CN105426723A - Voiceprint identification, face identification and synchronous in-vivo detection-based identity authentication method and system - Google Patents
Voiceprint identification, face identification and synchronous in-vivo detection-based identity authentication method and system Download PDFInfo
- Publication number
- CN105426723A CN105426723A CN201510811908.5A CN201510811908A CN105426723A CN 105426723 A CN105426723 A CN 105426723A CN 201510811908 A CN201510811908 A CN 201510811908A CN 105426723 A CN105426723 A CN 105426723A
- Authority
- CN
- China
- Prior art keywords
- recognition
- face
- voice signal
- user
- vivo detection
- 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
-
- 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
Abstract
The invention provides a voiceprint identification, face identification and synchronous in-vivo detection-based identity authentication method and system. The method comprises the following steps: obtaining a voice signal and a video signal of a user; carrying out in-vivo detection on the voice signal and the video signal so as to obtain an in-vivo detection result; if the in-vivo detection result is greater than a first set threshold, carrying out voiceprint identification and face identification on the obtained voice signal and video signal of the user; if the voiceprint identification and the face identification succeed, considering that the identity authentication succeeds; and if the voiceprint identification and the face identification fail, considering that the identity authentication fails. Through carrying out in-vivo detection, voiceprint identification and face identification on the obtained voice signal and video signal, the intrusion of illegal users is greatly prevented; and through carrying out multiple detection on the voice signal and video signal of the user, the deficiencies of the single biometric identification technology in the prior art are solved, and then the correctness, security and reliability of the identity authentication are improved.
Description
Technical field
The application relates to computerized information service technology field, particularly relates to a kind of identity identifying method based on Application on Voiceprint Recognition, recognition of face and synchronous In vivo detection and system.
Background technology
Along with the high speed development of mobile Internet and hand-held terminal device as smart mobile phone, panel computer universal, internet security problem becomes increasingly conspicuous.At present, be no matter hardware digital certificate or the E-token dynamic password card of bank, all only accomplished the management to trusted terminal, cannot verify user identity.
In recent years, along with the raising of public's account safety sex consciousness, prior art often adopts the authentication of single creature feature technology realization to account, but recognition performance swarmed in the voice of single creature feature technology to repeated taping, imitation and synthesis is not fine, and is used alone single creature feature verification in the occasion higher to security requirement and there is certain risk.Such as, adopt the checking that face technology realizes identity, but due to the profile of face very unstable, people can produce various expression by face's change; In addition, different observation angles and illumination condition, the visual pattern of face also differs larger.Therefore, when intruder utilizes high pixel image processing to swarm into face identification system, now face identification system have passed checking, but in fact this intruder is disabled user, thus brings potential safety hazard to user.
Summary of the invention
The application provides a kind of identity identifying method based on Application on Voiceprint Recognition, recognition of face and synchronous In vivo detection and system, to solve the problem of the inaccurate and poor stability of identification.
In order to solve the problem, this application discloses a kind of identity identifying method based on Application on Voiceprint Recognition, recognition of face and In vivo detection, comprising: the voice signal and the vision signal that obtain user;
In vivo detection is carried out to described voice signal and vision signal, obtains In vivo detection result;
If described In vivo detection result is greater than the first setting threshold value, then Application on Voiceprint Recognition and recognition of face are carried out to the voice signal and vision signal that obtain user: if Application on Voiceprint Recognition and recognition of face are all passed through, then authentication is passed through, otherwise authentication failure.
Preferably, described In vivo detection comprises speech recognition and lip reading identification.
Preferably, describedly carry out In vivo detection to described voice signal and vision signal, the step obtaining In vivo detection result comprises:
Speech recognition is carried out to described voice signal, obtains the language message that voice signal is corresponding;
Sub-frame processing is carried out to described vision signal, obtains the Hp position in the every two field picture after framing;
Lip reading identification is carried out to the Hp position in described every two field picture, obtains the language message that the lip reading of every two field picture is corresponding;
Alignment algorithm calculated the Similarity value of language message corresponding to the voice signal language message corresponding with lip reading identification, using described Similarity value as In vivo detection result service time.
Preferably, the step that described voice signal and vision signal to obtaining user carries out Application on Voiceprint Recognition and recognition of face comprises:
Application on Voiceprint Recognition is carried out to the voice signal of user, obtains the Application on Voiceprint Recognition marking of voice signal;
To the facial video image of user, carry out framing, obtain face sequential frame image, recognition of face is carried out to described face sequential frame image, mark fusion is carried out to the recognition of face obtained, obtain recognition of face marking;
According to described Application on Voiceprint Recognition marking and recognition of face marking, obtain the judgement score of user's authentication;
If described judgement score is greater than the second setting threshold value, then user's authentication success;
If described judgement score is less than the second setting threshold value, then user's authentication failure.
Preferably, also comprise: use video image acquisition device to obtain user's vision signal, use voice collector to obtain the voice signal of user.
In order to solve the problem, disclosed herein as well is a kind of identity authorization system based on Application on Voiceprint Recognition, recognition of face and In vivo detection, comprising: acquisition module, for obtaining voice signal and the vision signal of user;
In vivo detection module, for carrying out In vivo detection to described voice signal and vision signal, obtains In vivo detection result;
First judge module, if be greater than the first setting threshold value for described In vivo detection result, then carries out Application on Voiceprint Recognition and recognition of face to the voice signal and vision signal that obtain user; If Application on Voiceprint Recognition and recognition of face are all passed through, then authentication is passed through, otherwise authentication failure.
Preferably, described In vivo detection comprises speech recognition and lip reading identification.
Preferably, In vivo detection module comprises:
Sound identification module, for carrying out speech recognition to described voice signal, obtains the language message that voice signal is corresponding;
Dividing frame module, for carrying out sub-frame processing to described vision signal, obtaining the Hp position in the every two field picture after framing;
Lip reading identification module, for carrying out lip reading identification to the Hp position in described every two field picture, obtains the language message that the lip reading identification of every two field picture is corresponding;
Computing module, calculates the Similarity value of language message corresponding to the voice signal language message corresponding with lip reading identification, using described Similarity value as In vivo detection result for alignment algorithm service time.
Preferably, judge module comprises:
Voiceprint identification module, for carrying out Application on Voiceprint Recognition to the voice signal of user, obtains the Application on Voiceprint Recognition marking of voice signal;
Face recognition module, for the facial video image to user, carries out framing, obtains face sequential frame image, carries out recognition of face to described face sequential frame image, carries out mark fusion to the recognition of face obtained, and obtains recognition of face marking;
Judging module, for according to described Application on Voiceprint Recognition marking and recognition of face marking, obtains the judgement score of user's authentication;
Second judge module, if be greater than the second setting threshold value for described judgement score, then user's authentication success;
If described judgement score is less than the second setting threshold value, then user's authentication failure.
Preferably, also comprise: use video image acquisition device to obtain user's vision signal, use voice collector to obtain the voice signal of user.
Compared with prior art, the application comprises following advantage:
The voice signal of acquisition and vision signal are first carried out In vivo detection by the application, when In vivo detection result is less than or equal to the first setting threshold value, then authentication failure, when In vivo detection result is greater than the first setting threshold value, then continue to carry out Application on Voiceprint Recognition and face understanding to the voice signal obtained and vision signal, if Application on Voiceprint Recognition and recognition of face are all passed through, then the authentication of this user is passed through, otherwise authentification failure, by carrying out In vivo detection to the voice signal obtained and vision signal, Application on Voiceprint Recognition and recognition of face, thus prevent swarming into of disabled user greatly, by carrying out Multiple detection to the voice signal of user and vision signal, thus solve the deficiency of prior art single creature feature identification technique, and then improve the accuracy of authentication, safety and reliability.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of a kind of identity identifying method based on Application on Voiceprint Recognition, recognition of face and In vivo detection described in the embodiment of the present application one;
Fig. 2 is the embodiment of the present application 21 kinds based on the process flow diagram of the identity identifying method of Application on Voiceprint Recognition and recognition of face;
Fig. 3 is the process flow diagram of a kind of identity identifying method based on Application on Voiceprint Recognition, recognition of face and In vivo detection described in the embodiment of the present application three;
Fig. 4 is the structural representation of the application's collector;
Fig. 5 is the schematic diagram that language message that the application's voice signal the is corresponding language message corresponding with lip reading identification synchronously detects;
Fig. 6 is the process flow diagram of a kind of identity identifying method based on Application on Voiceprint Recognition, recognition of face and In vivo detection described in the embodiment of the present application four;
Fig. 7 is the structured flowchart of a kind of identity authorization system based on Application on Voiceprint Recognition, recognition of face and In vivo detection described in the embodiment of the present application five.
Embodiment
For enabling above-mentioned purpose, the feature and advantage of the application more become apparent, below in conjunction with the drawings and specific embodiments, the application is described in further detail.
Embodiment one
The application can use online based on the identity identifying method of Application on Voiceprint Recognition, recognition of face and In vivo detection or off-line state uses.
The method of online this authentication of use is the framework based on client and server, user sends authentication request by client to service end, server is verified authentication request, when identity request is verified, service end is to client feedback information acquisition instructions, client receives the information acquisition instruction of service end, and client opens camera and microphone according to this information acquisition instruction.
Service end generates dynamic reminding code, and this dynamic reminding code is sent to client.
Client gathers voice signal and vision signal according to keying.
The voice and video signal collected is sent to server by client, according to the feedback signal of service end, makes corresponding response.
Off-line state can client be used alone again, also can be used alone at server end, does not do concrete restriction to this application.
With reference to Fig. 1, show a kind of identity identifying method based on Application on Voiceprint Recognition, recognition of face and In vivo detection of the application, the method comprises:
Step 101: the voice signal and the vision signal that obtain user.
Service end received speech signal and vision signal, call sound identification module and identify voice signal, obtains the language message that voice signal is corresponding.
Step 102: carry out In vivo detection to described voice signal and vision signal, obtains In vivo detection result.
Step 103: if described In vivo detection result is greater than the first setting threshold value, then perform step 104, if described In vivo detection result is less than or equal to the first setting threshold value, then performs step 105.
If In vivo detection result is greater than the first setting threshold value, then think that the live body of user exists; Otherwise, then authentification failure.
Testing result is fed back to user side by service end; If testing result is not passed through, then service end terminates certification, and to client feedback authentification failure signal, if testing result is passed through, service end proceeds follow-up Application on Voiceprint Recognition and recognition of face.
Wherein, the setting of the first setting threshold value and the second setting threshold value can adopt any appropriate ways to set by those skilled in the art, as artificial experience can be adopted to set threshold value, or set threshold value for the difference value of historical data, the application is not restricted this.
Step 104: carry out Application on Voiceprint Recognition and recognition of face to the voice signal and vision signal that obtain user, if Application on Voiceprint Recognition and recognition of face are all passed through, then authentication is passed through, otherwise authentication failure.
Step 105: the authentication failure of user.
The present embodiment, by the voice signal of acquisition and vision signal are first carried out In vivo detection, when In vivo detection result is less than or equal to the first setting threshold value, then authentication failure, when In vivo detection result is greater than the first setting threshold value, then continue to carry out Application on Voiceprint Recognition and face understanding to the voice signal obtained and vision signal, if Application on Voiceprint Recognition and recognition of face are all passed through, then the authentication of this user is passed through, otherwise authentification failure, by carrying out In vivo detection to the voice signal obtained and vision signal, Application on Voiceprint Recognition and recognition of face, thus prevent swarming into of disabled user greatly, by carrying out Multiple detection to the voice signal of user and vision signal, improve the accuracy of authentication, safety and reliability, thus solve the problem of prior art single creature feature identification technique deficiency.
Embodiment two
With reference to Fig. 2, show a kind of identity identifying method based on Application on Voiceprint Recognition and recognition of face of the application, the method comprises:
Step 201: use collector to gather voice signal and the vision signal of user.
Step 202: Application on Voiceprint Recognition and recognition of face are carried out to described voice signal and vision signal.
Import the voice signal collected and vision signal into Application on Voiceprint Recognition authentication module and recognition of face authentication module respectively, Application on Voiceprint Recognition is carried out to voice signal, recognition of face is carried out to vision signal.
It should be noted that and first can carry out Application on Voiceprint Recognition to voice signal, then recognition of face is carried out to vision signal, also first recognition of face can be carried out to vision signal, then first Application on Voiceprint Recognition is carried out to voice signal, Application on Voiceprint Recognition can also be carried out to voice signal simultaneously, recognition of face is carried out to vision signal, concrete restriction is not done to this application.
Step 203: if Application on Voiceprint Recognition and recognition of face are all passed through, then perform step 204, if do not pass through, performs step 205.
Step 204: authentication is passed through.
Step 205: authentication failure.
The voice signal of acquisition and vision signal are carried out Application on Voiceprint Recognition and face understanding by the application, if Application on Voiceprint Recognition and recognition of face are all passed through, then the authentication of this user is passed through, otherwise authentification failure, by carrying out Application on Voiceprint Recognition and recognition of face to the voice signal obtained and vision signal, thus prevent swarming into of disabled user greatly, by carrying out Multiple detection to the voice signal of user and vision signal, thus solve the deficiency of prior art single creature feature identification technique, and then improve accuracy, the safety and reliability of authentication.
Embodiment three
With reference to Fig. 3, show a kind of identity identifying method based on Application on Voiceprint Recognition, recognition of face and In vivo detection of the application, the method comprises:
Step 301: use collector to gather voice signal and the vision signal of user.
Collector comprises video image acquisition device and voice collector, uses video image acquisition device to obtain user's vision signal, uses voice collector to obtain the voice signal of user.
The structural representation of collector is shown see Fig. 4,
User sends authentication request by client to service end, server is verified authentication request, when identity request is verified, service end is to client feedback information acquisition instructions, client starts video image acquisition device and voice collector, realize the synchronous acquisition of vision signal and voice signal, wherein, voice collector comprises microphone or mobile phone or phone, use microphone or mobile phone or phone to gather voice signal, video image acquisition device gathers face and the lip of user.
Collector mainly comprises: prompting display screen and face display screen, the text string using prompting display screen display server to generate and the recognition result of server feedback.
Face display screen, integration of user interaction functionality is provided, present user's face location in real time, user is facilitated to adjust user's face location and action in real time, collector also can comprise pilot lamp, start button and text prompt display screen as the case may be, and wherein, text prompt display screen is as utility appliance, be not limited to display screen, can also the modes such as voice message be comprised.
Collector is connected with corresponding governor circuit by port, and in practice, user clicks startup button, and governor circuit Received signal strength also starts voice and video collector; After lamp to be instructed and text prompt display screen provide information acquisition prompting, the content of text of user's face display screen prompting; In information acquisition process, server can require that the whole facial image of user can be presented in face display screen in real time; If the face of face display screen display is not full-time, then server can send cue to user, adjusts, and when user's button click, completes video signal collective;
The voice signal collected and vision signal are undertaken being sent to server by authentication interface and carry out authentication by collector, and this authentication interface can complete authentication in this locality.
Step 302: carry out In vivo detection to described voice signal and vision signal, obtains In vivo detection result.
Described In vivo detection comprises speech recognition and lip reading identification.
It should be noted that can to the advanced row speech recognition of voice signal, then the identification of lip reading face is carried out to vision signal, also first the identification of lip reading face can be carried out to vision signal, then speech recognition is carried out to voice signal, speech recognition can also be carried out to voice signal simultaneously, lip reading identification is carried out to vision signal, concrete restriction is not done to this application.
Step 302 comprises following sub-step:
Step 3021: carry out speech recognition to described voice signal, obtains the language message that voice signal is corresponding.
Use the speech language module of training in advance voice signal to be carried out to the language message identifying that acquisition voice signal is corresponding, wherein language model can Hidden Markov HMM-GMM or deep neural network model.
Step 3022: carry out sub-frame processing to described vision signal, obtains the Hp position in the every two field picture after framing;
Step 3023: service end carries out framing to vision signal, catches Hp position in the every two field picture after framing, calls lip reading identification module, obtains the Hp position in the every two field picture after framing.
Sample to catching Hp position and voice signal in the every two field picture after framing, sampling precision can get a two field picture for every 20ms, and long mobile with the window of 10ms, ensures the synchronized sampling of voice signal and vision signal; Hp position method in the every two field picture after framing of catching has a lot, such as follow the tracks of the change in location situation setting key point between every frame Hp position, by calculating the difference change between setting key point, obtain the Hp position in every frame lip image, the application does not limit this.
Step 3024: lip reading identification is carried out to the Hp position in described every two field picture, obtains the language message that the lip reading of every two field picture is corresponding.
The lip reading language module of training in advance is used lip reading to be carried out to the language message identifying that the lip reading of the every two field picture of acquisition is corresponding.
Step 3025: alignment algorithm calculated the Similarity value of language message corresponding to the voice signal language message corresponding with lip reading identification, using described Similarity value as In vivo detection result service time.
See Fig. 5, show the schematic diagram of the synchronous detection of language message corresponding to the application's voice signal language message corresponding with lip reading identification.
The synchronous detection of the language message that the language message that employing time alignment algorithm voice signal is corresponding is corresponding with lip reading identification, the time alignment algorithm of normal employing comprises: dynamic time warping (DynamicTimeWarping, DTW), Viterbi algorithm etc.
Now to be described for numeric string when voice signal, the numeric string sent when voice signal is 8579, language message corresponding with lip reading identification for voice messaging 8579 corresponding in voice signal is compared, calculate the similarity of two groups of recognition results, it should be noted that, voice signal can also be other content of text, does not do concrete restriction to this application.
For dynamic time warping algorithm, calculate the similarity of two groups of recognition result sequences.Such as, carry out speech recognition to voice signal, the speech recognition sequence of acquisition is: S=s
1, s
2..., s
k; K is the frame number of voice signal, and after carrying out lip reading identification to vision signal, the lip reading recognition sequence of acquisition is: V=v
1, v
2..., v
n; N is the sampling frame number of lip reading image; In actual use, K with N can identical also can be different, the two numerical value difference is less.
Due to language feature vector s
kwith lip reading recognition sequence v
ndimension is identical, and therefore, also can adopt Euclidean distance, COS distance etc. to weigh the similarity of the two, dynamic programming algorithm can also be adopted to complete the Similarity Measure of sequence S and v, the core formula of dynamic programming algorithm is:
r(i,j)＝d(s
i,v
j)+min{r(i-1,j-1),r(i-1,j),r(i,j-1)}
Wherein, d (s
i, v
j) be s
iand v
jcurrent distance; By the continuous accumulation of distance, r (i, j) is sequence similarity angle value, and wherein i, j represent the frame position of voice signal and the frame position of vision signal respectively.
Step 303: if described In vivo detection result is greater than the first setting threshold value, then perform step 304.
Step 304: Application on Voiceprint Recognition and recognition of face are carried out to the voice signal and vision signal that obtain user.
Step 305: if Application on Voiceprint Recognition and recognition of face are all passed through, then perform step 306, otherwise perform step 307.
Step 304 comprises following sub-step:
Step 3041: carry out Application on Voiceprint Recognition to the voice signal of user, obtains the Application on Voiceprint Recognition marking of voice signal;
Step 3042: to the facial video image of user, carries out framing, obtains face sequential frame image, carries out recognition of face to described face sequential frame image, carries out mark fusion to the recognition of face obtained, and obtains recognition of face marking.
Recognition of face comprises human face expression, human face posture, human face five-sense-organ change etc.; Such as, face facial expression comprises happiness, misery, sadness, indignation and poker-faced etc.; Human face posture comprises front, left surface, right flank, upper side and downside; Human face five-sense-organ change comprise open one's mouth, shut up, frown, blink, towering nose etc.
Can carry out random sampling to the facial video image collected, carry out mark fusion to the face video pattern after sampling, obtain recognition of face marking, wherein, mark fusion comprises weighted mean.
Step 3043: according to described Application on Voiceprint Recognition marking and recognition of face marking, obtain the judgement score of user's authentication.
wherein, S '
vrepresent Application on Voiceprint Recognition score, S
vrepresent Application on Voiceprint Recognition marking, Rv represents the numerical value corresponding to Application on Voiceprint Recognition error probability.
wherein, S '
frepresent face identification score, S
frepresent sound recognition of face marking, R
frepresent the numerical value corresponding to face identification error probability.
The judgement score S of authentication can be obtained according to formula (1) and (2),
S=α × S '
v+ (1-α) × S '
f(c) wherein, S '
vrepresent Application on Voiceprint Recognition score, S '
frepresent face identification score, the judgement score of S representative capacity certification, α represents interpolation weighting coefficient, generally gets a numerical value between (0,1).
Step 3044: if described judgement score is greater than the second setting threshold value, then user's authentication success.
The authentication success of user, on the contrary illustrate that the vocal print of user and face all come from user, and certification is not passed through, then illustrate that the vocal print of user and face are not all come from user.
Step 3045: if described judgement score is less than the second setting threshold value, then user's authentication failure.
Step 306: authentication is passed through.
Step 307: authentication failure.
The present embodiment, by the voice signal of acquisition and vision signal are first carried out In vivo detection, when In vivo detection result is less than or equal to the first setting threshold value, then authentication failure, when In vivo detection result is greater than the first setting threshold value, then continue to carry out Application on Voiceprint Recognition and face understanding to the voice signal obtained and vision signal, if Application on Voiceprint Recognition and recognition of face are all passed through, then the authentication of this user is passed through, otherwise authentification failure, by carrying out In vivo detection to the voice signal obtained and vision signal, Application on Voiceprint Recognition and recognition of face, thus prevent swarming into of disabled user greatly, by carrying out Multiple detection to the voice signal of user and vision signal, improve the accuracy of authentication, safety and reliability, thus solve the problem of prior art single creature feature identification technique deficiency.
Embodiment four
With reference to Fig. 6, show a kind of identity identifying method based on Application on Voiceprint Recognition, recognition of face and In vivo detection of the application, the method comprises:
Step 601: use collector to gather voice signal and the vision signal of user.
Step 602: carry out In vivo detection and recognition of face to described voice signal and vision signal, obtains comprehensive detection result.
Step 603: if described comprehensive detection result is greater than the 3rd setting threshold value, then perform step 604, if described In vivo detection result is less than or equal to the 3rd setting threshold value, then performs step 607.
Wherein, the setting of the 3rd setting threshold value can adopt any appropriate ways to set by those skilled in the art, and as artificial experience can be adopted to set threshold value, or set threshold value for the difference value of historical data, the application is not restricted this.
Step 604: Application on Voiceprint Recognition and recognition of face are carried out to the voice signal and vision signal that obtain user.
Step 605: if whether Application on Voiceprint Recognition and recognition of face are all passed through, if so, then performs step 606, if not, then performs step 607.
Step 606: authentication is passed through.
Step 607: the authentication failure of user.
The voice signal of acquisition and vision signal are first carried out In vivo detection and Face datection by the application, when In vivo detection result is greater than the first setting threshold value, then continue to carry out Application on Voiceprint Recognition and face understanding to the voice signal obtained and vision signal, if Application on Voiceprint Recognition and recognition of face are all passed through, then the authentication of this user is passed through, otherwise authentification failure, by carrying out In vivo detection to the voice signal obtained and vision signal, Application on Voiceprint Recognition and recognition of face, thus prevent swarming into of disabled user greatly, by carrying out Multiple detection to the voice signal of user and vision signal, thus solve the deficiency of prior art single creature feature identification technique, and then improve the accuracy of authentication, safety and reliability.
Based on the explanation of said method embodiment, present invention also provides the embodiment of a kind of identity authorization system based on Application on Voiceprint Recognition, recognition of face and In vivo detection accordingly, realize the content described in said method embodiment.
Embodiment five
See Fig. 7, showing the structured flowchart of a kind of identity authorization system based on Application on Voiceprint Recognition, recognition of face and In vivo detection in the embodiment of the present application five, specifically can comprising: acquisition module 701, for obtaining voice signal and the vision signal of user.
In vivo detection module 702, for carrying out In vivo detection to described voice signal and vision signal, obtains In vivo detection result.
First judge module 703, if be greater than the first setting threshold value for described In vivo detection result, then carries out Application on Voiceprint Recognition and recognition of face to the voice signal and vision signal that obtain user; If Application on Voiceprint Recognition and recognition of face are all passed through, then authentication is passed through, otherwise authentication failure.
If described In vivo detection result is less than or equal to the first setting threshold value, then user's authentication failure.
Preferably, described In vivo detection comprises speech recognition and lip reading identification.
Preferably, In vivo detection module comprises: sound identification module, for carrying out speech recognition to described voice signal, obtains the language message that voice signal is corresponding;
Dividing frame module, for carrying out sub-frame processing to described vision signal, obtaining the Hp position in the every two field picture after framing;
Lip reading identification module, for carrying out lip reading identification to the Hp position in described every two field picture, obtains the language message that the lip reading identification of every two field picture is corresponding;
Computing module, calculates the Similarity value of language message corresponding to the voice signal language message corresponding with lip reading identification, using described Similarity value as In vivo detection result for alignment algorithm service time.
Preferably, judge module comprises: voiceprint identification module, for carrying out Application on Voiceprint Recognition to the voice signal of user, obtains the Application on Voiceprint Recognition marking of voice signal;
Face recognition module, for the facial video image to user, carries out framing, obtains face sequential frame image, carries out recognition of face to described face sequential frame image, carries out mark fusion to the recognition of face obtained, and obtains recognition of face marking;
Judging module, for according to described Application on Voiceprint Recognition marking and recognition of face marking, obtains the judgement score of user's authentication;
Second judge module, if be greater than the second setting threshold value for described judgement score, then user's authentication success;
If described judgement score is less than the second setting threshold value, then user's authentication failure.
Preferably, also comprise: use video image acquisition device to obtain user's vision signal, use voice collector to obtain the voice signal of user.
The present embodiment, by the voice signal of acquisition and vision signal are first carried out In vivo detection, when In vivo detection result is less than or equal to the first setting threshold value, then authentication failure, when In vivo detection result is greater than the first setting threshold value, then continue to carry out Application on Voiceprint Recognition and face understanding to the voice signal obtained and vision signal, if Application on Voiceprint Recognition and recognition of face are all passed through, then the authentication of this user is passed through, otherwise authentification failure, by carrying out In vivo detection to the voice signal obtained and vision signal, Application on Voiceprint Recognition and recognition of face, thus prevent swarming into of disabled user greatly, by carrying out Multiple detection to the voice signal of user and vision signal, thus solve the deficiency of prior art single creature feature identification technique, and then improve the accuracy of authentication, safety and reliability.
For system embodiment, due to itself and embodiment of the method basic simlarity, so description is fairly simple, relevant part illustrates see the part of embodiment of the method.
Each embodiment in this instructions all adopts the mode of going forward one by one to describe, and what each embodiment stressed is the difference with other embodiments, between each embodiment identical similar part mutually see.
A kind of identity identifying method based on Application on Voiceprint Recognition, recognition of face and In vivo detection above the application provided and system, be described in detail, apply specific case herein to set forth the principle of the application and embodiment, the explanation of above embodiment is just for helping method and the core concept thereof of understanding the application; Meanwhile, for one of ordinary skill in the art, according to the thought of the application, all will change in specific embodiments and applications, in sum, this description should not be construed as the restriction to the application.
Claims (10)
1., based on an identity identifying method for Application on Voiceprint Recognition, recognition of face and In vivo detection, it is characterized in that, comprising:
Obtain voice signal and the vision signal of user;
In vivo detection is carried out to described voice signal and vision signal, obtains In vivo detection result;
If described In vivo detection result is greater than the first setting threshold value, then carry out Application on Voiceprint Recognition and recognition of face to the voice signal and vision signal that obtain user, if Application on Voiceprint Recognition and recognition of face are all passed through, then authentication is passed through, otherwise authentication failure.
2. method according to claim 1, is characterized in that, described In vivo detection comprises speech recognition and lip reading identification.
3. method according to claim 2, is characterized in that, describedly carries out In vivo detection to described voice signal and vision signal, and the step obtaining In vivo detection result comprises:
Speech recognition is carried out to described voice signal, obtains the language message that voice signal is corresponding;
Sub-frame processing is carried out to described vision signal, obtains the Hp position in the every two field picture after framing;
Lip reading identification is carried out to the Hp position in described every two field picture, obtains the language message that the lip reading of every two field picture is corresponding;
Alignment algorithm calculated the Similarity value of language message corresponding to the voice signal language message corresponding with lip reading identification, using described Similarity value as In vivo detection result service time.
4. method according to claim 1, is characterized in that, the step that described voice signal and vision signal to obtaining user carries out Application on Voiceprint Recognition and recognition of face comprises:
Application on Voiceprint Recognition is carried out to the voice signal of user, obtains the Application on Voiceprint Recognition marking of voice signal;
To the facial video image of user, carry out framing, obtain face sequential frame image, recognition of face is carried out to described face sequential frame image, mark fusion is carried out to the recognition of face obtained, obtain recognition of face marking;
According to described Application on Voiceprint Recognition marking and recognition of face marking, obtain the judgement score of user's authentication;
If described judgement score is greater than the second setting threshold value, then user's authentication success;
If described judgement score is less than the second setting threshold value, then user's authentication failure.
5. method according to claim 1, is characterized in that, also comprises: use video image acquisition device to obtain user's vision signal, uses voice collector to obtain the voice signal of user.
6., based on an identity authorization system for Application on Voiceprint Recognition, recognition of face and In vivo detection, it is characterized in that, comprising:
Acquisition module, for obtaining voice signal and the vision signal of user;
In vivo detection module, for carrying out In vivo detection to described voice signal and vision signal, obtains In vivo detection result;
First judge module, if be greater than the first setting threshold value for described In vivo detection result, then carries out Application on Voiceprint Recognition and recognition of face to the voice signal and vision signal that obtain user; If Application on Voiceprint Recognition and recognition of face are all passed through, then authentication is passed through, otherwise authentication failure.
7. system according to claim 6, is characterized in that, described In vivo detection comprises speech recognition and lip reading identification.
8. system according to claim 7, is characterized in that, In vivo detection module comprises:
Sound identification module, for carrying out speech recognition to described voice signal, obtains the language message that voice signal is corresponding;
Dividing frame module, for carrying out sub-frame processing to described vision signal, obtaining the Hp position in the every two field picture after framing;
Lip reading identification module, for carrying out lip reading identification to the Hp position in described every two field picture, obtains the language message that the lip reading identification of every two field picture is corresponding;
Computing module, calculates the Similarity value of language message corresponding to the voice signal language message corresponding with lip reading identification, using described Similarity value as In vivo detection result for alignment algorithm service time.
9. system according to claim 6, is characterized in that, judge module comprises:
Voiceprint identification module, for carrying out Application on Voiceprint Recognition to the voice signal of user, obtains the Application on Voiceprint Recognition marking of voice signal;
Face recognition module, for the facial video image to user, carries out framing, obtains face sequential frame image, carries out recognition of face to described face sequential frame image, carries out mark fusion to the recognition of face obtained, and obtains recognition of face marking;
Judging module, for according to described Application on Voiceprint Recognition marking and recognition of face marking, obtains the judgement score of user's authentication;
Second judge module, if be greater than the second setting threshold value for described judgement score, then user's authentication success;
If described judgement score is less than the second setting threshold value, then user's authentication failure.
10. system according to claim 6, is characterized in that, also comprises: use video image acquisition device to obtain user's vision signal, uses voice collector to obtain the voice signal of user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510811908.5A CN105426723A (en) | 2015-11-20 | 2015-11-20 | Voiceprint identification, face identification and synchronous in-vivo detection-based identity authentication method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510811908.5A CN105426723A (en) | 2015-11-20 | 2015-11-20 | Voiceprint identification, face identification and synchronous in-vivo detection-based identity authentication method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105426723A true CN105426723A (en) | 2016-03-23 |
Family
ID=55504928
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510811908.5A Pending CN105426723A (en) | 2015-11-20 | 2015-11-20 | Voiceprint identification, face identification and synchronous in-vivo detection-based identity authentication method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105426723A (en) |
Cited By (43)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106096519A (en) * | 2016-06-01 | 2016-11-09 | 腾讯科技（深圳）有限公司 | Live body discrimination method and device |
| CN106127156A (en) * | 2016-06-27 | 2016-11-16 | 上海元趣信息技术有限公司 | Robot interactive method based on vocal print and recognition of face |
| CN106355171A (en) * | 2016-11-24 | 2017-01-25 | 深圳凯达通光电科技有限公司 | Video monitoring internetworking system |
| CN106790054A (en) * | 2016-12-20 | 2017-05-31 | 四川长虹电器股份有限公司 | Interactive authentication system and method based on recognition of face and Application on Voiceprint Recognition |
| CN106790260A (en) * | 2017-02-03 | 2017-05-31 | 国政通科技股份有限公司 | A kind of multiple-factor identity identifying method |
| WO2017198014A1 (en) * | 2016-05-19 | 2017-11-23 | 阿里巴巴集团控股有限公司 | Identity authentication method and apparatus |
| CN107864121A (en) * | 2017-09-30 | 2018-03-30 | 上海壹账通金融科技有限公司 | User ID authentication method and application server |
| WO2018058554A1 (en) * | 2016-09-30 | 2018-04-05 | Intel Corporation | Face anti-spoofing using spatial and temporal convolutional neural network analysis |
| CN107894836A (en) * | 2017-11-22 | 2018-04-10 | 河南大学 | Remote sensing image processing and the man-machine interaction method of displaying based on gesture and speech recognition |
| CN108108975A (en) * | 2017-12-12 | 2018-06-01 | 福建联迪商用设备有限公司 | A kind of payment authentication method and terminal based on electrocardiogram and vocal print |
| CN108124488A (en) * | 2017-12-12 | 2018-06-05 | 福建联迪商用设备有限公司 | A kind of payment authentication method and terminal based on face and vocal print |
| WO2018099276A1 (en) * | 2016-11-30 | 2018-06-07 | 阿里巴巴集团控股有限公司 | Identity authentication method and apparatus, and computing device |
| CN108460266A (en) * | 2018-03-22 | 2018-08-28 | 百度在线网络技术（北京）有限公司 | Method and apparatus for authenticating identity |
| CN108510364A (en) * | 2018-03-30 | 2018-09-07 | 杭州法奈昇科技有限公司 | Big data intelligent shopping guide system based on voiceprint identification |
| CN109346089A (en) * | 2018-09-27 | 2019-02-15 | 深圳市声扬科技有限公司 | Living body identity identifying method, device, computer equipment and readable storage medium storing program for executing |
| CN109344588A (en) * | 2018-09-03 | 2019-02-15 | 平安科技（深圳）有限公司 | Safety certifying method and terminal device |
| CN109614881A (en) * | 2018-11-19 | 2019-04-12 | 中国地质大学（武汉） | It can the biometric authentication method of automatic adjusument threshold value, equipment and storage equipment |
| CN109726624A (en) * | 2017-10-31 | 2019-05-07 | 百度（美国）有限责任公司 | Identity identifying method, terminal device and computer readable storage medium |
| CN109829691A (en) * | 2019-01-16 | 2019-05-31 | 北京影谱科技股份有限公司 | C/S punch card method and device based on position and deep learning multi-biological feature |
| CN109840494A (en) * | 2019-01-28 | 2019-06-04 | 北京得意音通技术有限责任公司 | Identity identifying method, device, computer program, storage medium and electronic equipment |
| CN109964226A (en) * | 2016-11-16 | 2019-07-02 | 三星电子株式会社 | Electronic device and its control method |
| CN109987358A (en) * | 2018-01-03 | 2019-07-09 | 谭寅俊 | A kind of transmitting-receiving cabinet having both recycle function and its recycle method |
| CN110009780A (en) * | 2019-03-29 | 2019-07-12 | 深圳市九洲电器有限公司 | A kind of car door unlocking method, server and storage medium based on car networking |
| CN110110513A (en) * | 2019-04-24 | 2019-08-09 | 上海迥灵信息技术有限公司 | Identity identifying method, device and storage medium based on face and vocal print |
| CN110276230A (en) * | 2018-03-14 | 2019-09-24 | 阿里巴巴集团控股有限公司 | The method, apparatus and electronic equipment that user authentication, lip reading identify |
| CN110321756A (en) * | 2018-03-28 | 2019-10-11 | 北京语智科技有限公司 | In vivo detection system and method |
| CN111105792A (en) * | 2018-10-29 | 2020-05-05 | 华为技术有限公司 | Voice interaction processing method and device |
| CN111104825A (en) * | 2018-10-26 | 2020-05-05 | 北京陌陌信息技术有限公司 | Face registry updating method, device, equipment and medium |
| CN111368811A (en) * | 2020-05-26 | 2020-07-03 | 腾讯科技（深圳）有限公司 | Living body detection method, living body detection device, living body detection equipment and storage medium |
| CN111667835A (en) * | 2020-06-01 | 2020-09-15 | 马上消费金融股份有限公司 | Voice recognition method, living body detection method, model training method and device |
| CN111708999A (en) * | 2020-05-22 | 2020-09-25 | 湖南映客互娱网络信息有限公司 | Live broadcast customer service authentication method and system based on image comparison |
| CN111881726A (en) * | 2020-06-15 | 2020-11-03 | 马上消费金融股份有限公司 | Living body detection method and device and storage medium |
| CN111949965A (en) * | 2020-08-12 | 2020-11-17 | 腾讯科技（深圳）有限公司 | Artificial intelligence-based identity verification method, device, medium and electronic equipment |
| CN112053147A (en) * | 2020-09-02 | 2020-12-08 | 中国银行股份有限公司 | Mobile phone bank transfer method and device, storage medium and electronic equipment |
| CN112328999A (en) * | 2021-01-05 | 2021-02-05 | 北京远鉴信息技术有限公司 | Double-recording quality inspection method and device, server and storage medium |
| CN112333545A (en) * | 2019-07-31 | 2021-02-05 | Tcl集团股份有限公司 | Television content recommendation method, system, storage medium and smart television |
| TWI722160B (en) * | 2016-03-30 | 2021-03-21 | 光吉俊二 | Meaning creation device, meaning creation method and meaning creation program |
| CN112560554A (en) * | 2019-09-25 | 2021-03-26 | 北京中关村科金技术有限公司 | Lip language-based living body detection method, device and storage medium |
| CN112597467A (en) * | 2020-12-15 | 2021-04-02 | 中标慧安信息技术股份有限公司 | Multimedia-based resident authentication method and system |
| CN113240428A (en) * | 2021-05-27 | 2021-08-10 | 支付宝(杭州)信息技术有限公司 | Payment processing method and device |
| CN113347608A (en) * | 2021-06-11 | 2021-09-03 | 焦作大学 | Internet of things credibility authentication method for vehicle |
| WO2022142521A1 (en) * | 2020-12-29 | 2022-07-07 | 北京旷视科技有限公司 | Liveness detection method and apparatus, device, and storage medium |
| US11914691B2 (en) | 2018-01-10 | 2024-02-27 | Huawei Technologies Co., Ltd. | Method for recognizing identity in video conference and related device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101697514A (en) * | 2009-10-22 | 2010-04-21 | 中兴通讯股份有限公司 | Method and system for identity authentication |
| CN104361276A (en) * | 2014-11-18 | 2015-02-18 | 新开普电子股份有限公司 | Multi-mode biometric authentication method and multi-mode biometric authentication system |
| CN104376250A (en) * | 2014-12-03 | 2015-02-25 | 优化科技（苏州）有限公司 | Real person living body identity verification method based on sound-type image feature |
| CN104484656A (en) * | 2014-12-26 | 2015-04-01 | 安徽寰智信息科技股份有限公司 | Deep learning-based lip language recognition lip shape model library construction method |
| CN104680375A (en) * | 2015-02-28 | 2015-06-03 | 优化科技（苏州）有限公司 | Identification verifying system for living human body for electronic payment |
| CN104834849A (en) * | 2015-04-14 | 2015-08-12 | 时代亿宝(北京)科技有限公司 | Dual-factor identity authentication method and system based on voiceprint recognition and face recognition |
-
2015
- 2015-11-20 CN CN201510811908.5A patent/CN105426723A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101697514A (en) * | 2009-10-22 | 2010-04-21 | 中兴通讯股份有限公司 | Method and system for identity authentication |
| CN104361276A (en) * | 2014-11-18 | 2015-02-18 | 新开普电子股份有限公司 | Multi-mode biometric authentication method and multi-mode biometric authentication system |
| CN104376250A (en) * | 2014-12-03 | 2015-02-25 | 优化科技（苏州）有限公司 | Real person living body identity verification method based on sound-type image feature |
| CN104484656A (en) * | 2014-12-26 | 2015-04-01 | 安徽寰智信息科技股份有限公司 | Deep learning-based lip language recognition lip shape model library construction method |
| CN104680375A (en) * | 2015-02-28 | 2015-06-03 | 优化科技（苏州）有限公司 | Identification verifying system for living human body for electronic payment |
| CN104834849A (en) * | 2015-04-14 | 2015-08-12 | 时代亿宝(北京)科技有限公司 | Dual-factor identity authentication method and system based on voiceprint recognition and face recognition |
Cited By (56)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI722160B (en) * | 2016-03-30 | 2021-03-21 | 光吉俊二 | Meaning creation device, meaning creation method and meaning creation program |
| RU2738325C2 (en) * | 2016-05-19 | 2020-12-11 | Алибаба Груп Холдинг Лимитед | Method and device for authenticating an individual |
| WO2017198014A1 (en) * | 2016-05-19 | 2017-11-23 | 阿里巴巴集团控股有限公司 | Identity authentication method and apparatus |
| CN107404381A (en) * | 2016-05-19 | 2017-11-28 | 阿里巴巴集团控股有限公司 | A kind of identity identifying method and device |
| US10789343B2 (en) | 2016-05-19 | 2020-09-29 | Alibaba Group Holding Limited | Identity authentication method and apparatus |
| CN106096519A (en) * | 2016-06-01 | 2016-11-09 | 腾讯科技（深圳）有限公司 | Live body discrimination method and device |
| CN106127156A (en) * | 2016-06-27 | 2016-11-16 | 上海元趣信息技术有限公司 | Robot interactive method based on vocal print and recognition of face |
| US10691923B2 (en) | 2016-09-30 | 2020-06-23 | Intel Corporation | Face anti-spoofing using spatial and temporal convolutional neural network analysis |
| WO2018058554A1 (en) * | 2016-09-30 | 2018-04-05 | Intel Corporation | Face anti-spoofing using spatial and temporal convolutional neural network analysis |
| CN109964226A (en) * | 2016-11-16 | 2019-07-02 | 三星电子株式会社 | Electronic device and its control method |
| CN109964226B (en) * | 2016-11-16 | 2023-06-30 | 三星电子株式会社 | Electronic device and control method thereof |
| CN106355171A (en) * | 2016-11-24 | 2017-01-25 | 深圳凯达通光电科技有限公司 | Video monitoring internetworking system |
| WO2018099276A1 (en) * | 2016-11-30 | 2018-06-07 | 阿里巴巴集团控股有限公司 | Identity authentication method and apparatus, and computing device |
| CN106790054A (en) * | 2016-12-20 | 2017-05-31 | 四川长虹电器股份有限公司 | Interactive authentication system and method based on recognition of face and Application on Voiceprint Recognition |
| WO2018113526A1 (en) * | 2016-12-20 | 2018-06-28 | 四川长虹电器股份有限公司 | Face recognition and voiceprint recognition-based interactive authentication system and method |
| CN106790260A (en) * | 2017-02-03 | 2017-05-31 | 国政通科技股份有限公司 | A kind of multiple-factor identity identifying method |
| CN107864121A (en) * | 2017-09-30 | 2018-03-30 | 上海壹账通金融科技有限公司 | User ID authentication method and application server |
| CN109726624A (en) * | 2017-10-31 | 2019-05-07 | 百度（美国）有限责任公司 | Identity identifying method, terminal device and computer readable storage medium |
| CN107894836B (en) * | 2017-11-22 | 2020-10-09 | 河南大学 | Human-computer interaction method for processing and displaying remote sensing image based on gesture and voice recognition |
| CN107894836A (en) * | 2017-11-22 | 2018-04-10 | 河南大学 | Remote sensing image processing and the man-machine interaction method of displaying based on gesture and speech recognition |
| CN108124488A (en) * | 2017-12-12 | 2018-06-05 | 福建联迪商用设备有限公司 | A kind of payment authentication method and terminal based on face and vocal print |
| WO2019113776A1 (en) * | 2017-12-12 | 2019-06-20 | 福建联迪商用设备有限公司 | Face and voiceprint-based payment authentication method, and terminal |
| CN108108975A (en) * | 2017-12-12 | 2018-06-01 | 福建联迪商用设备有限公司 | A kind of payment authentication method and terminal based on electrocardiogram and vocal print |
| CN109987358A (en) * | 2018-01-03 | 2019-07-09 | 谭寅俊 | A kind of transmitting-receiving cabinet having both recycle function and its recycle method |
| US11914691B2 (en) | 2018-01-10 | 2024-02-27 | Huawei Technologies Co., Ltd. | Method for recognizing identity in video conference and related device |
| CN110276230A (en) * | 2018-03-14 | 2019-09-24 | 阿里巴巴集团控股有限公司 | The method, apparatus and electronic equipment that user authentication, lip reading identify |
| CN108460266A (en) * | 2018-03-22 | 2018-08-28 | 百度在线网络技术（北京）有限公司 | Method and apparatus for authenticating identity |
| CN110321756A (en) * | 2018-03-28 | 2019-10-11 | 北京语智科技有限公司 | In vivo detection system and method |
| CN108510364A (en) * | 2018-03-30 | 2018-09-07 | 杭州法奈昇科技有限公司 | Big data intelligent shopping guide system based on voiceprint identification |
| CN109344588A (en) * | 2018-09-03 | 2019-02-15 | 平安科技（深圳）有限公司 | Safety certifying method and terminal device |
| CN109346089A (en) * | 2018-09-27 | 2019-02-15 | 深圳市声扬科技有限公司 | Living body identity identifying method, device, computer equipment and readable storage medium storing program for executing |
| CN111104825A (en) * | 2018-10-26 | 2020-05-05 | 北京陌陌信息技术有限公司 | Face registry updating method, device, equipment and medium |
| CN111105792A (en) * | 2018-10-29 | 2020-05-05 | 华为技术有限公司 | Voice interaction processing method and device |
| US11620995B2 (en) | 2018-10-29 | 2023-04-04 | Huawei Technologies Co., Ltd. | Voice interaction processing method and apparatus |
| CN109614881A (en) * | 2018-11-19 | 2019-04-12 | 中国地质大学（武汉） | It can the biometric authentication method of automatic adjusument threshold value, equipment and storage equipment |
| CN109829691A (en) * | 2019-01-16 | 2019-05-31 | 北京影谱科技股份有限公司 | C/S punch card method and device based on position and deep learning multi-biological feature |
| CN109840494A (en) * | 2019-01-28 | 2019-06-04 | 北京得意音通技术有限责任公司 | Identity identifying method, device, computer program, storage medium and electronic equipment |
| CN110009780A (en) * | 2019-03-29 | 2019-07-12 | 深圳市九洲电器有限公司 | A kind of car door unlocking method, server and storage medium based on car networking |
| CN110110513A (en) * | 2019-04-24 | 2019-08-09 | 上海迥灵信息技术有限公司 | Identity identifying method, device and storage medium based on face and vocal print |
| CN112333545A (en) * | 2019-07-31 | 2021-02-05 | Tcl集团股份有限公司 | Television content recommendation method, system, storage medium and smart television |
| CN112560554A (en) * | 2019-09-25 | 2021-03-26 | 北京中关村科金技术有限公司 | Lip language-based living body detection method, device and storage medium |
| CN111708999A (en) * | 2020-05-22 | 2020-09-25 | 湖南映客互娱网络信息有限公司 | Live broadcast customer service authentication method and system based on image comparison |
| CN111368811B (en) * | 2020-05-26 | 2020-09-18 | 腾讯科技（深圳）有限公司 | Living body detection method, living body detection device, living body detection equipment and storage medium |
| CN111368811A (en) * | 2020-05-26 | 2020-07-03 | 腾讯科技（深圳）有限公司 | Living body detection method, living body detection device, living body detection equipment and storage medium |
| CN111667835A (en) * | 2020-06-01 | 2020-09-15 | 马上消费金融股份有限公司 | Voice recognition method, living body detection method, model training method and device |
| CN111881726A (en) * | 2020-06-15 | 2020-11-03 | 马上消费金融股份有限公司 | Living body detection method and device and storage medium |
| CN111949965A (en) * | 2020-08-12 | 2020-11-17 | 腾讯科技（深圳）有限公司 | Artificial intelligence-based identity verification method, device, medium and electronic equipment |
| CN112053147A (en) * | 2020-09-02 | 2020-12-08 | 中国银行股份有限公司 | Mobile phone bank transfer method and device, storage medium and electronic equipment |
| CN112597467A (en) * | 2020-12-15 | 2021-04-02 | 中标慧安信息技术股份有限公司 | Multimedia-based resident authentication method and system |
| WO2022142521A1 (en) * | 2020-12-29 | 2022-07-07 | 北京旷视科技有限公司 | Liveness detection method and apparatus, device, and storage medium |
| CN112328999A (en) * | 2021-01-05 | 2021-02-05 | 北京远鉴信息技术有限公司 | Double-recording quality inspection method and device, server and storage medium |
| CN112328999B (en) * | 2021-01-05 | 2021-04-06 | 北京远鉴信息技术有限公司 | Double-recording quality inspection method and device, server and storage medium |
| CN113240428A (en) * | 2021-05-27 | 2021-08-10 | 支付宝(杭州)信息技术有限公司 | Payment processing method and device |
| CN113240428B (en) * | 2021-05-27 | 2023-09-08 | 支付宝(杭州)信息技术有限公司 | Payment processing method and device |
| CN113347608A (en) * | 2021-06-11 | 2021-09-03 | 焦作大学 | Internet of things credibility authentication method for vehicle |
| CN113347608B (en) * | 2021-06-11 | 2023-05-12 | 焦作大学 | Internet of things trusted authentication method for vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105426723A (en) | Voiceprint identification, face identification and synchronous in-vivo detection-based identity authentication method and system | |
| US10789343B2 (en) | Identity authentication method and apparatus | |
| US10275672B2 (en) | Method and apparatus for authenticating liveness face, and computer program product thereof | |
| WO2018113526A1 (en) | Face recognition and voiceprint recognition-based interactive authentication system and method | |
| AU2022203880B2 (en) | Methods and systems for determining user liveness and verifying user identities | |
| CN108470169A (en) | Face identification system and method | |
| WO2021135685A1 (en) | Identity authentication method and device | |
| Alsaadi | Study on most popular behavioral biometrics, advantages, disadvantages and recent applications: A review | |
| CN104361276A (en) | Multi-mode biometric authentication method and multi-mode biometric authentication system | |
| US11115408B2 (en) | Methods and systems for determining user liveness and verifying user identities | |
| EP3001343B1 (en) | System and method of enhanced identity recognition incorporating random actions | |
| JP7412496B2 (en) | Living body (liveness) detection verification method, living body detection verification system, recording medium, and training method for living body detection verification system | |
| CN208351494U (en) | Face identification system | |
| US20230306792A1 (en) | Spoof Detection Based on Challenge Response Analysis | |
| US11216648B2 (en) | Method and device for facial image recognition | |
| US11715330B2 (en) | Liveness detection in an interactive video session | |
| CN109034014A (en) | Biopsy method based on the micro- Expression Recognition of face | |
| KR102581415B1 (en) | UBT system using face contour recognition AI to prevent the cheating behaviour and method thereof | |
| CN110516426A (en) | Identity identifying method, certification terminal, device and readable storage medium storing program for executing | |
| CN104915661A (en) | Intelligent dynamic human face encryption recognition system | |
| CN106407783A (en) | An online verification method and system | |
| US20240086508A1 (en) | System and method for facilitating multi-factor face authentication of user | |
| US11132429B2 (en) | Authenticating a user subvocalizing a displayed text | |
| CN114973058A (en) | Surface labeling method and device, electronic equipment and storage medium | |
| GORIPARTHI et al. | ARM Based Smart Home Embedded System for Voice And Face Recognition |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160323 |