_PATH_IMAGE046
，
Figure 156533DEST_PATH_IMAGE047
Representing a range of gray levels in the original recognition image.
In detail, referring to fig. 3, the extracting, by using the improved LBP algorithm, the local features in the standard recognition image, and performing histogram feature fusion on the local features to obtain original fusion features includes:
s50, dividing the standard identification image into a plurality of image blocks by using a preset pixel acquisition area;
s51, performing inner layer and outer layer sampling processing on each image block, calculating LBP values of pixel points in the outer layer and the inner layer, and performing weighted average on the LBP values in the outer layer and the inner layer to obtain local characteristics of each image block;
and S52, the local features of each image block are connected in series to obtain the original fusion features.
In the embodiment of the invention, LBP is an algorithm for describing local texture, and the definition of extracting image features by the traditional LBP algorithm is as follows: selecting any point of an image as a central point, wherein an acquisition area is 3 multiplied by 3, taking a gray value of a central pixel point of the acquisition area as a threshold, comparing 8 neighborhood gray values with the central gray value, if the threshold is smaller than the neighborhood gray value, marking as 1, otherwise, marking as 0, and then serially connecting binary numbers of the 8 points in a clockwise direction, thereby forming binary coding; finally, a decimal number is obtained through weighted summation, and the value obtained through the calculation is the LBP value of the center point.
In order to collect more useful information and improve the utilization rate of texture information, the improved LBP algorithm is adopted, namely a 5 multiplied by 5 pixel acquisition area is used, meanwhile, pixels (similar to 'well' words) in a second row, a fourth row, a second column and a fourth column in the pixel acquisition area are selected to carry out LBP algorithm coding, wherein 8 pixel points near a central area are used as an inner layer, the other 8 pixel points are used as an outer layer, and the LBP values of the inner layer and the outer layer are weighted and averaged to obtain a new LBP value which is the most local characteristic.
Further, the improved LBP algorithm is used for extracting the LBP value in the standard identification image as the local feature, more texture information can be extracted (for example, local information such as a bright point and an edge in a face image can be reflected in a highlight mode), histogram feature fusion is carried out on the local features of all image blocks, and the utilization rate of useful information is improved.
And S6, carrying out identity recognition on the original fusion features by utilizing a pre-trained deep belief network to obtain an identity recognition result.
In the embodiment of the invention, the deep belief network comprises a plurality of limited Boltzmann machines (namely RBM layers) which are stacked and superposed and a layer of back propagation network (BP). The RBM layer is composed of a visual layer (V) and an implicit layer (H), and is a bipartite graph structure, nodes in one layer are not connected with each other, and nodes between different layers are connected with each other.
In an optional embodiment of the present invention, before the performing the identity recognition on the original fusion feature by using the pre-trained deep belief network, the method further includes:
acquiring a face training image set, extracting local features of each image in the face training image set by using the improved LBP algorithm, and performing histogram feature fusion to obtain original training features of each image;
performing feature fusion on the original training features and corresponding images in the face training image set to obtain a standard training feature set of all images;
acquiring an original deep belief network, training RBM layers in the original deep belief network layer by utilizing the standard training feature set, and solving an energy value of each RBM layer;
and based on the energy value, reversely adjusting parameters of RBM layers in the original deep belief network by using BP (back propagation) until the energy value of each RBM layer meets a preset energy threshold, and stopping training to obtain the trained deep belief network.
In an optional embodiment of the present invention, the original training features and the corresponding images in the face training image set may be feature fused by a convolutional layer. The method for extracting the local features in the face training image set is the same as that of S5, and is not described herein again. The face training image set can be a face image set uploaded by a mobile equipment end user in advance. The method comprises the steps of training the RBMs of each layer by adopting an unsupervised training mode from the bottom to the top gradually, specifically, inputting a standard training feature set into a visual layer of the RBMs of the first layer, taking an implicit layer of the RBMs of the first layer as a visual layer of the RBMs of the second layer after full training, training the whole DBN network layer by layer in a progressive mode, and performing supervised fine tuning on the whole DBN network by utilizing the BP network from the top to the bottom gradually in a fine tuning stage.
In an optional embodiment of the present invention, the energy value of each RBM layer is calculated by using the following energy formula:
Figure 371614DEST_PATH_IMAGE014
wherein,
Figure 132896DEST_PATH_IMAGE048
for the said amount of energy to be taken into account,
Figure 458836DEST_PATH_IMAGE049
representing the visible nodes in the RBM layer,
Figure 887543DEST_PATH_IMAGE050
representing an implicit node in the RBM layer,
Figure 260143DEST_PATH_IMAGE051
indicates the number of the visible nodes,
Figure 977563DEST_PATH_IMAGE052
the number of the implied nodes is indicated,
Figure 107193DEST_PATH_IMAGE053
is shown as
Figure 108516DEST_PATH_IMAGE054
The number of the visible nodes is one,
Figure 665399DEST_PATH_IMAGE055
is shown as
Figure 401274DEST_PATH_IMAGE056
An implicit node is defined as a node that,
Figure 334595DEST_PATH_IMAGE057
is shown as
Figure 456004DEST_PATH_IMAGE054
A visual node and
Figure 183788DEST_PATH_IMAGE056
the weight between the implicit nodes is such that,
Figure 406959DEST_PATH_IMAGE058
a preset threshold value for the visible node,
Figure 612813DEST_PATH_IMAGE059
a preset threshold value for the hidden node.
In detail, the performing identity recognition on the original fusion features by using a pre-trained deep belief network to obtain an identity recognition result, including:
performing feature fusion on the original fusion features and the face image to be recognized to obtain standard fusion features;
and outputting the identity recognition result of the standard fusion characteristic by using the pre-trained deep belief network.
In the embodiment of the invention, the deep belief network is trained through the image uploaded by the user in advance, and the accuracy of face recognition can be improved under the interference of various internal and external factors such as sampling, expression, illumination, shielding and the like due to the fact that local features are concerned more during training.
Compared with the background art: the basic authentication mode of inputting a user name/password has the biggest problem that the user name and the password are transmitted in a clear text mode in a network and are easy to suffer from replay attack and dictionary attack, so that higher security requirements are difficult to meet. In order to improve the security of identity recognition during commodity payment, the embodiment of the invention generates an authentication password based on a commodity payment request and sends the authentication password to an authentication server, receives a dynamic encryption random password fed back by the authentication server based on the authentication password, analyzes the dynamic encryption random password to obtain a dynamic random number, performs dynamic password authentication based on the dynamic random number and the authentication server to obtain a password authentication result, and improves the security of identity authentication, secondly, a face recognition interface is generated based on the password authentication result, because the improved LBP algorithm pays more attention to the local features in the standard recognition image and performs histogram feature fusion on the local features, the accuracy rate of face recognition can be improved, meanwhile, the identity is verified by combining the dynamic password with the face recognition, so that the accuracy and the safety of the identity recognition are further improved. Therefore, the dynamic identification method for the online commodity payment provided by the invention can solve the problem that the safety and the accuracy of identification are not high when the online commodity payment is carried out.
Example 2:
fig. 4 is a functional block diagram of a dynamic identification apparatus for online commodity payment according to an embodiment of the present invention, which can implement the monitoring method in embodiment 1.
The dynamic identification device 100 for online commodity payment can be installed in an electronic device. According to the realized functions, the dynamic identity recognition device 100 for online commodity payment may include a dynamic password obtaining module 101, a password authentication module 102, a face image obtaining module 103, a local feature fusion module 104, and an identity recognition module 105. The module of the present invention, which may also be referred to as a unit, refers to a series of computer program segments that can be executed by a processor of an electronic device and that can perform a fixed function, and that are stored in a memory of the electronic device.
The dynamic password obtaining module 101 is configured to obtain a commodity payment request, generate an authentication password based on the commodity payment request, send the authentication password to an authentication server, and receive a dynamic encrypted random password fed back by the authentication server based on the authentication password;
the password authentication module 102 is configured to analyze the dynamic encrypted random password to obtain a dynamic random number, and perform password authentication with the authentication server based on the dynamic random number to obtain a password authentication result;
the face image obtaining module 103 is configured to generate a face recognition interface based on the password authentication result, and obtain a face image to be recognized from the face recognition interface;
the local feature fusion module 104 is configured to perform denoising and histogram equalization on the face image to be recognized to obtain a standard recognition image, extract local features in the standard recognition image by using an improved LBP algorithm, and perform histogram feature fusion on the local features to obtain original fusion features;
the identity recognition module 105 is configured to perform identity recognition on the original fusion feature by using a pre-trained deep belief network to obtain an identity recognition result.
In detail, when the modules in the dynamic identification apparatus 100 for online commodity payment according to the embodiment of the present invention are used, the same technical means as the above dynamic identification method for online commodity payment described in fig. 1 is adopted, and the same technical effects can be produced, which is not described herein again.
Example 3:
fig. 5 is a schematic structural diagram of an electronic device for implementing the dynamic identity identification method for online commodity payment according to an embodiment of the present invention.
The electronic device 1 may comprise a processor 10, a memory 11 and a bus, and may further comprise a computer program stored in the memory 11 and operable on the processor 10, such as a dynamic identification method program 12 for online payment of goods.
The memory 11 includes at least one type of readable storage medium, which includes flash memory, removable hard disk, multimedia card, card-type memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device 1, such as a removable hard disk of the electronic device 1. The memory 11 may also be an external storage device of the electronic device 1 in other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the electronic device 1. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device 1. The memory 11 may be used not only to store application software installed in the electronic device 1 and various types of data, such as codes of the dynamic identification method program 12 for online payment of goods, but also to temporarily store data that has been output or is to be output.
The processor 10 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same or different functions, including one or more Central Processing Units (CPUs), microprocessors, digital Processing chips, graphics processors, and combinations of various control chips. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects various components of the whole electronic device by using various interfaces and lines, and executes various functions and processes data of the electronic device 1 by running or executing programs or modules (for example, a dynamic identification method program for online commodity payment, etc.) stored in the memory 11 and calling data stored in the memory 11.
The bus may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is arranged to enable connection communication between the memory 11 and at least one processor 10 or the like.
Fig. 5 only shows an electronic device with components, and it will be understood by a person skilled in the art that the structure shown in fig. 5 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than shown, or a combination of certain components, or a different arrangement of components.
For example, although not shown, the electronic device 1 may further include a power supply (such as a battery) for supplying power to each component, and preferably, the power supply may be logically connected to the at least one processor 10 through a power management device, so as to implement functions of charge management, discharge management, power consumption management, and the like through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The electronic device 1 may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.
Further, the electronic device 1 may further include a network interface, and optionally, the network interface may include a wired interface and/or a wireless interface (such as a WI-FI interface, a bluetooth interface, etc.), which are generally used for establishing a communication connection between the electronic device 1 and other electronic devices.
Optionally, the electronic device 1 may further comprise a user interface, which may be a Display (Display), an input unit (such as a Keyboard), and optionally a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable for displaying information processed in the electronic device 1 and for displaying a visualized user interface, among other things.
It is to be understood that the described embodiments are for purposes of illustration only and that the scope of the appended claims is not limited to such structures.
The dynamic identification method for online payment of goods program 12 stored in the memory 11 of the electronic device 1 is a combination of instructions, which when executed in the processor 10, can realize:
acquiring a commodity payment request, generating an authentication password based on the commodity payment request and sending the authentication password to an authentication server;
receiving a dynamic encryption random password fed back by the authentication server based on the authentication password;
analyzing the dynamic encryption random password to obtain a dynamic random number, and performing password authentication based on the dynamic random number and the authentication server to obtain a password authentication result;
generating a face recognition interface based on the password authentication result, and acquiring a face image to be recognized from the face recognition interface;
carrying out denoising processing and histogram equalization processing on the face image to be recognized to obtain a standard recognition image, extracting local features in the standard recognition image by using an improved LBP algorithm, and carrying out histogram feature fusion on the local features to obtain original fusion features;
and carrying out identity recognition on the original fusion characteristics by utilizing a pre-trained deep belief network to obtain an identity recognition result.
Specifically, the specific implementation method of the processor 10 for the instruction may refer to the description of the relevant steps in the embodiments corresponding to fig. 1 to fig. 5, which is not repeated herein.
Further, the integrated modules/units of the electronic device 1, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. The computer readable storage medium may be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying said computer program code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM).
The present invention also provides a computer-readable storage medium, storing a computer program which, when executed by a processor of an electronic device, may implement:
acquiring a commodity payment request, generating an authentication password based on the commodity payment request and sending the authentication password to an authentication server;
receiving a dynamic encryption random password fed back by the authentication server based on the authentication password;
analyzing the dynamic encryption random password to obtain a dynamic random number, and performing password authentication based on the dynamic random number and the authentication server to obtain a password authentication result;
generating a face recognition interface based on the password authentication result, and acquiring a face image to be recognized from the face recognition interface;
carrying out denoising processing and histogram equalization processing on the face image to be recognized to obtain a standard recognition image, extracting local features in the standard recognition image by using an improved LBP algorithm, and carrying out histogram feature fusion on the local features to obtain original fusion features;
and carrying out identity recognition on the original fusion characteristics by utilizing a pre-trained deep belief network to obtain an identity recognition result.
In the several embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof.
The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims (10)

1. A dynamic identification method for online merchandise payment, the method comprising:
acquiring a commodity payment request, generating an authentication password based on the commodity payment request and sending the authentication password to an authentication server;
receiving a dynamic encryption random password fed back by the authentication server based on the authentication password;
analyzing the dynamic encryption random password to obtain a dynamic random number, and performing password authentication based on the dynamic random number and the authentication server to obtain a password authentication result;
generating a face recognition interface based on the password authentication result, and acquiring a face image to be recognized from the face recognition interface;
denoising the face image to be recognized by using a mean value filtering formula to obtain an original recognition image, wherein the mean value filtering formula is as follows:
Figure DEST_PATH_IMAGE001
wherein,
Figure DEST_PATH_IMAGE002
for presetting neighborhood in the face image to be recognized
Figure DEST_PATH_IMAGE003
Internal removal
Figure DEST_PATH_IMAGE004
The total number of remaining pixel points other than the point,
Figure DEST_PATH_IMAGE005
in order to remove the noise of the pixel point,
Figure DEST_PATH_IMAGE006
the pixel points before denoising are obtained;
performing histogram equalization processing on the original identification image to obtain a standard identification image, extracting local features in the standard identification image by using an improved LBP algorithm, and performing histogram feature fusion on the local features to obtain original fusion features;
and carrying out identity recognition on the original fusion characteristics by utilizing a pre-trained deep belief network to obtain an identity recognition result.
2. The dynamic identification method for online commodity payment according to claim 1, wherein the generating an authentication password based on the commodity payment request and sending the authentication password to an authentication server comprises:
analyzing and extracting the unique identification code IMEI and the commodity payment information in the commodity payment request;
and encrypting the unique identification code IMEI and the commodity payment information by using a preset server public key to obtain the authentication password.
3. The dynamic identity recognition method for online commodity payment according to claim 1, wherein the analyzing the dynamic encrypted random password to obtain a dynamic random number, and performing password authentication based on the dynamic random number and the authentication server to obtain a password authentication result, comprises:
decrypting the dynamic encrypted random password by using a preset user private key to obtain the dynamic random number and a random number hash value;
carrying out hash processing on the dynamic random number to obtain a verification hash value;
comparing whether the verification hash value and the random number hash value are equal or not;
if the verification hash value is not equal to the random number hash value, the password authentication result is authentication failure;
and if the verification hash value is not equal to the random number hash value, performing hash processing on a preset communication secret and the dynamic random number, sending a hash processing result to the authentication server and receiving a password authentication result fed back by the authentication server, wherein the password authentication result comprises authentication success or authentication failure.
4. The dynamic identity recognition method for online commodity payment according to claim 3, wherein the generating a face recognition interface based on the password authentication result and obtaining the face image to be recognized from the face recognition interface comprises:
when the password authentication result is that the authentication is successful, generating the face recognition interface;
and acquiring a face video stream by using the face recognition interface, reading face images in the face video stream frame by frame and carrying out face correction to obtain the face image to be recognized.
5. The dynamic identification method for online merchandise payment as claimed in claim 1, wherein said histogram equalization processing of the original identification image to obtain a standard identification image comprises:
calculating a gray level histogram of the original identification image;
and carrying out gray mean value conversion on the gray level histogram by using a preset conversion function to obtain the standard identification image.
6. The dynamic identification method for online merchandise payment according to claim 5, wherein the transforming the gray level histogram with a preset transformation function to a gray level mean value comprises:
performing gray level mean value conversion on the gray level histogram by using the following gray level conversion formula:
Figure DEST_PATH_IMAGE007
wherein,
Figure DEST_PATH_IMAGE008
for standard identificationThe gray-scale level of the image,
Figure DEST_PATH_IMAGE009
a formula for converting a gray scale is expressed,
Figure DEST_PATH_IMAGE010
the formula of the rounding is expressed,
Figure DEST_PATH_IMAGE011
represents the gray level histogram, an
Figure DEST_PATH_IMAGE012
，
Figure DEST_PATH_IMAGE013
Representing a range of gray levels in the original recognition image.
7. The dynamic identification method for online commodity payment according to claim 1, wherein the extracting local features in the standard identification image by using the improved LBP algorithm and performing histogram feature fusion on the local features to obtain original fusion features comprises:
dividing the standard identification image into a plurality of image blocks by using a preset pixel acquisition area;
carrying out inner layer and outer layer sampling processing on each image block, calculating LBP values of pixel points in the outer layer and the inner layer, and carrying out weighted average on the LBP values in the outer layer and the inner layer to obtain local characteristics of each image block;
and connecting the local features of each image block in series to obtain the original fusion features.
8. The dynamic identification method for online merchandise payment of claim 7, wherein prior to identifying the original fused feature using the pre-trained deep belief network, the method further comprises:
acquiring a face training image set, extracting local features of each image in the face training image set by using the improved LBP algorithm, and performing histogram feature fusion to obtain original training features of each image;
performing feature fusion on the original training features and corresponding images in the face training image set to obtain a standard training feature set of all images;
acquiring an original deep belief network, training RBM layers in the original deep belief network layer by utilizing the standard training feature set, and solving an energy value of each RBM layer;
and based on the energy value, reversely adjusting parameters of RBM layers in the original deep belief network by using BP (back propagation) until the energy value of each RBM layer meets a preset energy threshold, and stopping training to obtain the trained deep belief network.
9. The dynamic identification method for payment of online goods according to claim 8, wherein the energy value of each RBM layer is calculated using the following energy formula:
Figure DEST_PATH_IMAGE014
wherein,
Figure DEST_PATH_IMAGE015
for the said amount of energy to be taken into account,
Figure DEST_PATH_IMAGE016
representing the visible nodes in the RBM layer,
Figure DEST_PATH_IMAGE017
representing an implicit node in the RBM layer,
Figure DEST_PATH_IMAGE018
indicates the number of the visible nodes,
Figure DEST_PATH_IMAGE019
the number of the implied nodes is indicated,
Figure DEST_PATH_IMAGE020
denotes the first
Figure DEST_PATH_IMAGE021
The number of the visible nodes is one,
Figure DEST_PATH_IMAGE022
is shown as
Figure DEST_PATH_IMAGE023
An implicit node is defined as a node that is,
Figure DEST_PATH_IMAGE024
denotes the first
Figure 214291DEST_PATH_IMAGE021
A visual node and
Figure 193748DEST_PATH_IMAGE023
the weight between the implicit nodes is such that,
Figure DEST_PATH_IMAGE025
is a preset threshold value for the visible node,
Figure DEST_PATH_IMAGE026
a preset threshold value for the hidden node.
10. A dynamic identification device for payment of online goods, the device comprising:
the dynamic password acquisition module is used for acquiring a commodity payment request, generating an authentication password based on the commodity payment request, sending the authentication password to an authentication server, and receiving a dynamic encryption random password fed back by the authentication server based on the authentication password;
the password authentication module is used for analyzing the dynamic encryption random password to obtain a dynamic random number, and performing password authentication with the authentication server based on the dynamic random number to obtain a password authentication result;
the face image acquisition module is used for generating a face recognition interface based on the password authentication result and acquiring a face image to be recognized from the face recognition interface;
the local feature fusion module is used for carrying out denoising processing and histogram equalization processing on the face image to be recognized to obtain a standard recognition image, extracting local features in the standard recognition image by utilizing an improved LBP algorithm, and carrying out histogram feature fusion on the local features to obtain original fusion features;
and the identity recognition module is used for carrying out identity recognition on the original fusion characteristics by utilizing a pre-trained deep belief network to obtain an identity recognition result.
CN202210513978.2A 2022-05-12 2022-05-12 Dynamic identity identification method and device for online commodity payment Active CN114626860B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210513978.2A CN114626860B (en) 2022-05-12 2022-05-12 Dynamic identity identification method and device for online commodity payment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210513978.2A CN114626860B (en) 2022-05-12 2022-05-12 Dynamic identity identification method and device for online commodity payment

Publications (2)

Publication Number Publication Date
CN114626860A true CN114626860A (en) 2022-06-14
CN114626860B CN114626860B (en) 2022-08-05

Family

ID=81905357

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210513978.2A Active CN114626860B (en) 2022-05-12 2022-05-12 Dynamic identity identification method and device for online commodity payment

Country Status (1)

Country Link
CN (1) CN114626860B (en)

Citations (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060053289A1 (en) * 2004-09-09 2006-03-09 International Business Machines Corporation Peer-to-peer communications
CN1758594A (en) * 2004-10-08 2006-04-12 富士通株式会社 Biometric authenticating apparatus and terminal
CN106576041A (en) * 2014-06-27 2017-04-19 林建华 Method of mutual verification between a client and a server
CN106778512A (en) * 2016-11-25 2017-05-31 南京蓝泰交通设施有限责任公司 Face identification method under the conditions of a kind of unrestricted based on LBP and depth school
CN107403312A (en) * 2016-05-18 2017-11-28 北京三星通信技术研究有限公司 Quick payment method and apparatus
CN107578007A (en) * 2017-09-01 2018-01-12 杭州电子科技大学 A kind of deep learning face identification method based on multi-feature fusion
CN107729890A (en) * 2017-11-30 2018-02-23 华北理工大学 Face identification method based on LBP and deep learning
US20180181964A1 (en) * 2015-02-13 2018-06-28 Yoti Holding Limited Secure Electronic Payment
CN108446682A (en) * 2018-05-11 2018-08-24 深圳尊豪网络科技股份有限公司 A kind of recognition of face calibration detection method of full-automation
US20190116180A1 (en) * 2016-05-13 2019-04-18 Nec Corporation Authentication system, authentication method, and program
CN110855444A (en) * 2019-11-01 2020-02-28 北京印刷学院 Pure software CAVA identity authentication method based on trusted third party
CN112242993A (en) * 2020-09-02 2021-01-19 海量安全技术有限公司 Bidirectional authentication method and system
CN112311794A (en) * 2020-10-30 2021-02-02 中电万维信息技术有限责任公司 Bidirectional identity authentication method based on MFA algorithm
CN112422587A (en) * 2021-01-21 2021-02-26 腾讯科技（深圳）有限公司 Identity verification method and device, computer equipment and storage medium
WO2021096192A1 (en) * 2019-11-12 2021-05-20 Samsung Electronics Co., Ltd. Neural facial expressions and head poses reenactment with latent pose descriptors

Patent Citations (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060053289A1 (en) * 2004-09-09 2006-03-09 International Business Machines Corporation Peer-to-peer communications
CN1758594A (en) * 2004-10-08 2006-04-12 富士通株式会社 Biometric authenticating apparatus and terminal
CN106576041A (en) * 2014-06-27 2017-04-19 林建华 Method of mutual verification between a client and a server
US20180181964A1 (en) * 2015-02-13 2018-06-28 Yoti Holding Limited Secure Electronic Payment
US20190116180A1 (en) * 2016-05-13 2019-04-18 Nec Corporation Authentication system, authentication method, and program
CN107403312A (en) * 2016-05-18 2017-11-28 北京三星通信技术研究有限公司 Quick payment method and apparatus
CN106778512A (en) * 2016-11-25 2017-05-31 南京蓝泰交通设施有限责任公司 Face identification method under the conditions of a kind of unrestricted based on LBP and depth school
CN107578007A (en) * 2017-09-01 2018-01-12 杭州电子科技大学 A kind of deep learning face identification method based on multi-feature fusion
CN107729890A (en) * 2017-11-30 2018-02-23 华北理工大学 Face identification method based on LBP and deep learning
CN108446682A (en) * 2018-05-11 2018-08-24 深圳尊豪网络科技股份有限公司 A kind of recognition of face calibration detection method of full-automation
CN110855444A (en) * 2019-11-01 2020-02-28 北京印刷学院 Pure software CAVA identity authentication method based on trusted third party
WO2021096192A1 (en) * 2019-11-12 2021-05-20 Samsung Electronics Co., Ltd. Neural facial expressions and head poses reenactment with latent pose descriptors
CN112242993A (en) * 2020-09-02 2021-01-19 海量安全技术有限公司 Bidirectional authentication method and system
CN112311794A (en) * 2020-10-30 2021-02-02 中电万维信息技术有限责任公司 Bidirectional identity authentication method based on MFA algorithm
CN112422587A (en) * 2021-01-21 2021-02-26 腾讯科技（深圳）有限公司 Identity verification method and device, computer equipment and storage medium

Also Published As

Publication number Publication date
CN114626860B (en) 2022-08-05

Similar Documents

Publication Publication Date Title
US9769156B2 (en) Image based key derivation function
WO2021189364A1 (en) Method and device for generating adversarial image, equipment, and readable storage medium
CN105471575B (en) Information encryption and decryption method and device
CN110494854A (en) Use the Verification System of multi-party computations
CN112949760A (en) Model precision control method and device based on federal learning and storage medium
CN101877639B (en) Information processing apparatus, key update method, and program
CN113887408A (en) Method, device and equipment for detecting activated face video and storage medium
CN112699400B (en) Image information security processing method and device
CN109919109A (en) Image-recognizing method, device and equipment
CN114626860B (en) Dynamic identity identification method and device for online commodity payment
CN110781503A (en) Data calling method and device and computer readable storage medium
CN113868690B (en) Trusted deposit certificate based privacy calculation method and system
CN113255456B (en) Inactive living body detection method, inactive living body detection device, electronic equipment and storage medium
CN113761479B (en) Software authorization method, system, equipment and computer storage medium
CN113407968A (en) Encryption method, device, equipment and storage medium of target detection model
CN113888086A (en) Article signing method, device and equipment based on image recognition and storage medium
CN115280309A (en) Method, system and computer program product for authentication
CN108632228B (en) Decision engine scheduling method and system
CN116055129B (en) Internet of things equipment identity authentication method and system based on dynamic graphic password picture
CN116862541B (en) Commodity anti-counterfeiting management system based on NFC label
CN117315298B (en) RFID tag-based identification method and device, electronic equipment and storage medium
JP6253283B2 (en) Content data processing device
CN115545710A (en) Insurance expense payment method and system
CN114238902A (en) Fingerprint authentication method and device based on SM9 encryption and computer equipment
CN116645556A (en) Picture generation method and device, electronic equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
PE01 Entry into force of the registration of the contract for pledge of patent right

Denomination of invention: Dynamic identification method and device for online commodity payment

Effective date of registration: 20220928

Granted publication date: 20220805

Pledgee: Guanggu Branch of Wuhan Rural Commercial Bank Co.,Ltd.

Pledgor: Wuhan Heyue Digital Technology Co.,Ltd.

Registration number: Y2022420000334

PE01 Entry into force of the registration of the contract for pledge of patent right
PC01 Cancellation of the registration of the contract for pledge of patent right

Date of cancellation: 20230925

Granted publication date: 20220805

Pledgee: Guanggu Branch of Wuhan Rural Commercial Bank Co.,Ltd.

Pledgor: Wuhan Heyue Digital Technology Co.,Ltd.

Registration number: Y2022420000334

PC01 Cancellation of the registration of the contract for pledge of patent right
PE01 Entry into force of the registration of the contract for pledge of patent right

Denomination of invention: Dynamic identification method and device for online product payment

Effective date of registration: 20230927

Granted publication date: 20220805

Pledgee: Guanggu Branch of Wuhan Rural Commercial Bank Co.,Ltd.

Pledgor: Wuhan Heyue Digital Technology Co.,Ltd.

Registration number: Y2023980059448

PE01 Entry into force of the registration of the contract for pledge of patent right