CN104376250A - Real person living body identity verification method based on sound-type image feature - Google Patents
Real person living body identity verification method based on sound-type image feature Download PDFInfo
- Publication number
- CN104376250A CN104376250A CN201410723798.2A CN201410723798A CN104376250A CN 104376250 A CN104376250 A CN 104376250A CN 201410723798 A CN201410723798 A CN 201410723798A CN 104376250 A CN104376250 A CN 104376250A
- Authority
- CN
- China
- Prior art keywords
- lip
- operator
- face
- live body
- voice
- 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
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000012795 verification Methods 0.000 title abstract description 7
- 238000000605 extraction Methods 0.000 claims description 14
- 239000000284 extract Substances 0.000 claims description 12
- 230000001815 facial effect Effects 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 description 9
- 238000009432 framing Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 235000021472 generally recognized as safe Nutrition 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 230000001755 vocal effect Effects 0.000 description 2
- 206010011878 Deafness Diseases 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011840 criminal investigation Methods 0.000 description 1
- 238000012942 design verification Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000013011 mating Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000013138 pruning Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Computer Security & Cryptography (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Computer Hardware Design (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Acoustics & Sound (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a real person living body identity verification method. The method comprises the steps that a face recognition database, a voiceprint recognition database, a lip recognition database and a voice recognition database are set; the video and the audio of reading random preset content of an operator are collected; according to the video, a face image is extracted and compared with data in the face recognition database, or/and according to the audio, voiceprints are extracted and compared with data in the voiceprint recognition database, and if comparison is successful, the operator is himself; according to the video, a continuous lip image is extracted and compared with data in the lip recognition database, the lip semantics is recognized and compared with the random preset content, or/and according to the audio, voice is extracted and compared with data in the voice recognition database, the recognized semantics and the random preset content are compared, and if comparison is successful, the operator is an intelligent living body; if the operator is himself and the intelligent living body, identity verification is successful. The himself identity and the intelligent living body identity are verified at the same time, direct contact with the operator is not needed, and therefore the method is convenient to apply and popularize.
Description
Technical field
The present invention relates to a kind of auth method, particularly relate to a kind of based on the true man live body auth method of figure as feature.
Background technology
Along with the fast development of infotech and network technology, the demand of people to identity recognizing technology gets more and more, also more and more stricter to the requirement of its safe reliability.Identity recognizing technology based on conventional cipher certification has exposed many weak points in actual information network application, and the identity recognizing technology distinguished based on biological characteristic is also increasingly mature in recent years and show great superiority in actual applications, but the single recognition of face of tradition, Application on Voiceprint Recognition and fingerprint recognition can only the feature of underwriter can effectively be verified, can not ensure that operator is me, and cause utilizing photo, the case of fingerprint film and recording crime is often reported in media.
This identity recognizing technology based on single creature feature is faked, is used video recording recording etc. that this technical security is reduced greatly due to himself limitation such as sensor noise and identification photographs, and practical application gets up to have difficulties.
Therefore, be necessary to provide a kind of new true man's live body auth method to solve the problems referred to above.
Summary of the invention
The object of the present invention is to provide a kind ofly can merge multiple biological characteristic simultaneous verification and live body identity, do not need directly to contact with operator based on the true man live body auth method of figure as feature.
To achieve these goals, the technical solution adopted in the present invention is as follows:
Based on the true man live body auth method of figure as feature, comprise the following steps:
Face recognition database, Application on Voiceprint Recognition database, lipreading recognition database and speech recognition database are set;
Video information when acquisition operations person reads preset content and audio-frequency information;
Compare or/and compare according to the data in described audio information voiceprint and Application on Voiceprint Recognition database according to the data that described video information is extracted in human face image information and face recognition database, if comparison success, operator is me, otherwise operator is not me;
Compare according to the data that described video information is extracted in lip image information and lip reading identification database, identify lip reading semanteme, lip reading is semantic to be compared or/and compare according to the data in described audio information voice messaging and speech recognition database with random preset content, identify voice semanteme, voice are semantic to be compared with random preset content; If comparison success, operator is intelligent live body, otherwise operator is not intelligent live body;
If operator is I and live body, authentication success, namely this operator is my true man's intelligence live body really; Otherwise authentication failure.
Preferably, described recognition of face mainly comprises the following steps: Face datection, face tracking, image quality analysis, facial image pre-service, face characteristic extract and face alignment identification.
Preferably, described Application on Voiceprint Recognition mainly comprises the following steps: voice pre-service, the characteristic parameter extracting each frame voice signal and use sorter are classified to the parameter extracted, and identify speaker.
Preferably, described lipreading recognition mainly comprises the following steps: Image semantic classification, lip location, lip outline extraction, the extraction of lip Contour extraction, lip contour feature, tagsort and lip matching identification.
Preferably, described speech recognition mainly comprises the following steps: voice pre-service, speech feature extraction, feature mode identification and output voice identification result.
Preferably, described random preset content comprises voice messaging or Word message, and described Word message comprises any one character in word, letter and number or combination in any character.
Compared with prior art, the present invention is based on figure to be as the beneficial effect of true man's live body auth method of feature: the present invention can adopt recognition of face or audio identification to judge that whether operator is for me, lipreading recognition or speech recognition is adopted to judge whether operator is live body, namely merge multiple biological characteristic to verify true man's live body identity, recognition efficiency is high; Identifying does not need directly to contact with operator, not by the restriction of extraneous factor, acceptant, easy to utilize, strong adaptability; Low to hardware requirement, be easy to use on various terminal device; There are video information and audio-frequency information, follow the trail of invasive ability strong.
Accompanying drawing explanation
Fig. 1 is the FB(flow block) of recognition of face of the present invention;
Fig. 2 is the FB(flow block) of Application on Voiceprint Recognition of the present invention;
Fig. 3 is the FB(flow block) of lipreading recognition of the present invention;
Fig. 4 is the FB(flow block) of speech recognition of the present invention;
Fig. 5 is the workflow diagram of application terminal of the present invention.
Embodiment
Below in conjunction with specific embodiment, the present invention is described further.
Based on the true man live body auth method of figure as feature, comprise the following steps:
Face recognition database, Application on Voiceprint Recognition database, lipreading recognition database and speech recognition database are set;
Video information when acquisition operations person reads preset content and audio-frequency information, described random preset content comprises voice messaging or Word message, and described Word message comprises any one character in word, letter and number or combination in any character;
Compare or/and compare according to the data in described audio information voiceprint and Application on Voiceprint Recognition database according to the data that described video information is extracted in human face image information and face recognition database, if comparison success, operator is me, otherwise operator is not me;
Compare according to the data that described video information is extracted in lip image information and lip reading identification database, identify lip reading semanteme, lip reading is semantic to be compared or/and compare according to the data in described audio information voice messaging and speech recognition database with random preset content, identify voice semanteme, voice are semantic to be compared with random preset content; If comparison success, operator is intelligent live body, otherwise operator is not intelligent live body;
If operator is I and live body, authentication success, namely this operator is my true man's intelligence live body really; Otherwise authentication failure.
Refer to shown in Fig. 1, recognition of face mainly comprises the following steps: Face datection, face tracking, image quality analysis, facial image pre-service, face characteristic extract and face alignment identification.Facial image pre-service is done facial image the methods such as color range, contrast, color balance, sharpening, noise reduction, deblurring, histogram equalization, super resolution and is strengthened.Face datection algorithm extracts the feature of face, rear use adboost cascade classifier is classified to it, extract the face position of face, image tracking algorithm is used to the face extracted, face is followed the tracks of, guarantee it is same people, and preferred several high-quality pictures, from human face photo, extract the feature being used for recognition of face, and with principal component analysis algorithm, dimension-reduction treatment is carried out to data, form face feature vector, use sorting algorithm to identify face identity.
Refer to shown in Fig. 2, Application on Voiceprint Recognition mainly comprises the following steps: voice pre-service, the characteristic parameter extracting each frame voice signal and use sorter are classified to the parameter extracted, and identify speaker.Voice pre-service carries out framing to the speech-sound data sequence (pcm stream) of input, calculate the cumlative energy of each frame speech data, extract the speech data with information, to there is the speech data of information by the process of Hi-pass filter pre-emphasis, voice signal after process is divided into short time interval one by one, and then every frame is multiplied by window function, to increase the continuity of every frame left end and right-hand member, the frequency spectrum obtaining each frame is converted to each frame signal after framing windowing, the proper vector of the voice of every section is extracted according to frequency spectrum, there is proper vector according to deep neural network or other sorters and template base identification vocal print identity.
Refer to shown in Fig. 3, lipreading recognition mainly comprises the following steps: Image semantic classification, lip location, lip outline extraction, the extraction of lip Contour extraction, lip contour feature, tagsort and lip matching identification.Lip location is in the facial image region of above-mentioned Face datection location, lip and the colour of skin is distinguished according to the priori of lip site color, and strengthen lip region color, utilize binary image to complete the coarse positioning of lip, then realize lip fine positioning in conjunction with lip color model.It is by morphology processing that lip outline extracts, and extracts the initial curve of lip, then by extracting the contour curve of lip based on contour extraction method.Lip Contour extraction adopts optical flow method or meanshift to follow the tracks of sequence image, and next frame initial profile is predicted, extract the feature point set vector of lip profile, according to eigenvector and training template base, utilize artificial intelligence sorting algorithm to carry out the identification of lip reading.
Refer to shown in Fig. 4, speech recognition mainly comprises the following steps: voice pre-service, speech feature extraction, feature mode identification and output voice identification result.Extract the characteristic parameter of each frame voice signal, use sorter to classify to the parameter extracted, identify speaker.Voice pre-service carries out framing to the voice of input, calculate the cumlative energy of each frame speech data, extract the speech data with information, hidden Markov model is used to build a state network, the path of mating most with sound is found from state network, structure word level network, is launched into phoneme network and state network.Then in state network, an optimal path is searched for, the maximum probability between these paths and voice.Using the searching algorithm calculating dynamic programming beta pruning, for finding global optimum path, identifying current speech content according to state transfer.
The corresponding feature of the present invention and existing biological identification technology is as shown in the table:
According to upper table, the present invention has the following advantages relative to existing biological identification technology:
1. adopt contactless recognition technology, easy to use;
2. can use under special circumstances, such as deaf-mute can use lipreading recognition and recognition of face, and face infringement personnel can use Application on Voiceprint Recognition and voice recognition, so almost general to anyone, not by the restriction of extraneous factor, and strong adaptability;
3. pair hardware requirement is low, easily uses on various terminal device, easy to utilize;
4. there are video information and audio-frequency information, follow the trail of invasive ability strong;
5. merge multiple biological characteristic and verify true man's live body identity, can the use of these features of flexible configuration, solve the problem that the identification of existing single creature feature can not ensure true man, live body, improve the reliability of true man's live body checking;
6. the checking of intelligent live body ensure that live body carries out authentication when reason, effectively can reduce the possibility that the financial swindling case in similar drunk, insanity situation in the past occurs.
The present invention can be widely used in mobile terminal and control system, enters the station the public safety, safety monitoring, anti-terrorism criminal investigation etc. of checking, the automatic clearance system of border inspection station and public security automatically in automatically enter the station checking, airport of the Self-service card sender of such as mobile terminal payment system, bank, ATM in bank, railway station.Mobile terminal is responsible for the input of shooting and audio frequency, and the pre-service to recognition of face, Application on Voiceprint Recognition, lip reading identification and speech recognition, the above-mentioned recognition feature extracted is transferred to background server, and background server carries out identification checking to above-mentioned biological characteristic one by one by artificial intelligence recognizer.
When embody rule, the present invention can flexible design verification mode, can arrange checking rank voluntarily according to customer requirement, checking rank be divided into Generally Recognized as safe to verify grade, intermediate security checking grade and these three kinds of grades of high safety verification grade, the standard be proved to be successful of each grade is as follows:
Generally Recognized as safe checking grade: simultaneously by recognition of face and lip reading identification, or simultaneously by recognition of face and voice recognition, or simultaneously by Application on Voiceprint Recognition and lip reading identification, or simultaneously by Application on Voiceprint Recognition and voice recognition.
Intermediate security checking grade: simultaneously by recognition of face, Application on Voiceprint Recognition and lip reading identification, or simultaneously by recognition of face, Application on Voiceprint Recognition and voice recognition, or simultaneously by recognition of face, lip reading identification and voice recognition, or simultaneously by Application on Voiceprint Recognition, lip reading identification and voice recognition.
High safety verification grade: simultaneously by recognition of face, lip reading identification, Application on Voiceprint Recognition and voice recognition.
Please refer to shown in Fig. 5, the true man live body auth method of figure as feature is the present invention is based on for better illustrating, true man's auth method of the present invention be applied to there is high safety verification grade terminal on, described terminal configuration has the camera for recorded video and the microphone for recording audio (MIC), and the specific works flow process of terminal is as follows:
A prepares: opening program;
B starts camera and microphone: the camera and the microphone that start terminal device, enter and prepare shooting and recording voice;
The random text importing of C: read aloud at voice and screen displaying character and show the word that will read;
D reads above-mentioned word: according to the display word of upper step voice and screen, read these words, and video read in camera record, microphone record audio;
E identifies: system detects face in video, and identifies it, if not operator, then jumps out checking; Or according to the change of operator's shape of the mouth as one speaks in video, whether correctly analyze lip reading, determine whether live body, if lip reading is incorrect, jump out checking;
F intelligence vivo identification: according to the audio file of operator, whether the vocal print analyzing this operator is he or she, if not operator, jumps out checking; Or according to the audio file of operator, the sound bite of intercept operation person, whether the voice messaging of analysis operation person is consistent with random word, inconsistent, and playback is described, is not the live body with intelligence, jumps out checking.
Schematically above be described the present invention and embodiment thereof, this description does not have restricted, and also just one of the embodiments of the present invention shown in accompanying drawing, actual structure is not limited thereto.So, if those of ordinary skill in the art enlightens by it, when not departing from the invention aim, designing the frame mode similar to this technical scheme and embodiment without creationary, all should protection scope of the present invention be belonged to.
Claims (6)
1., based on the true man live body auth method of figure as feature, it is characterized in that, comprise the following steps:
Face recognition database, Application on Voiceprint Recognition database, lipreading recognition database and speech recognition database are set;
Video information when acquisition operations person reads random preset content and audio-frequency information;
Compare or/and compare according to the data in described audio information voiceprint and Application on Voiceprint Recognition database according to the data that described video information is extracted in human face image information and face recognition database, if comparison success, operator is me, otherwise operator is not me;
Compare according to the data that described video information is extracted in lip image information and lip reading identification database, identify lip reading semanteme, lip reading is semantic to be compared or/and compare according to the data in described audio information voice messaging and speech recognition database with random preset content, identify voice semanteme, voice are semantic to be compared with random preset content; If comparison success, operator is intelligent live body, otherwise operator is not intelligent live body;
If operator is I and intelligent live body, authentication success, namely this operator is my true man's intelligence live body really; Otherwise authentication failure.
2. as claimed in claim 1 based on true man's live body auth method of figure as feature, it is characterized in that, described recognition of face mainly comprises the following steps: Face datection, face tracking, image quality analysis, facial image pre-service, face characteristic extract and face alignment identification.
3. as claimed in claim 1 based on true man's live body auth method of figure as feature, it is characterized in that, described Application on Voiceprint Recognition mainly comprises the following steps: voice pre-service, the characteristic parameter extracting each frame voice signal and use sorter are classified to the parameter extracted, and identify speaker.
4. as claimed in claim 1 based on true man's live body auth method of figure as feature, it is characterized in that, described lipreading recognition mainly comprises the following steps: Image semantic classification, lip location, lip outline extraction, the extraction of lip Contour extraction, lip contour feature, tagsort and lip matching identification.
5. as claimed in claim 1 based on the true man live body auth method of figure as feature, it is characterized in that, described speech recognition mainly comprises the following steps: voice pre-service, speech feature extraction, feature mode identification and output voice identification result.
6. as claimed in claim 1 based on true man's live body auth method of figure as feature, it is characterized in that, described random preset content comprises voice messaging or Word message, and described Word message comprises any one character in word, letter and number or combination in any character.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410723798.2A CN104376250A (en) | 2014-12-03 | 2014-12-03 | Real person living body identity verification method based on sound-type image feature |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410723798.2A CN104376250A (en) | 2014-12-03 | 2014-12-03 | Real person living body identity verification method based on sound-type image feature |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104376250A true CN104376250A (en) | 2015-02-25 |
Family
ID=52555152
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410723798.2A Pending CN104376250A (en) | 2014-12-03 | 2014-12-03 | Real person living body identity verification method based on sound-type image feature |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104376250A (en) |
Cited By (55)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN104834900A (en) * | 2015-04-15 | 2015-08-12 | 常州飞寻视讯信息科技有限公司 | Method and system for vivo detection in combination with acoustic image signal |
| CN104850827A (en) * | 2015-04-23 | 2015-08-19 | 小米科技有限责任公司 | Fingerprint identification method and apparatus |
| CN105119872A (en) * | 2015-02-13 | 2015-12-02 | 腾讯科技（深圳）有限公司 | Identity verification method, client, and service platform |
| CN105426723A (en) * | 2015-11-20 | 2016-03-23 | 北京得意音通技术有限责任公司 | Voiceprint identification, face identification and synchronous in-vivo detection-based identity authentication method and system |
| CN105518708A (en) * | 2015-04-29 | 2016-04-20 | 北京旷视科技有限公司 | Method and equipment for verifying living human face, and computer program product |
| CN105528578A (en) * | 2015-12-04 | 2016-04-27 | 国家电网公司 | Online training monitoring method based on sound image process tracking |
| CN105577664A (en) * | 2015-12-22 | 2016-05-11 | 深圳前海微众银行股份有限公司 | Cipher reset method and system, client and server |
| CN106028129A (en) * | 2016-06-16 | 2016-10-12 | 深圳Tcl数字技术有限公司 | Method and system for sharing television programs among televisions |
| WO2016173453A1 (en) * | 2015-04-30 | 2016-11-03 | 腾讯科技（深圳）有限公司 | Living body identification method, information generation method and terminal |
| CN106096519A (en) * | 2016-06-01 | 2016-11-09 | 腾讯科技（深圳）有限公司 | Live body discrimination method and device |
| CN106098069A (en) * | 2016-06-21 | 2016-11-09 | 佛山科学技术学院 | A kind of identity identifying method and terminal unit |
| WO2016197765A1 (en) * | 2015-06-11 | 2016-12-15 | 腾讯科技（深圳）有限公司 | Human face recognition method and recognition system |
| CN106407783A (en) * | 2016-09-23 | 2017-02-15 | 武汉必腾移动科技有限责任公司 | An online verification method and system |
| CN106529379A (en) * | 2015-09-15 | 2017-03-22 | 阿里巴巴集团控股有限公司 | Method and device for recognizing living body |
| WO2017059700A1 (en) * | 2015-10-09 | 2017-04-13 | 腾讯科技（深圳）有限公司 | Identity authentication method and apparatus |
| CN106570369A (en) * | 2015-10-08 | 2017-04-19 | 三竹资讯股份有限公司 | video identity confirming device and method |
| CN106599764A (en) * | 2015-10-20 | 2017-04-26 | 深圳市商汤科技有限公司 | Lip-shape-characteristic-based living body determination method and equipment |
| CN106599660A (en) * | 2016-12-02 | 2017-04-26 | 宇龙计算机通信科技(深圳)有限公司 | Terminal safety verification method and terminal safety verification device |
| CN106683661A (en) * | 2015-11-05 | 2017-05-17 | 阿里巴巴集团控股有限公司 | Role separation method and device based on voice |
| CN106709804A (en) * | 2015-11-16 | 2017-05-24 | 优化科技（苏州）有限公司 | Interactive wealth planning consulting robot system |
| CN106911630A (en) * | 2015-12-22 | 2017-06-30 | 上海仪电数字技术股份有限公司 | Terminal and the authentication method and system of identity identifying method, terminal and authentication center |
| CN107087133A (en) * | 2017-03-24 | 2017-08-22 | 宇龙计算机通信科技(深圳)有限公司 | A kind of method of controlling security and terminal device |
| CN107437019A (en) * | 2017-07-31 | 2017-12-05 | 广东欧珀移动通信有限公司 | The auth method and device of lip reading identification |
| CN107819807A (en) * | 2016-09-14 | 2018-03-20 | 腾讯科技（深圳）有限公司 | A kind of Information Authentication method, apparatus and equipment |
| CN108306886A (en) * | 2018-02-01 | 2018-07-20 | 深圳市腾讯计算机系统有限公司 | A kind of auth method, device and storage medium |
| WO2018137426A1 (en) * | 2017-01-24 | 2018-08-02 | 中兴通讯股份有限公司 | Method and apparatus for recognizing voice information of user |
| CN108399395A (en) * | 2018-03-13 | 2018-08-14 | 成都数智凌云科技有限公司 | The compound identity identifying method of voice and face based on end-to-end deep neural network |
| CN108595233A (en) * | 2018-03-09 | 2018-09-28 | 福州米鱼信息科技有限公司 | A kind of electronic evidence acquisition method and system based on voice prompt |
| CN108764010A (en) * | 2018-03-23 | 2018-11-06 | 姜涵予 | Emotional state determines method and device |
| CN109087651A (en) * | 2018-09-05 | 2018-12-25 | 广州势必可赢网络科技有限公司 | A kind of vocal print identification method, system and equipment based on video and sound spectrograph |
| CN109146480A (en) * | 2018-08-23 | 2019-01-04 | 交通银行股份有限公司 | A kind of method of payment, device, electronic equipment and storage medium |
| CN109624925A (en) * | 2018-12-10 | 2019-04-16 | 百度在线网络技术（北京）有限公司 | Automobile control method, device, equipment and storage medium |
| 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 |
| CN109910818A (en) * | 2019-02-15 | 2019-06-21 | 东华大学 | A kind of VATS Vehicle Anti-Theft System based on human body multiple features fusion identification |
| CN110032924A (en) * | 2019-02-21 | 2019-07-19 | 百度在线网络技术（北京）有限公司 | Recognition of face biopsy method, terminal device, storage medium and electronic equipment |
| CN110082723A (en) * | 2019-05-16 | 2019-08-02 | 浙江大华技术股份有限公司 | A kind of sound localization method, device, equipment and storage medium |
| CN110198381A (en) * | 2019-04-28 | 2019-09-03 | 北京蓦然认知科技有限公司 | A kind of method and device of identification AI incoming call |
| CN110222719A (en) * | 2019-05-10 | 2019-09-10 | 中国科学院计算技术研究所 | A kind of character recognition method and system based on multiframe audio-video converged network |
| CN110851101A (en) * | 2015-03-08 | 2020-02-28 | 苹果公司 | Virtual assistant activation |
| CN111339806A (en) * | 2018-12-19 | 2020-06-26 | 马上消费金融股份有限公司 | Training method of lip language recognition model, living body recognition method and device |
| CN111684459A (en) * | 2019-07-18 | 2020-09-18 | 深圳海付移通科技有限公司 | Identity authentication method, terminal equipment and storage medium |
| CN111684444A (en) * | 2019-07-18 | 2020-09-18 | 深圳海付移通科技有限公司 | Identity authentication method, terminal equipment and storage medium |
| CN111967293A (en) * | 2020-06-22 | 2020-11-20 | 云知声智能科技股份有限公司 | Face authentication method and system combining voiceprint recognition and attention detection |
| CN112132996A (en) * | 2019-06-05 | 2020-12-25 | Tcl集团股份有限公司 | Door lock control method, mobile terminal, door control terminal 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 |
| CN112507311A (en) * | 2020-12-10 | 2021-03-16 | 东南大学 | High-security identity verification method based on multi-mode feature fusion |
| CN112614333A (en) * | 2020-12-17 | 2021-04-06 | 杭州当贝网络科技有限公司 | Remote controller retrieving method and system |
| CN113032758A (en) * | 2021-03-26 | 2021-06-25 | 平安银行股份有限公司 | Video question-answer flow identity identification method, device, equipment and storage medium |
| 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 |
| TWI801647B (en) * | 2019-08-07 | 2023-05-11 | 華南商業銀行股份有限公司 | Identity verification device and method based on dynamic image |
| CN116405635A (en) * | 2023-06-02 | 2023-07-07 | 山东正中信息技术股份有限公司 | Multi-mode conference recording method and system based on edge calculation |
| CN116938611A (en) * | 2023-09-19 | 2023-10-24 | 苏州宏存芯捷科技有限公司 | Information verification method and system based on artificial intelligence |
| TWI822646B (en) * | 2019-08-07 | 2023-11-11 | 華南商業銀行股份有限公司 | Identity verification device and method based on dynamic lip image |
| US11853647B2 (en) | 2015-12-23 | 2023-12-26 | Apple Inc. | Proactive assistance based on dialog communication between devices |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090018831A1 (en) * | 2005-01-28 | 2009-01-15 | Kyocera Corporation | Speech Recognition Apparatus and Speech Recognition Method |
| CN102298443A (en) * | 2011-06-24 | 2011-12-28 | 华南理工大学 | Smart home voice control system combined with video channel and control method thereof |
| CN103324918A (en) * | 2013-06-25 | 2013-09-25 | 浙江中烟工业有限责任公司 | Identity authentication method with face identification and lip identification matched |
-
2014
- 2014-12-03 CN CN201410723798.2A patent/CN104376250A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090018831A1 (en) * | 2005-01-28 | 2009-01-15 | Kyocera Corporation | Speech Recognition Apparatus and Speech Recognition Method |
| CN102298443A (en) * | 2011-06-24 | 2011-12-28 | 华南理工大学 | Smart home voice control system combined with video channel and control method thereof |
| CN103324918A (en) * | 2013-06-25 | 2013-09-25 | 浙江中烟工业有限责任公司 | Identity authentication method with face identification and lip identification matched |
Cited By (79)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105119872A (en) * | 2015-02-13 | 2015-12-02 | 腾讯科技（深圳）有限公司 | Identity verification method, client, and service platform |
| 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 |
| CN110851101B (en) * | 2015-03-08 | 2023-08-08 | 苹果公司 | Virtual assistant activation |
| CN110851101A (en) * | 2015-03-08 | 2020-02-28 | 苹果公司 | Virtual assistant activation |
| US11842734B2 (en) | 2015-03-08 | 2023-12-12 | Apple Inc. | Virtual assistant activation |
| CN104834900A (en) * | 2015-04-15 | 2015-08-12 | 常州飞寻视讯信息科技有限公司 | Method and system for vivo detection in combination with acoustic image signal |
| CN104834900B (en) * | 2015-04-15 | 2017-12-19 | 常州飞寻视讯信息科技有限公司 | A kind of method and system combined audio-visual signal and carry out In vivo detection |
| CN104850827A (en) * | 2015-04-23 | 2015-08-19 | 小米科技有限责任公司 | Fingerprint identification method and apparatus |
| CN105518708A (en) * | 2015-04-29 | 2016-04-20 | 北京旷视科技有限公司 | Method and equipment for verifying living human face, and computer program product |
| US10275672B2 (en) | 2015-04-29 | 2019-04-30 | Beijing Kuangshi Technology Co., Ltd. | Method and apparatus for authenticating liveness face, and computer program product thereof |
| WO2016172872A1 (en) * | 2015-04-29 | 2016-11-03 | 北京旷视科技有限公司 | Method and device for verifying real human face, and computer program product |
| WO2016173453A1 (en) * | 2015-04-30 | 2016-11-03 | 腾讯科技（深圳）有限公司 | Living body identification method, information generation method and terminal |
| CN106203235A (en) * | 2015-04-30 | 2016-12-07 | 腾讯科技（深圳）有限公司 | Live body discrimination method and device |
| US10607066B2 (en) | 2015-04-30 | 2020-03-31 | Tencent Technology (Shenzhen) Company Limited | Living body identification method, information generation method, and terminal |
| WO2016197765A1 (en) * | 2015-06-11 | 2016-12-15 | 腾讯科技（深圳）有限公司 | Human face recognition method and recognition system |
| US10650259B2 (en) | 2015-06-11 | 2020-05-12 | Tencent Technology (Shenzhen) Company Limited | Human face recognition method and recognition system based on lip movement information and voice information |
| CN106529379A (en) * | 2015-09-15 | 2017-03-22 | 阿里巴巴集团控股有限公司 | Method and device for recognizing living body |
| CN106570369A (en) * | 2015-10-08 | 2017-04-19 | 三竹资讯股份有限公司 | video identity confirming device and method |
| US10701066B2 (en) | 2015-10-09 | 2020-06-30 | Tencent Technology (Shenzhen) Company Limited | Identity authentication method and apparatus |
| US11310223B2 (en) | 2015-10-09 | 2022-04-19 | Tencent Technology (Shenzhen) Company Limited | Identity authentication method and apparatus |
| WO2017059700A1 (en) * | 2015-10-09 | 2017-04-13 | 腾讯科技（深圳）有限公司 | Identity authentication method and apparatus |
| CN106572049A (en) * | 2015-10-09 | 2017-04-19 | 腾讯科技（深圳）有限公司 | Identity verifying apparatus and method |
| CN106572049B (en) * | 2015-10-09 | 2019-08-27 | 腾讯科技（深圳）有限公司 | A kind of auth method and device |
| CN106599764A (en) * | 2015-10-20 | 2017-04-26 | 深圳市商汤科技有限公司 | Lip-shape-characteristic-based living body determination method and equipment |
| CN106683661A (en) * | 2015-11-05 | 2017-05-17 | 阿里巴巴集团控股有限公司 | Role separation method and device based on voice |
| CN106709804A (en) * | 2015-11-16 | 2017-05-24 | 优化科技（苏州）有限公司 | Interactive wealth planning consulting robot system |
| CN105426723A (en) * | 2015-11-20 | 2016-03-23 | 北京得意音通技术有限责任公司 | Voiceprint identification, face identification and synchronous in-vivo detection-based identity authentication method and system |
| CN105528578A (en) * | 2015-12-04 | 2016-04-27 | 国家电网公司 | Online training monitoring method based on sound image process tracking |
| CN105577664B (en) * | 2015-12-22 | 2019-03-19 | 深圳前海微众银行股份有限公司 | Password remapping method and system, client and server |
| CN106911630A (en) * | 2015-12-22 | 2017-06-30 | 上海仪电数字技术股份有限公司 | Terminal and the authentication method and system of identity identifying method, terminal and authentication center |
| CN105577664A (en) * | 2015-12-22 | 2016-05-11 | 深圳前海微众银行股份有限公司 | Cipher reset method and system, client and server |
| US11853647B2 (en) | 2015-12-23 | 2023-12-26 | Apple Inc. | Proactive assistance based on dialog communication between devices |
| CN106096519A (en) * | 2016-06-01 | 2016-11-09 | 腾讯科技（深圳）有限公司 | Live body discrimination method and device |
| CN106028129A (en) * | 2016-06-16 | 2016-10-12 | 深圳Tcl数字技术有限公司 | Method and system for sharing television programs among televisions |
| CN106098069B (en) * | 2016-06-21 | 2019-12-20 | 佛山科学技术学院 | Identity authentication method and terminal equipment |
| CN106098069A (en) * | 2016-06-21 | 2016-11-09 | 佛山科学技术学院 | A kind of identity identifying method and terminal unit |
| CN107819807A (en) * | 2016-09-14 | 2018-03-20 | 腾讯科技（深圳）有限公司 | A kind of Information Authentication method, apparatus and equipment |
| CN106407783A (en) * | 2016-09-23 | 2017-02-15 | 武汉必腾移动科技有限责任公司 | An online verification method and system |
| CN106599660A (en) * | 2016-12-02 | 2017-04-26 | 宇龙计算机通信科技(深圳)有限公司 | Terminal safety verification method and terminal safety verification device |
| WO2018137426A1 (en) * | 2017-01-24 | 2018-08-02 | 中兴通讯股份有限公司 | Method and apparatus for recognizing voice information of user |
| CN107087133B (en) * | 2017-03-24 | 2020-07-03 | 宇龙计算机通信科技(深圳)有限公司 | Safety control method and terminal equipment |
| CN107087133A (en) * | 2017-03-24 | 2017-08-22 | 宇龙计算机通信科技(深圳)有限公司 | A kind of method of controlling security and terminal device |
| CN107437019A (en) * | 2017-07-31 | 2017-12-05 | 广东欧珀移动通信有限公司 | The auth method and device of lip reading identification |
| 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 |
| CN108306886A (en) * | 2018-02-01 | 2018-07-20 | 深圳市腾讯计算机系统有限公司 | A kind of auth method, device and storage medium |
| CN108306886B (en) * | 2018-02-01 | 2021-02-02 | 深圳市腾讯计算机系统有限公司 | Identity authentication method, device and storage medium |
| CN108595233A (en) * | 2018-03-09 | 2018-09-28 | 福州米鱼信息科技有限公司 | A kind of electronic evidence acquisition method and system based on voice prompt |
| CN108399395A (en) * | 2018-03-13 | 2018-08-14 | 成都数智凌云科技有限公司 | The compound identity identifying method of voice and face based on end-to-end deep neural network |
| CN108764010A (en) * | 2018-03-23 | 2018-11-06 | 姜涵予 | Emotional state determines method and device |
| CN109146480A (en) * | 2018-08-23 | 2019-01-04 | 交通银行股份有限公司 | A kind of method of payment, device, electronic equipment and storage medium |
| CN109087651A (en) * | 2018-09-05 | 2018-12-25 | 广州势必可赢网络科技有限公司 | A kind of vocal print identification method, system and equipment based on video and sound spectrograph |
| CN109624925A (en) * | 2018-12-10 | 2019-04-16 | 百度在线网络技术（北京）有限公司 | Automobile control method, device, equipment and storage medium |
| CN111339806B (en) * | 2018-12-19 | 2021-04-13 | 马上消费金融股份有限公司 | Training method of lip language recognition model, living body recognition method and device |
| CN111339806A (en) * | 2018-12-19 | 2020-06-26 | 马上消费金融股份有限公司 | Training method of lip language recognition model, living body recognition method and device |
| CN109910818A (en) * | 2019-02-15 | 2019-06-21 | 东华大学 | A kind of VATS Vehicle Anti-Theft System based on human body multiple features fusion identification |
| CN109910818B (en) * | 2019-02-15 | 2021-10-08 | 东华大学 | Vehicle anti-theft system based on human body multi-feature fusion identity recognition |
| CN110032924A (en) * | 2019-02-21 | 2019-07-19 | 百度在线网络技术（北京）有限公司 | Recognition of face biopsy method, terminal device, storage medium and electronic equipment |
| CN110198381A (en) * | 2019-04-28 | 2019-09-03 | 北京蓦然认知科技有限公司 | A kind of method and device of identification AI incoming call |
| CN110198381B (en) * | 2019-04-28 | 2020-11-27 | 北京蓦然认知科技有限公司 | Method, device, voice assistant, terminal, computer equipment and computer readable storage medium for identifying AI incoming call |
| CN110222719A (en) * | 2019-05-10 | 2019-09-10 | 中国科学院计算技术研究所 | A kind of character recognition method and system based on multiframe audio-video converged network |
| CN110082723A (en) * | 2019-05-16 | 2019-08-02 | 浙江大华技术股份有限公司 | A kind of sound localization method, device, equipment and storage medium |
| CN110082723B (en) * | 2019-05-16 | 2022-03-15 | 浙江大华技术股份有限公司 | Sound source positioning method, device, equipment and storage medium |
| CN112132996A (en) * | 2019-06-05 | 2020-12-25 | Tcl集团股份有限公司 | Door lock control method, mobile terminal, door control terminal and storage medium |
| WO2021007857A1 (en) * | 2019-07-18 | 2021-01-21 | 深圳海付移通科技有限公司 | Identity authentication method, terminal device, and storage medium |
| CN111684459A (en) * | 2019-07-18 | 2020-09-18 | 深圳海付移通科技有限公司 | Identity authentication method, terminal equipment and storage medium |
| CN111684444A (en) * | 2019-07-18 | 2020-09-18 | 深圳海付移通科技有限公司 | Identity authentication method, terminal equipment and storage medium |
| WO2021007856A1 (en) * | 2019-07-18 | 2021-01-21 | 深圳海付移通科技有限公司 | Identity verification method, terminal device, and storage medium |
| TWI801647B (en) * | 2019-08-07 | 2023-05-11 | 華南商業銀行股份有限公司 | Identity verification device and method based on dynamic image |
| TWI822646B (en) * | 2019-08-07 | 2023-11-11 | 華南商業銀行股份有限公司 | Identity verification device and method based on dynamic lip image |
| CN111967293A (en) * | 2020-06-22 | 2020-11-20 | 云知声智能科技股份有限公司 | Face authentication method and system combining voiceprint recognition and attention detection |
| CN112507311A (en) * | 2020-12-10 | 2021-03-16 | 东南大学 | High-security identity verification method based on multi-mode feature fusion |
| CN112614333A (en) * | 2020-12-17 | 2021-04-06 | 杭州当贝网络科技有限公司 | Remote controller retrieving 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 |
| CN113032758A (en) * | 2021-03-26 | 2021-06-25 | 平安银行股份有限公司 | Video question-answer flow identity identification method, device, equipment and storage medium |
| CN116405635A (en) * | 2023-06-02 | 2023-07-07 | 山东正中信息技术股份有限公司 | Multi-mode conference recording method and system based on edge calculation |
| CN116938611A (en) * | 2023-09-19 | 2023-10-24 | 苏州宏存芯捷科技有限公司 | Information verification method and system based on artificial intelligence |
| CN116938611B (en) * | 2023-09-19 | 2023-12-12 | 苏州宏存芯捷科技有限公司 | Information verification method and system based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104376250A (en) | Real person living body identity verification method based on sound-type image feature | |
| CN106709402A (en) | Living person identity authentication method based on voice pattern and image features | |
| CN104361276B (en) | A kind of multi-modal biological characteristic identity identifying method and system | |
| CN104680375A (en) | Identification verifying system for living human body for electronic payment | |
| RU2738325C2 (en) | Method and device for authenticating an individual | |
| Choudhury et al. | Multimodal person recognition using unconstrained audio and video | |
| CN204667465U (en) | Pay true man's live body authentication system by mails | |
| US6219640B1 (en) | Methods and apparatus for audio-visual speaker recognition and utterance verification | |
| CN112997186A (en) | Detection system for' viability | |
| CN102142254A (en) | Voiceprint identification and voice identification-based recording and faking resistant identity confirmation method | |
| CN101216884A (en) | A method and system for face authentication | |
| CN102682273A (en) | Device and method for detecting lip movement | |
| CN105718874A (en) | Method and device of in-vivo detection and authentication | |
| CN106709804A (en) | Interactive wealth planning consulting robot system | |
| CN106096519A (en) | Live body discrimination method and device | |
| WO2021007857A1 (en) | Identity authentication method, terminal device, and storage medium | |
| CN109255618A (en) | For the recognition of face payment information method for anti-counterfeit of dynamic video | |
| CN204576520U (en) | Based on the Dual-factor identity authentication device of Application on Voiceprint Recognition and recognition of face | |
| Shen et al. | Secure mobile services by face and speech based personal authentication | |
| Patel et al. | Human identification by partial iris segmentation using pupil circle growing based on binary integrated edge intensity curve | |
| CN116612542A (en) | Multi-mode biological feature consistency-based audio and video character recognition method and system | |
| CN110738985A (en) | Cross-modal biometric feature recognition method and system based on voice signals | |
| CN109034828A (en) | For the Application on Voiceprint Recognition payment information method for anti-counterfeit of recording | |
| Shenai et al. | Fast biometric authentication system based on audio-visual fusion | |
| Saleh et al. | Multimodal person identification through the fusion of face and voice biometrics |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150225 |
|
| WD01 | Invention patent application deemed withdrawn after publication |