CN108429619A - Identity identifying method and system - Google Patents
Identity identifying method and system Download PDFInfo
- Publication number
- CN108429619A CN108429619A CN201810049723.9A CN201810049723A CN108429619A CN 108429619 A CN108429619 A CN 108429619A CN 201810049723 A CN201810049723 A CN 201810049723A CN 108429619 A CN108429619 A CN 108429619A
- Authority
- CN
- China
- Prior art keywords
- user
- voice signal
- matrix
- data
- default
- 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.)
- Pending
Links
Classifications
-
- 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
- H04L9/3231—Biological data, e.g. fingerprint, voice or retina
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
Landscapes
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Computer Networks & Wireless Communication (AREA)
- Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Collating Specific Patterns (AREA)
Abstract
The present invention provides a kind of identity identifying method and system, this method includes：Acquire voice signal, fingerprint image data and the face image data of user；Spectrum signature is extracted to voice signal, obtains vocal print feature information；Vocal print feature information, fingerprint image data and face image data are respectively converted into the vocal print matrix, fingerprint image matrix and facial image matrix of default dimension；Above three matrix is spliced to obtain identity matrix data；Identity matrix data is input to default neural network model, obtains the first biological attribute data of user；Calculate the similarity between the first biological attribute data and the second biological attribute data of pre-registered user；Determine the corresponding target user of maximum similarity；If maximum similarity is more than default similarity threshold, returns and indicate verification result of the target user by authentication；If maximum similarity is less than or equal to default similarity threshold, returns and indicate target user not by the verification result of authentication.
Description
Technical field
The present invention relates to computer safety information technical fields, more particularly to a kind of identity identifying method and authentication
System.
Background technology
Currently, the intelligent terminals such as computer and smart mobile phone have become the important aid of people's Working Life.Pass through user
Equipment end done shopping, managed money matters, being filed, data storage etc. has been provided to the user and easily serviced very much, but the thing followed
It is the safety problem of user data and user's property etc..So user equipment end needs to solve the Verify Your Identity questions of user.
There are prodigious security risks for traditional static password, although dynamic password can further ensure the information peace of user
Entirely, but situations such as user equipment is by invasion or loss can not also be solved.With the development of various human body biological characteristics identification technologies,
People can identify the biological characteristic of individual identity using vocal print, fingerprint, face etc., construct based on various living things feature recognition skills
The identification confirmation system of art.But the development of artificial intelligence technology makes single creature characteristic identity is verified to be no longer able to
Meet protection demand of the people to higher confidential information, includes the single capacity certification system of other biological feature identification technique guiding
System.For example, bank account, electronic record etc. be related to personal or business property and information security need protected object.
It can be seen that identity verification scheme in the prior art is in the prevalence of the low problem of authentication degree of safety.
Invention content
The present invention provides a kind of identity identifying method and systems, are deposited with solving identity verification scheme in the prior art
The low problem of authentication degree of safety.
To solve the above-mentioned problems, according to an aspect of the present invention, the invention discloses a kind of identity identifying method, packets
It includes：
If receiving the ID authentication request of user, the voice signal, fingerprint image data and people of the user are acquired
Face image data；
Spectrum signature is extracted to the voice signal, obtains vocal print feature information；
The vocal print feature information is converted to the vocal print matrix of default dimension；
The fingerprint image data is converted to the fingerprint image matrix of the default dimension；
The face image data is converted to the facial image matrix of the default dimension；
The vocal print matrix, the fingerprint image matrix and the facial image matrix are spliced into row matrix, obtain institute
State the identity matrix data of user；
The identity matrix data of the user is input to default neural network model trained in advance to carry out
Living things feature recognition obtains the first biological attribute data of the user；
At least one second biology for calculating first biological attribute data and pre-registered at least one user is special
Levy the similarity between data；
Determine the corresponding target user of the maximum similarity；
If maximum similarity is more than default similarity threshold, returns and indicate target user's testing by authentication
Demonstrate,prove result；
If the maximum similarity is less than or equal to the default similarity threshold, returns and indicate the target user not
Pass through the verification result of authentication.
According to another aspect of the present invention, the invention also discloses a kind of identity authorization systems, including：
Acquisition module acquires voice signal, the fingerprint of the user if the ID authentication request for receiving user
Image data and face image data；
Characteristic extracting module obtains vocal print feature information for extracting spectrum signature to the voice signal；
First conversion module, the vocal print matrix for the vocal print feature information to be converted to default dimension；
Second conversion module, the fingerprint image matrix for the fingerprint image data to be converted to the default dimension；
Third conversion module, the facial image matrix for the face image data to be converted to the default dimension；
Concatenation module, for the vocal print matrix, the fingerprint image matrix and the facial image matrix to be carried out square
Battle array splicing, obtains the identity matrix data of the user；
Input module, for the identity matrix data of the user to be input to advance trained default nerve
Network model carries out living things feature recognition, obtains the first biological attribute data of the user；
Computing module, at least one for calculating first biological attribute data and pre-registered at least one user
Similarity between a second biological attribute data；
Determining module, for determining the corresponding target user of the maximum similarity；
First returns to module, if being more than default similarity threshold for maximum similarity, returns and indicates that the target is used
The verification result that family passes through authentication；
Second returns to module, if being less than or equal to the default similarity threshold for the maximum similarity, returns
Indicate the target user not by the verification result of authentication.
Compared with prior art, the present invention includes following advantages：
The present invention asks vocal print matrix, fingerprint image matrix and the facial image square of the user of authentication by acquisition
Battle array, and these three matrixes are spliced into an identity matrix data, to realize the fusion of vocal print, three fingerprint, face features；
And the identification of biological characteristic is carried out to the matrix data of fusion using an advance trained default neural network model,
To judge the identity of the user using the biological attribute data of the biological attribute data and pre-registered user that recognize
Whether by certification, the security intensity of authentication is improved, ensures the safety of information processing.
Description of the drawings
Fig. 1 is the work flow diagram of the identity authorization system of one embodiment of the invention；
Fig. 2 is the flow chart of the identity identifying method of one embodiment of the invention；
Fig. 3 is the structure diagram of the identity authorization system of one embodiment of the invention.
Specific implementation mode
For make the present invention above-mentioned purpose,
Feature and advantage can be more obvious and easy to understand, makees with reference to the accompanying drawings and detailed description to the present invention further
Detailed description.
Referring to Fig.1, a kind of work flow diagram of identity authorization system of the embodiment of the present invention is shown.
The identity authorization system includes voiceprint processing module, finger print information processing module, face information processing module
With comprehensive organism characteristic identity authentication module.
For the substantially workflow of the identity authorization system：
When user wants using operation system shown in FIG. 1, need to carry out authentication, user can be operable to
Send the identity authorization system for using the ID authentication request of operation system to the embodiment of the present invention, then, the embodiment of the present invention
Identity authorization system can to the ID authentication request carry out living things feature recognition, to according to registered in advance and preserve one
The biological characteristic of a or multiple users and judge whether the user is the user of mistake registered in advance, and identity authentication result is sent
To operation system, such operation system can be according to identity authentication result to determine whether the user is made to carry out partial function
It uses, ensures the information security of operation system.
With reference to Fig. 2, the embodiment of the present invention additionally provides a kind of identity identifying method, can be applied to the authentication system
System, the specific workflow of this method are as follows：
S1, identity authorization system can receive the ID authentication request of such as user A, then, the embodiment of the present invention
Identity authorization system will prompt user's typing for verifying identity：Voice data, fingerprint image and facial image, to adopt
Collect voice signal, fingerprint image data and the face image data of user A.
In practical applications, the mobile terminal which is applied can have recording
Function, camera function and finger print collecting function, to acquire voice signal, fingerprint image data and the face figure of user A respectively
As data.
Wherein, it when acquiring voice signal, can be realized in the way of any one by following：
Then mode 1 can obtain random voice letter by any random voice of user's typing from the random voice
Number；
Wherein, the corresponding random voice of the random voice signal supports at least one of following three classes character：It is Arabic
Number, English alphabet and simplified Hanzi.
The method of mode 2, the embodiment of the present invention can provide text data when prompting user's typing voice signal, use
Family is by reading aloud this article notebook data come the voice data of typing oneself, so as to obtain voice signal from the voice data.
Wherein, the voice signal of collected user A can be stored in voiceprint processing module shown in FIG. 1；
And when acquiring fingerprint image data, then it can acquire the user A using the finger print collecting function of mobile terminal
Finger print data, and the finger print data is generated as fingerprint image data；
Wherein, the fingerprint image data of collected user A can be stored in finger print information processing module shown in FIG. 1
In；
And when acquiring face image data, then the people of the user A can be acquired using the camera function of mobile terminal
Face image carries out image taking, to obtain the face image data of user A；
Wherein, the face image data of collected user A can be stored in face information processing module shown in FIG. 1
In；
Wherein, the present invention for above-mentioned voice signal, fingerprint image data and face image data acquisition order not
It limits.
Optionally, in one embodiment, in order to ensure the accuracy to living things feature recognition, to above-mentioned collected
Before three classes data carry out characteristic processing, the method for the embodiment of the present invention can execute S2, to above-mentioned voice signal, fingerprint image
One or more of data and face image data data carry out pretreatment operation respectively.
Wherein, it when carrying out pretreatment operation to voice signal, may include steps of：
Remove the noise information in the voice signal；
Sample quantization processing is carried out to the voice signal after removal noise information；
Wherein, sample quantization：Voice signal is usually digitized with 8kHz or higher sampling rates, and each sampling is at least used
Family 8bit is indicated.
To sample quantization, treated that the voice signal carries out preemphasis processing；
Wherein, sound is converted into audio digital signals after the sampling of 8kHz or higher sampling rate, then passes through one
A single order high-pass filter is handled to make preemphasis to highlight high frequency section.
To preemphasis, treated that the voice signal carries out that sound frame is taken to handle；
Wherein it is possible to which it is a sound frame (20ms) to take at 256 points, between sound frame and sound frame be overlapped 128 points (10ms), i.e., every time
Take after 128 points of displacement again at 256 points as next sound frame, it in this way can be excessively violent to avoid the characteristic variations between sound frame.
Treated to taking sound frame, and the voice signal carries out windowing process；
Wherein, Hamming window is multiplied by eliminate the discontinuity at sound frame both ends for each sound frame, by preceding when avoiding analyzing
The influence of sound frame afterwards.
In this way, the voice signal after above-mentioned pretreatment operation can carry in favor of subsequent audible spectrum feature extraction
Rise the recognition accuracy of vocal print feature.
And when carrying out pretreatment operation to fingerprint image data, which refers to Noise and pseudo-characteristic
Fingerprint image is pocessed using certain algorithm, keeps its streakline clear in structure, and characteristic information protrudes.The purpose is to improve fingerprint
The quality of image improves the accuracy of feature extraction.In general, when being pre-processed to fingerprint image, main process includes returning
One change, image segmentation, enhancing, binaryzation and refinement, but according to different application scenarios and actual demand, it can be to above-mentioned pre- place
Reason operation is flexibly selected.
And when carrying out pretreatment operation to face image data, then grey scale can be carried out to the face image data
The operations such as change, consequently facilitating the extraction for carrying out face characteristic to face image data identifies.
Wherein, priority of the present invention for the pretreatment operation of voice signal, fingerprint image data and face image data
Sequence does not limit, and in specific execute, then it can be respectively by the voiceprint processing module in Fig. 1, finger print information processing
Module and face information processing module carry out above-mentioned corresponding pretreatment operation.
In this way, voice signal, fingerprint image data and face image data after above-mentioned each pretreatment operation
Vocal print feature, fingerprint characteristic and face characteristic are more notable, to improve the extraction to each feature and recognition accuracy.
S2 extracts spectrum signature to the voice signal of (that is, after windowing process) after pretreatment operation, obtains vocal print spy
Reference ceases；And the vocal print feature information is converted to the vocal print matrix of default dimension；
Wherein it is possible to be extracted compared with subject to from pretreated voice signal by the voiceprint processing module in Fig. 1
True vocal print feature information, and convert the vocal print feature information in the matrix of 256*256 fixed sizes.Wherein, it is herein
It is extracted the spectrum signature of audio (voice signal), wherein including the vocal print feature of user.
The fingerprint image data is converted to the fingerprint image matrix of the default dimension by S3；
Wherein it is possible to be converted pretreated fingerprint image data to by the finger print information processing module in Fig. 1
The fingerprint image matrix of 256*256 fixed sizes shows as the fingerprint gray-scale map of 256*256 pixels.
The face image data is converted to the facial image matrix of the default dimension by S4；
Wherein it is possible to be converted pretreated face image data to by the face information processing module in Fig. 1
The facial image matrix of 256*256 fixed sizes shows as the face gray-scale map of 256*256 pixels.
It should be noted that in other embodiments, which is not intended to be limited to 256*256, can also be other
The square formation or line number of the dimension matrix different with columns, in the present embodiment, due to advance trained default nerve net
Network model is when data are inputted using 768*256, that is, is directed to the matrix of 3 256*256, therefore, default dimension here
For 256*256；But in other embodiments, if the number that trained default neural network model receives in advance
According to the matrix that input is other dimensions, then default dimension herein can also be adjusted to other dimensions, also, vocal print matrix, refer to
The dimension of print image matrix and facial image matrix can be identical or different.
Further, it should be noted that the present invention does not limit the execution sequence of S2~S4.
The vocal print matrix, the fingerprint image matrix and the facial image matrix are spliced into row matrix, are obtained by S5
The identity matrix data of the user；The identity matrix data of the user is input to advance trained default god
Living things feature recognition is carried out through network model, obtains the first biological attribute data of the user；
Wherein, voiceprint processing module as shown in Figure 1, finger print information processing module and face information processing module point
It is defeated that obtained 256*256 vocal prints matrix, 256*256 fingerprint images matrix and 256*256 facial image matrixes will not be handled respectively
Go out to comprehensive organism characteristic identity authentication module, then, comprehensive organism characteristic identity authentication module by 256*256 vocal prints matrix,
256*256 fingerprint images matrix and 256*256 facial images matrix splice into row matrix, to obtain the body of a 768*256
Part matrix data, wherein since in the default neural network model of training, the dimension of identity matrix data used herein is
768*256, therefore, it is required that the dimension of spliced matrix is consistent with the data dimension when training when matrix splices here.
But in other embodiments, if in the default neural network model of training, the dimension of identity matrix data used herein
For 256*768, then this is in when splicing to three matrixes, then needs the identity matrix data for obtaining 256*768.Wherein,
The comprehensive organism characteristic identity authentication module may include advance trained default neural network model, therefore, comprehensive life
The identity matrix data of 768*256 by matrix splicing can be input to the default nerve net by object characteristic identity authentication module
Network model (such as CNN, convolutional neural networks model) carries out living things feature recognition, obtains the first biological attribute data of user A；
It wherein, can be using the identity matrix data for the 768*256 that matrix splices as by instructing in specific implementation
The input data of experienced CNN, successively pass through the CNN convolutional layer C1 (7*7 convolution, totally 128), pond layer P1 (adopt by 2*2 most values
Sample), convolutional layer C2 (5*5 convolution, totally 128), pond layer P2 (2*2 is most worth sampling), convolutional layer C3* (5*5 convolution, totally 128
It is a), pond layer P3 (2*2 is most worth sampling), convolutional layer C4 (3*3 convolution, totally 128), pond layer P4 (2*2 is most worth sampling), volume
Tanh layers of lamination C5 (3*3, totally 128), pond layer P5 (2*2 is most worth sampling), full articulamentum and activation primitive, obtain 128 dimensions
Vector, i.e. the first biological attribute data of user A.
Further, it should be noted that in this example, the attended operation of three eigenmatrixes be not realized by the CNN, and
In other embodiments, it can also be realized by CNN.
Further, it should be noted that the advance trained default neural network model of the embodiment of the present invention and unlimited
In CNN, the neural network models such as RNN (Recognition with Recurrent Neural Network), DNN (deep neural network) are can also be.
Wherein, living things feature recognition, identification is comprehensive characteristics (including vocal print, fingerprint and face characteristic), and non-individual
It identifies vocal print, fingerprint and face characteristic, then combines them, but Direct Recognition represents vocal print feature, fingerprint to one
The comprehensive characteristics of feature and face characteristic, the identity of the identity user for uniqueness.
S6 calculates first biological attribute data and at least one second biology of pre-registered at least one user
Similarity between characteristic；Determine the corresponding target user of the maximum similarity；If maximum similarity is more than default phase
Like degree threshold value, then the verification result for indicating that the target user passes through authentication is returned；If the maximum similarity be less than or
Equal to the default similarity threshold, then returns and indicate the target user not by the verification result of authentication.
Wherein, the user for carrying out authentication is firstly the need of the registration for carrying out identity information, the identity information registration of user
Flow and above-mentioned flow for authenticating ID difference lies in receive be user identity registration request, to which CNN be identified
To registration user biological attribute data (here with the second biological attribute data come distinguish over verification user biological characteristic
Data), and second biological attribute data is stored in the present invention as the uniqueness identity identifier of registration user
In the identity authorization system of embodiment, as to how obtaining second biological attribute data, it is referred to above-mentioned authentication stream
Journey S1~S5, which is not described herein again.
Wherein, when the identity authorization system is applied to the mobile terminal of some personal use, such as when mobile phone, then the body
Part Verification System generally only preserves the second biological attribute data of oneself of owner's registration, i.e., the second of user there are one preservation
Biological attribute data, so that other users can not carry out business processing to the mobile terminal of owner；
And when the identity authorization system is applied to the terminal device of more personal uses, such as public computer or server
When, then the identity authorization system can preserve the second biological attribute data of multiple users, and each user has unique the
Two biological attribute datas to carry out the operation system on the terminal device for verifying personal identity to have permission
Conditional business processing, guarantees data security.
Therefore, in step S6 when carrying out the calculating of similarity, if only registered with when identity authorization system is registered in advance
The second biological attribute data of one user, that is, be suitable for personal use mobile terminal the case where, then when executing S6, it is only necessary to
The pre-registered owner preserved in the first biological attribute data of the user A of computation requests authentication and identity authorization system
The second biological attribute data between similarity, which is maximum similarity, and corresponding user is exactly owner；If
The similarity is more than such as 98%, then it is exactly owner that explanation, which currently makes requests on the user A of authentication, returns and indicates user A
By the verification result of authentication to operation system；On the contrary, it is not machine that then explanation, which currently makes requests on the user A of authentication,
It is main, expression user A is returned not by the verification result of authentication to operation system, so that the user A can not be to business
System carries out the operation that part is related to partial information safety.
In another embodiment, in S6 when carrying out the calculating of similarity, if identity authorization system is registered in advance,
The case where registering with the second biological attribute data of multiple users, that is, being suitable for the terminal device of more personal uses, then executing
When S6, then the first biological attribute data for calculating separately the user A of request authentication is needed to be preserved with identity authorization system
Each of similarity between the second biological attribute data of each of pre-registered user, then obtain multiple similarities, then,
It determines the corresponding registration user of maximum similarity being calculated, that is, indicates that the user A may be registration user；If this is most
Big similarity is more than such as 98%, then it is exactly the registration user found that explanation, which currently makes requests on the user A of authentication, is returned
Return indicate user A by the verification result of authentication to operation system (so that user A can carry out the operation system
The operation of its permission having)；On the contrary, the user A that then explanation currently makes requests on authentication is not registration user, table is returned
Show user A not by the verification result of authentication to operation system so that the user A can not be to operation system carry out portion
Divide the operation for being related to partial information safety.
By means of the above-mentioned technical proposal of the embodiment of the present invention, the present invention asks the sound of the user of authentication by acquisition
Line matrix, fingerprint image matrix and facial image matrix, and matrix is spliced into an identity matrix data, to realize vocal print,
The fusion of three fingerprint, face features；And using an advance trained default neural network model come the square to fusion
Battle array data carry out the identification of biological characteristic, to special using the biology of the biological attribute data and pre-registered user recognized
Identity of the data to judge the user is levied whether by certification, the security intensity of authentication is improved, ensures information processing
Safety.
Optionally, in one embodiment, before executing above-mentioned flow for authenticating ID, side according to the ... of the embodiment of the present invention
Method can also include the step preset the living things feature recognition of neural network model to this and trained.
Specifically, can be using the training sample of multiple users (such as 100,000 users) come to the default nerve net
Network model (such as CNN) carries out living things feature recognition training, after CNN convergences, so that it may trained described pre- to obtain
If neural network model；
Wherein, the training sample of each user includes positive sample and negative sample, wherein positive sample includes same
Voice signal, fingerprint image data and the face image data of user, negative sample include the voice signal of different user, fingerprint image
As data and face image data.
For example, it is carried out by taking the training sample of some user M in the training sample of above-mentioned 100,000 users as an example
Illustrate, user M can be acquired to same section of content of text at three sections of three different time sections (such as the morning, noon and evening)
Recording data, i.e. user M have three sections of recording for the same text；It can also be to the same finger typing of the user M
10 fingerprints obtain 10 fingerprint images for the same finger (such as right hand index finger)；The user M can also be acquired not
10 captured by under same shooting condition (such as the different shooting conditions such as different light, different background, different hair styles, different dressings)
Open facial image.In this way, when generating positive sample to user M, so that it may to choose any one recording from three sections of recording datas
Data arbitrarily choose a fingerprint image from 10 fingerprint images, then choose any one face from 10 facial images
Image, a positive sample as the user M.And this three category information can be combined arbitrarily, so as to obtain 300 combinations,
So that the positive sample of the user M there are 300, the data of any one type in 300 positive samples are then replaced with it again
The data of the corresponding types of his user, such as the recording data in one group of positive sample of user M is replaced with to the recording number of user C
According to, then one group of negative sample of the user M can be obtained, and so on, and multigroup negative sample of user M can be obtained.
Then, the CNN models are distinguished using each sample in the multiple positive samples and multiple negative samples of the user M
Multiple living things feature recognition training is carried out, until the biological attribute data that the CNN models export and this for training the CNN
Error between the biological attribute data that vocal print, fingerprint and the face characteristic of the training sample of user M merge is less than default error
Threshold value, such as 0.002%, so that it may to illustrate that the CNN models are restrained to a certain extent；Similarly recycle the positive sample of other users
This and negative sample further train CNN models so that the CNN models all receive the recognition result of all training samples
It holds back, so that it may to obtain above-mentioned trained neural network model in advance.
Optionally, in one embodiment, it if the maximum similarity is more than default similarity threshold, returns and indicates institute
After stating the verification result that target user passes through authentication, can also include according to the method for the embodiment of the present invention：
Using first biological attribute data to the second biological characteristic number of the pre-registered target user
According to being updated and be updated to the default similarity threshold using the maximum similarity.
I.e., it is possible to using the biological attribute data of the user A by authentication come to registered in advance and preservation to the body
The biological attribute data of the user A of part Verification System is updated, to ensure the user A's locally preserved in identity people's system
Biological attribute data (i.e. the second biological attribute data) is highest with the practical biometric matches degree of user A.In addition, example
Such as, which is 98%, and default similarity threshold is 97%, then after the authentication of the user A passes through, is
Accuracy of the lifting system to biological characteristic (fusion of vocal print, fingerprint and face characteristic) certification, can also be with the similarity
98% is updated default similarity threshold (97%).Certainly, similarity threshold update here pertains only to positive update,
It is not related to negative sense update (being updated to lower value from higher value).
To sum up, the present invention integrates multinomial human body biological characteristics, including vocal print, fingerprint and face characteristic, realizes a set of base
In the synthesis identity authorization system solution of human body biological characteristics identification；The voiceprint of user, fingerprint are believed in the present invention
Breath, face characteristic information are merged, and realize the comprehensive organism feature recognition of triplicity, have evaded the knowledge of single creature feature
Potentially identify and practise fraud in not the risk brought.The multi-biological characteristic integrates three biologies in identity authorization system solution
Feature is uniformly treated, and is realized by CNN algorithms, Holistic modeling, and whole identity verification scheme is constituted, and it is more next can to meet user
Higher security requirement.In addition the data acquisition equipment of the identity verification scheme requires relatively low, current overwhelming majority intelligence
The terminals such as mobile phone, pad can complete the acquisition of required human body biological characteristics data, be answered convenient for the business in intelligent terminal field
With.
In addition, the identity authorization system of the comprehensive organism feature based on vocal print, fingerprint and face of the present invention, comprehensive organism
Characteristic identity authentication module can check three kinds of biological characteristics of human body, by unified model layer, return to final identity and recognize
Card as a result, can with open an account with the bank, security are opened an account etc., and securities rank requires in high, the true complete business of data information,
For maintaining secrecy and other are needed in the trouble free service of authentication, it is clear that in conjunction with the authentication system of three-type-person's body biological characteristic
System, robustness is stronger, safety higher, more worth user trust.
It should be noted that for embodiment of the method, for simple description, therefore it is all expressed as a series of action group
It closes, but those skilled in the art should understand that, the embodiment of the present invention is not limited by the described action sequence, because according to
According to the embodiment of the present invention, certain steps can be performed in other orders or simultaneously.Secondly, those skilled in the art also should
Know, embodiment described in this description belongs to preferred embodiment, and the involved action not necessarily present invention is implemented
Necessary to example.
It is corresponding with the method that the embodiments of the present invention are provided, with reference to Fig. 3, show a kind of authentication of the present invention
The structure diagram of system embodiment, can specifically include following module：
Acquisition module 31 acquires the voice signal of the user, refers to if the ID authentication request for receiving user
Print image data and face image data；
Characteristic extracting module 32 obtains vocal print feature information for extracting spectrum signature to the voice signal；
First conversion module 33, the vocal print matrix for the vocal print feature information to be converted to default dimension；
Second conversion module 34, the fingerprint image square for the fingerprint image data to be converted to the default dimension
Battle array；
Third conversion module 35, the facial image square for the face image data to be converted to the default dimension
Battle array；
Concatenation module 36, for carrying out the vocal print matrix, the fingerprint image matrix and the facial image matrix
Matrix splices, and obtains the identity matrix data of the user；
Input module 37, for the identity matrix data of the user to be input to advance trained default god
Living things feature recognition is carried out through network model, obtains the first biological attribute data of the user；
Computing module 38, for calculating first biological attribute data and pre-registered at least one user at least
Similarity between one the second biological attribute data；
Determining module 39, for determining the corresponding target user of the maximum similarity；
First returns to module 40, if being more than default similarity threshold for maximum similarity, returns and indicates the target
The verification result that user passes through authentication；
Second returns to module 41, if being less than or equal to the default similarity threshold for the maximum similarity, returns
It returns and indicates that the target user does not pass through the verification result of authentication.
Optionally, the system also includes：
Module is removed, for removing the noise information in the voice signal；
First processing module, for carrying out sample quantization processing to the voice signal after removal noise information；
Second processing module, for treated that the voice signal carries out preemphasis processing to sample quantization；
Third processing module, for treated that the voice signal carries out that sound frame is taken to handle to preemphasis；
Fourth processing module, for treated to taking sound frame, the voice signal carries out windowing process；
The characteristic extracting module 32 includes：
Feature extraction submodule obtains vocal print spy for extracting spectrum signature to the voice signal after windowing process
Reference ceases.
Optionally, the system also includes：
Training module carries out biological characteristic for the training sample using multiple users to the default neural network model
Recognition training obtains the trained default neural network model；
The training sample includes positive sample and negative sample, wherein positive sample includes the voice signal of the same user, refers to
Print image data and face image data；Negative sample includes the voice signal, fingerprint image data and facial image of different user
Data.
Optionally, the system also includes：
Update module, for using first biological attribute data to the pre-registered target user described the
Two biological attribute datas are updated, and are updated to the default similarity threshold using the maximum similarity.
For system embodiments, since it is basically similar to the method embodiment, so fairly simple, the correlation of description
Place illustrates referring to the part of embodiment of the method.
Each embodiment in this specification is described in a progressive manner, the highlights of each of the examples are with
The difference of other embodiment, the same or similar parts between the embodiments can be referred to each other.
It should be understood by those skilled in the art that, the embodiment of the embodiment of the present invention can be provided as method, apparatus or calculate
Machine program product.Therefore, the embodiment of the present invention can be used complete hardware embodiment, complete software embodiment or combine software and
The form of the embodiment of hardware aspect.Moreover, the embodiment of the present invention can be used one or more wherein include computer can
With in the computer-usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) of program code
The form of the computer program product of implementation.
The embodiment of the present invention be with reference to according to the method for the embodiment of the present invention, terminal device (system) and computer program
The flowchart and/or the block diagram of product describes.It should be understood that flowchart and/or the block diagram can be realized by computer program instructions
In each flow and/or block and flowchart and/or the block diagram in flow and/or box combination.These can be provided
Computer program instructions are set to all-purpose computer, special purpose computer, Embedded Processor or other programmable data processing terminals
Standby processor is to generate a machine so that is held by the processor of computer or other programmable data processing terminal equipments
Capable instruction generates for realizing in one flow of flow chart or multiple flows and/or one box of block diagram or multiple boxes
The device of specified function.
These computer program instructions, which may also be stored in, can guide computer or other programmable data processing terminal equipments
In computer-readable memory operate in a specific manner so that instruction stored in the computer readable memory generates packet
The manufacture of command device is included, which realizes in one flow of flow chart or multiple flows and/or one side of block diagram
The function of being specified in frame or multiple boxes.
These computer program instructions can be also loaded into computer or other programmable data processing terminal equipments so that
Series of operation steps are executed on computer or other programmable terminal equipments to generate computer implemented processing, thus
The instruction executed on computer or other programmable terminal equipments is provided for realizing in one flow of flow chart or multiple flows
And/or in one box of block diagram or multiple boxes specify function the step of.
Although the preferred embodiment of the embodiment of the present invention has been described, once a person skilled in the art knows bases
This creative concept, then additional changes and modifications can be made to these embodiments.So the following claims are intended to be interpreted as
Including preferred embodiment and fall into all change and modification of range of embodiment of the invention.
Finally, it is to be noted that, herein, relational terms such as first and second and the like be used merely to by
One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation
Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant meaning
Covering non-exclusive inclusion, so that process, method, article or terminal device including a series of elements not only wrap
Those elements are included, but also include other elements that are not explicitly listed, or further include for this process, method, article
Or the element that terminal device is intrinsic.In the absence of more restrictions, being wanted by what sentence "including a ..." limited
Element, it is not excluded that there is also other identical elements in process, method, article or the terminal device including the element.
Above to a kind of identity identifying method provided by the present invention and a kind of identity authorization system, detailed Jie has been carried out
It continues, principle and implementation of the present invention are described for specific case used herein, and the explanation of above example is only
It is the method and its core concept for being used to help understand the present invention；Meanwhile for those of ordinary skill in the art, according to this hair
Bright thought, there will be changes in the specific implementation manner and application range, in conclusion the content of the present specification should not manage
Solution is limitation of the present invention.
Claims (8)
1. a kind of identity identifying method, which is characterized in that including：
If receiving the ID authentication request of user, the voice signal, fingerprint image data and face figure of the user are acquired
As data；
Spectrum signature is extracted to the voice signal, obtains vocal print feature information；
The vocal print feature information is converted to the vocal print matrix of default dimension；
The fingerprint image data is converted to the fingerprint image matrix of the default dimension；
The face image data is converted to the facial image matrix of the default dimension；
The vocal print matrix, the fingerprint image matrix and the facial image matrix are spliced into row matrix, obtain the use
The identity matrix data at family；
The identity matrix data of the user is input to default neural network model trained in advance and carries out biology
Feature recognition obtains the first biological attribute data of the user；
Calculate first biological attribute data and at least one second biological characteristic number of pre-registered at least one user
Similarity between；
Determine the corresponding target user of the maximum similarity；
If maximum similarity is more than default similarity threshold, the verification knot for indicating that the target user passes through authentication is returned
Fruit；
If the maximum similarity is less than or equal to the default similarity threshold, returns and indicate that the target user does not pass through
The verification result of authentication.
2. according to the method described in claim 1, it is characterized in that,
Described to extract spectrum signature to the voice signal, before obtaining vocal print feature information, the method further includes：
Remove the noise information in the voice signal；
Sample quantization processing is carried out to the voice signal after removal noise information；
To sample quantization, treated that the voice signal carries out preemphasis processing；
To preemphasis, treated that the voice signal carries out that sound frame is taken to handle；
Treated to taking sound frame, and the voice signal carries out windowing process；
It is described that spectrum signature is extracted to the voice signal, vocal print feature information is obtained, including：
Spectrum signature is extracted to the voice signal after windowing process, obtains vocal print feature information.
3. according to the method described in claim 1, it is characterized in that, before the ID authentication request for receiving the user, institute
The method of stating further includes：
Living things feature recognition training is carried out to the default neural network model using the training sample of multiple users, obtain by
The trained default neural network model；
The training sample includes positive sample and negative sample, wherein positive sample includes the voice signal of the same user, fingerprint image
As data and face image data；Negative sample includes the voice signal, fingerprint image data and face image data of different user.
4. according to the method described in claim 1, it is characterized in that, if the maximum similarity is more than default similarity threshold,
After then returning to the verification result that the expression target user passes through authentication, the method further includes：
Using first biological attribute data to second biological attribute data of the pre-registered target user into
Row update, and the default similarity threshold is updated using the maximum similarity.
5. a kind of identity authorization system, which is characterized in that including：
Acquisition module acquires voice signal, the fingerprint image of the user if the ID authentication request for receiving user
Data and face image data；
Characteristic extracting module obtains vocal print feature information for extracting spectrum signature to the voice signal；
First conversion module, the vocal print matrix for the vocal print feature information to be converted to default dimension；
Second conversion module, the fingerprint image matrix for the fingerprint image data to be converted to the default dimension；
Third conversion module, the facial image matrix for the face image data to be converted to the default dimension；
Concatenation module, for spelling the vocal print matrix, the fingerprint image matrix and the facial image matrix into row matrix
It connects, obtains the identity matrix data of the user；
Input module, for the identity matrix data of the user to be input to advance trained default neural network
Model carries out living things feature recognition, obtains the first biological attribute data of the user；
Computing module, at least one for calculating first biological attribute data and pre-registered at least one user
Similarity between two biological attribute datas；
Determining module, for determining the corresponding target user of the maximum similarity；
First returns to module, if being more than default similarity threshold for maximum similarity, returns and indicates that the target user is logical
Cross the verification result of authentication；
Second returns to module, if being less than or equal to the default similarity threshold for the maximum similarity, returns to expression
The target user does not pass through the verification result of authentication.
6. system according to claim 5, which is characterized in that the system also includes：
Module is removed, for removing the noise information in the voice signal；
First processing module, for carrying out sample quantization processing to the voice signal after removal noise information；
Second processing module, for treated that the voice signal carries out preemphasis processing to sample quantization；
Third processing module, for treated that the voice signal carries out that sound frame is taken to handle to preemphasis；
Fourth processing module, for treated to taking sound frame, the voice signal carries out windowing process；
The characteristic extracting module includes：
Feature extraction submodule obtains vocal print feature letter for extracting spectrum signature to the voice signal after windowing process
Breath.
7. system according to claim 5, which is characterized in that the system also includes：
Training module carries out living things feature recognition for the training sample using multiple users to the default neural network model
Training, obtains the trained default neural network model；
The training sample includes positive sample and negative sample, wherein positive sample includes the voice signal of the same user, fingerprint image
As data and face image data；Negative sample includes the voice signal, fingerprint image data and face image data of different user.
8. system according to claim 5, which is characterized in that the system also includes：
Update module, for second life using first biological attribute data to the pre-registered target user
Object characteristic is updated, and is updated to the default similarity threshold using the maximum similarity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810049723.9A CN108429619A (en) | 2018-01-18 | 2018-01-18 | Identity identifying method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810049723.9A CN108429619A (en) | 2018-01-18 | 2018-01-18 | Identity identifying method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108429619A true CN108429619A (en) | 2018-08-21 |
Family
ID=63156031
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810049723.9A Pending CN108429619A (en) | 2018-01-18 | 2018-01-18 | Identity identifying method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108429619A (en) |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109299594A (en) * | 2018-09-04 | 2019-02-01 | 阿里巴巴集团控股有限公司 | Auth method and device |
| CN109583387A (en) * | 2018-11-30 | 2019-04-05 | 龙马智芯（珠海横琴）科技有限公司 | Identity identifying method and device |
| CN109584886A (en) * | 2018-12-04 | 2019-04-05 | 科大讯飞股份有限公司 | Identity identifying method, device, equipment and storage medium based on Application on Voiceprint Recognition |
| CN109614844A (en) * | 2018-10-16 | 2019-04-12 | 阿里巴巴集团控股有限公司 | A kind of link verification method, device and equipment |
| CN109858366A (en) * | 2018-12-28 | 2019-06-07 | 龙马智芯（珠海横琴）科技有限公司 | Identity identifying method and device |
| CN109977639A (en) * | 2018-10-26 | 2019-07-05 | 招商银行股份有限公司 | Identity identifying method, device and computer readable storage medium |
| CN110516435A (en) * | 2019-09-02 | 2019-11-29 | 国网电子商务有限公司 | Private key management method and device based on biological characteristics |
| CN110827453A (en) * | 2019-11-18 | 2020-02-21 | 成都启英泰伦科技有限公司 | Fingerprint and voiceprint double authentication method and authentication system |
| CN110866234A (en) * | 2019-09-29 | 2020-03-06 | 南京大学 | Identity verification system based on multiple biological characteristics |
| CN110875037A (en) * | 2019-11-19 | 2020-03-10 | 腾讯科技（深圳）有限公司 | Voice data processing method and device and electronic equipment |
| CN111104658A (en) * | 2018-10-25 | 2020-05-05 | 北京嘀嘀无限科技发展有限公司 | Registration method and device, authentication method and device |
| CN111464541A (en) * | 2020-04-01 | 2020-07-28 | 重庆德信建信息技术有限公司 | Electronic government affair multifunctional intelligent hardware terminal based on biological recognition and working method |
| CN112232255A (en) * | 2020-10-26 | 2021-01-15 | 上海鹰瞳医疗科技有限公司 | Identity authentication method and equipment based on multi-mode data |
| CN112637209A (en) * | 2020-12-23 | 2021-04-09 | 四川虹微技术有限公司 | Security authentication method and device, security registration method and device, and storage medium |
| CN112669511A (en) * | 2020-12-18 | 2021-04-16 | 中用科技有限公司 | User registration and authentication method, system and equipment based on face voiceprint |
| CN112669966A (en) * | 2020-12-14 | 2021-04-16 | 北京易华录信息技术股份有限公司 | Behavior analysis system based on monitoring data |
| CN112990943A (en) * | 2021-03-16 | 2021-06-18 | 上海万向区块链股份公司 | Method and system for realizing block chain prediction machine based on image information identification of biological assets |
| CN113505824A (en) * | 2019-01-23 | 2021-10-15 | 北京影谱科技股份有限公司 | Judgment updating method and device and face card punching system |
| CN113538771A (en) * | 2021-07-16 | 2021-10-22 | 中国银行股份有限公司 | Identity authentication method and device |
| CN115022030A (en) * | 2022-05-31 | 2022-09-06 | 中国银行股份有限公司 | Bank business handling request processing method and device based on block chain |
| CN116110159A (en) * | 2023-04-13 | 2023-05-12 | 新兴际华集团财务有限公司 | User authentication method, device and medium based on CFCA authentication standard |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101339607A (en) * | 2008-08-15 | 2009-01-07 | 北京中星微电子有限公司 | Human face recognition method and system, human face recognition model training method and system |
| CN101483652A (en) * | 2009-01-10 | 2009-07-15 | 五邑大学 | Living creature characteristic recognition system |
| CN103679158A (en) * | 2013-12-31 | 2014-03-26 | 北京天诚盛业科技有限公司 | Face authentication method and device |
| CN104899579A (en) * | 2015-06-29 | 2015-09-09 | 小米科技有限责任公司 | Face recognition method and face recognition device |
| CN105184238A (en) * | 2015-08-26 | 2015-12-23 | 广西小草信息产业有限责任公司 | Human face recognition method and system |
| CN106228045A (en) * | 2016-07-06 | 2016-12-14 | 吴本刚 | A kind of identification system |
| CN106339702A (en) * | 2016-11-03 | 2017-01-18 | 北京星宇联合投资管理有限公司 | Multi-feature fusion based face identification method |
-
2018
- 2018-01-18 CN CN201810049723.9A patent/CN108429619A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101339607A (en) * | 2008-08-15 | 2009-01-07 | 北京中星微电子有限公司 | Human face recognition method and system, human face recognition model training method and system |
| CN101483652A (en) * | 2009-01-10 | 2009-07-15 | 五邑大学 | Living creature characteristic recognition system |
| CN103679158A (en) * | 2013-12-31 | 2014-03-26 | 北京天诚盛业科技有限公司 | Face authentication method and device |
| CN104899579A (en) * | 2015-06-29 | 2015-09-09 | 小米科技有限责任公司 | Face recognition method and face recognition device |
| CN105184238A (en) * | 2015-08-26 | 2015-12-23 | 广西小草信息产业有限责任公司 | Human face recognition method and system |
| CN106228045A (en) * | 2016-07-06 | 2016-12-14 | 吴本刚 | A kind of identification system |
| CN106339702A (en) * | 2016-11-03 | 2017-01-18 | 北京星宇联合投资管理有限公司 | Multi-feature fusion based face identification method |
Non-Patent Citations (3)
| Title |
|---|
| XIAO-YUAN JING等: "Face and palmprint pixel level fusion and Kernel DCV-RBF classifier forsmall sample biometric recognition", 《PATTERN RECOGNITION》 * |
| 胡航: "《语音信号处理》", 31 July 2009, 哈尔滨工业出版社 * |
| 陈敏: "《认知计算导论》", 31 May 2017, 华中科技大学出版社 * |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109299594A (en) * | 2018-09-04 | 2019-02-01 | 阿里巴巴集团控股有限公司 | Auth method and device |
| CN109614844A (en) * | 2018-10-16 | 2019-04-12 | 阿里巴巴集团控股有限公司 | A kind of link verification method, device and equipment |
| CN109614844B (en) * | 2018-10-16 | 2023-01-24 | 创新先进技术有限公司 | Link verification method, device and equipment |
| CN111104658A (en) * | 2018-10-25 | 2020-05-05 | 北京嘀嘀无限科技发展有限公司 | Registration method and device, authentication method and device |
| CN109977639A (en) * | 2018-10-26 | 2019-07-05 | 招商银行股份有限公司 | Identity identifying method, device and computer readable storage medium |
| CN109583387A (en) * | 2018-11-30 | 2019-04-05 | 龙马智芯（珠海横琴）科技有限公司 | Identity identifying method and device |
| CN109584886A (en) * | 2018-12-04 | 2019-04-05 | 科大讯飞股份有限公司 | Identity identifying method, device, equipment and storage medium based on Application on Voiceprint Recognition |
| CN109858366A (en) * | 2018-12-28 | 2019-06-07 | 龙马智芯（珠海横琴）科技有限公司 | Identity identifying method and device |
| CN113505824B (en) * | 2019-01-23 | 2024-01-09 | 北京影谱科技股份有限公司 | Judgment updating method and device and face card punching system |
| CN113505824A (en) * | 2019-01-23 | 2021-10-15 | 北京影谱科技股份有限公司 | Judgment updating method and device and face card punching system |
| CN110516435A (en) * | 2019-09-02 | 2019-11-29 | 国网电子商务有限公司 | Private key management method and device based on biological characteristics |
| CN110866234A (en) * | 2019-09-29 | 2020-03-06 | 南京大学 | Identity verification system based on multiple biological characteristics |
| CN110866234B (en) * | 2019-09-29 | 2022-06-07 | 南京大学 | Identity verification system based on multiple biological characteristics |
| CN110827453A (en) * | 2019-11-18 | 2020-02-21 | 成都启英泰伦科技有限公司 | Fingerprint and voiceprint double authentication method and authentication system |
| CN110875037A (en) * | 2019-11-19 | 2020-03-10 | 腾讯科技（深圳）有限公司 | Voice data processing method and device and electronic equipment |
| CN111464541A (en) * | 2020-04-01 | 2020-07-28 | 重庆德信建信息技术有限公司 | Electronic government affair multifunctional intelligent hardware terminal based on biological recognition and working method |
| CN112232255A (en) * | 2020-10-26 | 2021-01-15 | 上海鹰瞳医疗科技有限公司 | Identity authentication method and equipment based on multi-mode data |
| CN112669966A (en) * | 2020-12-14 | 2021-04-16 | 北京易华录信息技术股份有限公司 | Behavior analysis system based on monitoring data |
| CN112669511A (en) * | 2020-12-18 | 2021-04-16 | 中用科技有限公司 | User registration and authentication method, system and equipment based on face voiceprint |
| CN112637209A (en) * | 2020-12-23 | 2021-04-09 | 四川虹微技术有限公司 | Security authentication method and device, security registration method and device, and storage medium |
| CN112990943A (en) * | 2021-03-16 | 2021-06-18 | 上海万向区块链股份公司 | Method and system for realizing block chain prediction machine based on image information identification of biological assets |
| CN112990943B (en) * | 2021-03-16 | 2023-04-07 | 上海万向区块链股份公司 | Method and system for realizing block chain prediction machine based on image information identification of biological assets |
| CN113538771A (en) * | 2021-07-16 | 2021-10-22 | 中国银行股份有限公司 | Identity authentication method and device |
| CN115022030A (en) * | 2022-05-31 | 2022-09-06 | 中国银行股份有限公司 | Bank business handling request processing method and device based on block chain |
| CN115022030B (en) * | 2022-05-31 | 2024-04-19 | 中国银行股份有限公司 | Bank business handling request processing method and device based on blockchain |
| CN116110159A (en) * | 2023-04-13 | 2023-05-12 | 新兴际华集团财务有限公司 | User authentication method, device and medium based on CFCA authentication standard |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108429619A (en) | Identity identifying method and system | |
| Ali et al. | Edge-centric multimodal authentication system using encrypted biometric templates | |
| US20210141896A1 (en) | Systems and methods for private authentication with helper networks | |
| JP2022532677A (en) | Identity verification and management system | |
| CN112651841B (en) | Online business handling method, online business handling device, server and computer readable storage medium | |
| CN109120605A (en) | Authentication and account information variation and device | |
| JP7412496B2 (en) | Living body (liveness) detection verification method, living body detection verification system, recording medium, and training method for living body detection verification system | |
| CN107731234A (en) | A kind of method and device of authentication | |
| CN106878344A (en) | A kind of biological characteristic authentication, register method and device | |
| CN108510290A (en) | Customer information amending method, device, computer equipment and storage medium in call | |
| CN110796054A (en) | Certificate authenticity verifying method and device | |
| CN111160928A (en) | Identity verification method and device | |
| CN113886792A (en) | Application method and system of print control instrument combining voiceprint recognition and face recognition | |
| CN110136726A (en) | A kind of estimation method, device, system and the storage medium of voice gender | |
| CN110298240A (en) | A kind of user vehicle recognition methods, device, system and storage medium | |
| CN110324314A (en) | User registering method and device, storage medium, electronic equipment | |
| CN112351047A (en) | Double-engine based voiceprint identity authentication method, device, equipment and storage medium | |
| EP3767872A1 (en) | Method for generating a private key from biometric characteristics | |
| CN111914769A (en) | User validity judging method, device, computer readable storage medium and equipment | |
| CN113362852A (en) | User attribute identification method and device | |
| KR20210018586A (en) | Method and apparatus for identifying video content using biometric features of characters | |
| Saleema et al. | Voice biometrics: the promising future of authentication in the internet of things | |
| CN115906028A (en) | User identity verification method and device and self-service terminal | |
| JP5279007B2 (en) | Verification system, verification method, program, and recording medium | |
| US11418502B2 (en) | Input entry based on user identity validation |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180821 |
|
| RJ01 | Rejection of invention patent application after publication |