CN102694653A - Method of logging into system through speech recognition and/or facial image recognition - Google Patents
Method of logging into system through speech recognition and/or facial image recognition Download PDFInfo
- Publication number
- CN102694653A CN102694653A CN2012101322499A CN201210132249A CN102694653A CN 102694653 A CN102694653 A CN 102694653A CN 2012101322499 A CN2012101322499 A CN 2012101322499A CN 201210132249 A CN201210132249 A CN 201210132249A CN 102694653 A CN102694653 A CN 102694653A
- Authority
- CN
- China
- Prior art keywords
- user
- facial image
- voice
- account
- speech recognition
- 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
Images
Landscapes
- Collating Specific Patterns (AREA)
Abstract
The invention relates to a method of logging into a system through speech recognition and/or facial image recognition, more specifically, to a method of logging into the system after an identity has been confirmed through speech recognition and/or facial image recognition by software before logging into the system. For unrecognized or newly added speech recognition and/or facial image recognition, the system will automatically create new account information and allow login and use of unclassified resource information of the system. The method provided by the invention has a very high value with respect to system login security.
Description
Technical field
The present invention relates to electronic information technical field, relate to the man-machine a kind of key technology that gets into system through modes such as interactive voice resolution and facial image identification resolutions.
Background technology
In actual life; User's various identity mainly realize through authentication; Such as identity card, residence booklet etc., there is more similarity in the world of computer and the world of reality, and various computational resources are such as file, database, system etc.; Also need the protection of authentication mechanism, guarantee that the people that these resources should be used uses.Present all kinds of computational resource is mainly protected by fixing password mode; Such as NT system of needs visit, at first an account must be set on this NT, and set a password for this account; When this resource of visit; Must correct account and the password of input, after the account is identified correctly with password, just can allow to visit this resource.But there is more drawback in this mode, such as network data flow eavesdropped, authentication information forgotten or the like by intercepting, playback, account and password, make the account become dangerous and maybe can not use.
Summary of the invention
The technical problem that the present invention will solve is: propose a kind of with speech recognition or/and the method for facial image identification entering system; Owing to pass through the method for account and password login system now; Occur easily that network data flow is eavesdropped, authentication information more problem such as forgotten by intercepting, playback, account and password, makes the system that will login dangerous or forget Password and can not use, voice are a kind of distinctive characteristics of people; Through speech characteristic parameter is extracted, form only one information.Image is that the ambiguity of human head picture is judged, extracts the image feature parameter through image collection repeatedly, sets up people's image parameter recognition feature.Or/and the facial image RM, it is stolen to solve Zhang Hu password with speech recognition, and account password Yi Wang loses problem.
The technical scheme that the present invention adopted is: a kind of method that gets into system through speech recognition, when the user logined privately owned resource account, system picked up, discerns and judge according to the desired voice that the user sends, and the user is logined.
The system requirements user sends continuous voice snippet; System carries out pre-filtering, sampling and quantification, windowing, end-point detection, preemphasis, characteristic parameter extraction and pattern matching to this voice signal; And with the system template storehouse in account information mate contrast; The user signs in to privately owned resource account after mating successfully, and coupling is unsuccessful carries out speech recognition again or set up new account.
Perhaps, a kind of method through facial image identification entering system, when the user logined privately owned resource account, system picked up, discerns and judge people's dignity picture of user, and the user is logined.
System obtains people's dignity picture of active user; And current face generated face line coding as file; Retrieve contrast through face line coding and the face line coding in the system template storehouse; The user signed in to privately owned resource account after retrieval contrasted successfully, and contrast is unsuccessful to be carried out speech recognition again or set up new account.
Further, of the present invention line coding can be resisted the variation of light, skin color, facial hair, hair style, glasses, expression and attitude, and therefore, a face only generates a face line coding as file.
Simultaneously; In order to enjoy good fail safe; A kind of method that gets into system through voice and the dual identification of facial image provided by the invention; When the user logined privately owned resource account, system picked up respectively, discerns and judge the desired voice that user's people's dignity picture and user sends, and behind the simultaneous verification user identity user is logined.
System verifies to user's people's dignity picture and voice snippet that simultaneously two kinds of information simultaneous verification success back users sign in to privately owned resource account; There is a kind of checking to get nowhere in two kinds of information and then carries out people's dignity picture and voice snippet identification again or set up new account.
The invention has the beneficial effects as follows: from the convenience aspect; No matter be city, rural area, or young people, old gang because be through voice or (with) the image mode; Compare through account and pin mode; Forget never or lose that the people arrives to voice then to, image, solves the account and the password Problem of Failure that occur because of older, the time is long etc.; From the fail safe aspect, consult through online data and to learn, use account and pin mode, Net silver, network game and various websites etc. annually stolen amount occurs and are unequal to number.On the contrary, under same channel, the accuracy rate of speech recognition is near 100%; The image RM, the False Rate that present technology reaches is less than 0.1%, and therefore, this is invented for login system fail safe aspect, has very high value.
Description of drawings
Below in conjunction with accompanying drawing and embodiment the present invention is further specified.
Fig. 1 is the explanation diagram that gets into the management method of system through speech recognition;
Fig. 2 is the explanation diagram through the management method of facial image identification login system;
Fig. 3 is the explanation diagram through the management method of speech recognition and the two identification logins of image identification.
Embodiment
Combine accompanying drawing and preferred embodiment that the present invention is done further detailed explanation now.These accompanying drawings are the sketch map of simplification, basic structure of the present invention only is described in a schematic way, so it only show the formation relevant with the present invention.
As shown in Figure 1, by the method that speech recognition gets into system, the user clicks login; One section continuous language and characters of system prompt is also read aloud by the user, and system extracts, discerns and judge user's voice, and with the system template storehouse in the speech parameter aspect ratio to coupling; If the match is successful; Then the user successfully logins and preserves customer management information, successfully uses privately owned resource, logs off after the completion.If coupling is unsuccessful, then system carries out speech recognition again, discern again successfully that the back user successfully logins, and perhaps identification is unsuccessful again, the also preservation of accounts information that system is new for the user sets up, and the user can use publicly-owned resource.
Shown in Figure 2 is that it is similar with the above-mentioned method of passing through speech recognition, here no longer repeat specification through the method for facial image identification entering system.
Shown in Figure 3 is the method through the dual identification of speech recognition and facial image identification; System need gather user's voice information and facial image information simultaneously; And mate contrast respectively, and having only when two kinds of information of same of gathering and mate successfully, system just can carry out next step operation.If there is a kind of information not meet coupling, then system can require to discern again or set up new accounts information.
What describe in the above specification is embodiment of the present invention; Various not illustrating constitutes restriction to flesh and blood of the present invention; Under the those of ordinary skill of technical field after having read specification can to before described embodiment make an amendment or be out of shape, and do not deviate from essence of an invention and scope.
Claims (7)
1. method that gets into system through speech recognition is characterized in that: when the user logined privately owned resource account, system picked up, discerns and judge according to the desired voice that the user sends, and the user is logined.
2. a kind of method that gets into system through speech recognition as claimed in claim 1; It is characterized in that: the system requirements user sends continuous voice snippet; System carries out pre-filtering, sampling and quantification, windowing, end-point detection, preemphasis, characteristic parameter extraction and pattern matching to this voice signal; And with the system template storehouse in account information mate contrast, mate successfully the back user and sign in to privately owned resource account, coupling is unsuccessful carries out speech recognition again or sets up new account.
3. method through facial image identification entering system is characterized in that: when the user logined privately owned resource account, system picked up, discerns and judge people's dignity picture of user, and the user is logined.
4. a kind of method as claimed in claim 3 through facial image identification entering system; It is characterized in that: system obtains people's dignity picture of active user; And current face generated face line coding as file; Retrieve contrast through face line coding and the face line coding in the system template storehouse, the user signed in to privately owned resource account after retrieval contrasted successfully, and contrast is unsuccessful to be carried out speech recognition again or set up new account.
5. a kind of method through facial image identification entering system as claimed in claim 4 is characterized in that: a face only generates a face line coding as file.
6. method through the dual identification entering of voice and facial image system; It is characterized in that: when the user logins privately owned resource account; System picks up respectively, discerns and judge user's the desired voice that people's dignity looks like and the user sends, and behind the simultaneous verification user identity user is logined.
7. a kind of method that gets into system through voice and the dual identification of facial image as claimed in claim 6; It is characterized in that: system verifies to user's people's dignity picture and voice snippet that simultaneously two kinds of information simultaneous verification success back users sign in to privately owned resource account; There is a kind of checking to get nowhere in two kinds of information and then carries out people's dignity picture and voice snippet identification again or set up new account.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2012101322499A CN102694653A (en) | 2012-04-28 | 2012-04-28 | Method of logging into system through speech recognition and/or facial image recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2012101322499A CN102694653A (en) | 2012-04-28 | 2012-04-28 | Method of logging into system through speech recognition and/or facial image recognition |
Publications (1)
Publication Number | Publication Date |
---|---|
CN102694653A true CN102694653A (en) | 2012-09-26 |
Family
ID=46859945
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2012101322499A Pending CN102694653A (en) | 2012-04-28 | 2012-04-28 | Method of logging into system through speech recognition and/or facial image recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102694653A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104820798A (en) * | 2015-04-24 | 2015-08-05 | 成都腾悦科技有限公司 | A novel voice and face recognition system for a computer |
CN105489218A (en) * | 2015-11-24 | 2016-04-13 | 江苏惠通集团有限责任公司 | Speech control system, remote control and server |
CN105871601A (en) * | 2016-03-28 | 2016-08-17 | 深圳市双赢伟业科技股份有限公司 | Router configuration interface access method and device |
CN108108605A (en) * | 2017-12-18 | 2018-06-01 | 北京百度网讯科技有限公司 | Approaches to IM and device |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101179385A (en) * | 2007-11-22 | 2008-05-14 | 北京金山软件有限公司 | Method, network game server and system for improving security of user account |
CN102164113A (en) * | 2010-02-22 | 2011-08-24 | 深圳市联通万达科技有限公司 | Face recognition login method and system |
CN202003365U (en) * | 2010-12-31 | 2011-10-05 | 深圳市丰泰瑞达实业有限公司 | Authentication device based on system on programmable chip (SOPC) |
CN102222502A (en) * | 2011-05-16 | 2011-10-19 | 上海先先信息科技有限公司 | Effective way for voice verification by Chinese text-prompted mode |
CN202116118U (en) * | 2011-06-27 | 2012-01-18 | 吴江市德菱电梯配套有限公司 | Intelligent elevator device |
CN202124017U (en) * | 2011-06-10 | 2012-01-25 | 沈阳君天科技股份有限公司 | Device for directly starting automobile by voice and preventing burglary based on embedded system |
-
2012
- 2012-04-28 CN CN2012101322499A patent/CN102694653A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101179385A (en) * | 2007-11-22 | 2008-05-14 | 北京金山软件有限公司 | Method, network game server and system for improving security of user account |
CN102164113A (en) * | 2010-02-22 | 2011-08-24 | 深圳市联通万达科技有限公司 | Face recognition login method and system |
CN202003365U (en) * | 2010-12-31 | 2011-10-05 | 深圳市丰泰瑞达实业有限公司 | Authentication device based on system on programmable chip (SOPC) |
CN102222502A (en) * | 2011-05-16 | 2011-10-19 | 上海先先信息科技有限公司 | Effective way for voice verification by Chinese text-prompted mode |
CN202124017U (en) * | 2011-06-10 | 2012-01-25 | 沈阳君天科技股份有限公司 | Device for directly starting automobile by voice and preventing burglary based on embedded system |
CN202116118U (en) * | 2011-06-27 | 2012-01-18 | 吴江市德菱电梯配套有限公司 | Intelligent elevator device |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104820798A (en) * | 2015-04-24 | 2015-08-05 | 成都腾悦科技有限公司 | A novel voice and face recognition system for a computer |
CN105489218A (en) * | 2015-11-24 | 2016-04-13 | 江苏惠通集团有限责任公司 | Speech control system, remote control and server |
CN105871601A (en) * | 2016-03-28 | 2016-08-17 | 深圳市双赢伟业科技股份有限公司 | Router configuration interface access method and device |
CN105871601B (en) * | 2016-03-28 | 2019-02-12 | 深圳市双赢伟业科技股份有限公司 | A kind of configuration of routers interface cut-in method and device |
CN108108605A (en) * | 2017-12-18 | 2018-06-01 | 北京百度网讯科技有限公司 | Approaches to IM and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
TWI592820B (en) | Man-machine recognition method and system | |
Sultana et al. | A concept of social behavioral biometrics: motivation, current developments, and future trends | |
CN106529379A (en) | Method and device for recognizing living body | |
Sen et al. | Putting ‘pressure’on mobile authentication | |
US20210110015A1 (en) | Biometric Challenge-Response Authentication | |
CN105005779A (en) | Face verification anti-counterfeit recognition method and system thereof based on interactive action | |
CN103279764A (en) | Real-name network authentication system based on face identification | |
CN105740682A (en) | Computer system as well as identification method and system of user thereof | |
CN103714282A (en) | Interactive type identification method based on biological features | |
CN205883297U (en) | Number of account login system based on people's face and fingerprint identification | |
CN103413078B (en) | Based on two-layer on-line authentication system and the authentication method of user ID and person's handwriting | |
CN103607387A (en) | A network login authentication cloud service system based on face identification and a method | |
CN105975837B (en) | Calculate equipment, biological feather recognition method and template register method | |
CN102694653A (en) | Method of logging into system through speech recognition and/or facial image recognition | |
CN104821882A (en) | Network security verification method based on voice biometric features | |
CN109005140A (en) | Safe account registration and login method | |
CN106878344A (en) | A kind of biological characteristic authentication, register method and device | |
CN110008670A (en) | Identity identifying method and device based on hand-written password | |
WO2016062200A1 (en) | Fingerprint authentication method and apparatus, and server | |
JP2007265219A (en) | Biometrics system | |
CN106156590A (en) | A kind of computer startup processing method and processing system | |
CN102314594B (en) | Biometric authentication device and biometric authentication method | |
CN104123486A (en) | Non-contact type computer safety login system and method with voiceprint recognition function | |
CN103700151A (en) | Morning run check-in method | |
CN107808082A (en) | Electronic installation, data access verification method and computer-readable recording medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20120926 |