CN104573462B - Fingerprint and voiceprint dual-authentication method - Google Patents
Fingerprint and voiceprint dual-authentication method Download PDFInfo
- Publication number
- CN104573462B CN104573462B CN201510047966.5A CN201510047966A CN104573462B CN 104573462 B CN104573462 B CN 104573462B CN 201510047966 A CN201510047966 A CN 201510047966A CN 104573462 B CN104573462 B CN 104573462B
- Authority
- CN
- China
- Prior art keywords
- score
- fingerprint
- recognition
- user
- vocal print
- 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.)
- Active
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2221/00—Indexing scheme relating to security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F2221/21—Indexing scheme relating to G06F21/00 and subgroups addressing additional information or applications relating to security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F2221/2141—Access rights, e.g. capability lists, access control lists, access tables, access matrices
Landscapes
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Collating Specific Patterns (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a fingerprint and voiceprint dual-authentication method. The dual-authentication method includes: collecting a fingerprint and triggering voice collection at the same time; performing fingerprint recognition on the collected user fingerprint to obtain a fingerprint recognition score, performing voiceprint recognition on the collected user voice to obtain a voiceprint recognition score; performing integrated computation on the fingerprint recognition score and the voiceprint recognition score to obtain an integrated authentication score; judging a user identity according to the integrated authentication score; if the integrated authentication score is higher than or equal to a preset threshold, considering that both the fingerprint and the voiceprint come from a claimed user himself and the authentication passes, otherwise, considering that the authentication fails in passing. Fingerprint recognition and voiceprint recognition are combined to perform dual authentication, and accurately, safety and reliability of local and remote identity authentication are improved greatly by the dual-authentication mode.
Description
Technical field
The present invention relates to a kind of fingerprint and the double authentication methods of vocal print, belong to computer authentication service technical field.
Background technology
In living things feature recognition field, there is provided my biological characteristic is identified being referred to as self-identifying, biological characteristic
Identification includes fingerprint recognition, Application on Voiceprint Recognition etc..
Fingerprint recognition has been applied to the occasion of various authentications as a kind of important biometrics identification technology, but
From actual enforcement it is found that existing fingerprint identification technology to swarm into identification be not fine to various, will to safety
Higher occasion is sought, fingerprint recognition is used alone and is carried out authentication and there is certain risk.Other constantly entering with technology
Step, the appearance of fingerprint sleeve (also referred to as fingerprint film) cause the application of fingerprint identification technology to be limited by very large, and particularly exist
The occasion of long-distance identity-certifying, if used fingerprint sleeve to be difficult to be determined, this correctness and safety undoubtedly to authentication
Property all brings serious impact.
As can be seen here, the living things feature recognition of other species is added on the basis of fingerprint recognition, one kind is designed and can be corrected
Really, the technical scheme of certification is quickly and safely realized to user identity, is current urgent problem.
The content of the invention
It is an object of the invention to provide a kind of fingerprint and the double authentication methods of vocal print, fingerprint recognition and vocal print speech recognition phase
With reference to identity double authentication mode substantially increase accuracy under locally, remotely authentication situation, safety and reliability
Property.
To achieve these goals, present invention employs technical scheme below：
A kind of fingerprint and the double authentication methods of vocal print, it is characterised in that it includes step：
1) fingerprint is gathered, and voice collecting is triggered while fingerprint is gathered；
2) the user fingerprint to collecting carries out fingerprint recognition, obtains fingerprint recognition score f, while to making for collecting
User's voice carries out Application on Voiceprint Recognition, obtains Application on Voiceprint Recognition score v；
3) COMPREHENSIVE CALCULATING is carried out to fingerprint recognition score f and Application on Voiceprint Recognition score v, obtains comprehensive as the certification of identity judgement
Close score Score；
4) identity of user is judged based on certification comprehensive score Score：If Score is more than or equal to setting threshold
Value, then it is assumed that fingerprint and vocal print both are from the user claimed, certification passes through；If Score is less than given threshold, recognize
Card does not pass through.
Based on following formula a)-c) COMPREHENSIVE CALCULATING is carried out with Application on Voiceprint Recognition score v to fingerprint recognition score f, with
To certification comprehensive score Score：
Score=α × Scoref+(1-α)×Scorev c)
In formula a), μf、σfRespectively in advance to the calculated average of a large amount of fingerprint recognition scores, standard deviation, RfBe with
Fingerprint recognition false rejection rate FRRfCorresponding value, RfBased on F (Rf；0,1)=FRRfTry to achieve, F (x；0, it is 1) according to normal state
Distribution N (0, the cumulative distribution function for 1) obtaining；
In formula b), μv、σvRespectively in advance to the calculated average of a large amount of Application on Voiceprint Recognition scores, standard deviation, RvBe with
Application on Voiceprint Recognition false rejection rate FRRvCorresponding value, RvBased on F (Rv；0,1)=FRRvTry to achieve；
In formula c), α for it is interval (0,1) between a numerical value.
The span of certification comprehensive score Score is
One kind refers to vocal print harvester, it is characterised in that：It is included for gathering the fingerprint capturer of user fingerprint, being used for
The collection mike of user voice, governor circuit, fingerprint capturer, the signal port phase respectively with governor circuit of mike
Induction signal port connects, and the PORT COM of governor circuit is via communication interface and for fingerprint self-identifying, vocal print self-identifying, to referring to
Stricture of vagina recognizes that score and Application on Voiceprint Recognition score are carried out COMPREHENSIVE CALCULATING and draw certification comprehensive score and done based on certification comprehensive score
The finger vocal print collaboration Verification System for going out final identity judgement carries out Local or Remote communication.
It is described to refer to vocal print collaboration Verification System and be used to store the finger vocal print integrated database of Fingerprint Model and sound-groove model
It is connected.
The finger vocal print harvester also includes display screen, speaker, display lamp, display screen, speaker, the signal of display lamp
Port is connected with the corresponding signal port of the governor circuit respectively.
It is an advantage of the invention that：
The present invention is gathered and final by fingerprint recognition and vocal print speech recognition are combined, with fingerprint collecting triggering vocal print
The method for carrying out comprehensive descision, realizes fast and accurately double authentication to the identity of user, effectively prevent fingerprint sleeve
Use, solve the unsafe problems of single creature feature identification, either local authentication or long-distance identity-certifying are accurate
Really property, safety and reliability are obtained for very big raising, and misidentification rate is less than 0.0001%.
Description of the drawings
Fig. 1 is the flowchart of fingerprint of the present invention and the double authentication methods of vocal print.
Fig. 2 is the composition schematic diagram that the present invention refers to vocal print harvester.
Fig. 3 is the application note figure that the present invention refers to vocal print harvester.
Specific embodiment
As shown in figure 1, fingerprint of the present invention is comprised the steps with the double authentication methods of vocal print：
1) fingerprint is gathered, and voice collecting is triggered while fingerprint is gathered；
2) the user fingerprint to collecting carries out fingerprint recognition, obtains fingerprint recognition score f, while to making for collecting
User's voice carries out Application on Voiceprint Recognition, obtains Application on Voiceprint Recognition score v；
3) COMPREHENSIVE CALCULATING is carried out to fingerprint recognition score f and Application on Voiceprint Recognition score v, obtains comprehensive as the certification of identity judgement
Close score Score；
4) identity of user is judged based on certification comprehensive score Score：If Score is more than or equal to setting threshold
Value, then it is assumed that fingerprint and vocal print both are from the user claimed, certification passes through；If Score is less than given threshold, recognize
Card does not pass through.
In practice, step 1) the middle voice for the gathering voice that preferably user is said based on the text for showing,
Can so prevent recording from swarming into.
In actual design, following formula a)-c can be based on) comprehensive meter is carried out to fingerprint recognition score f and Application on Voiceprint Recognition score v
Calculate, to obtain certification comprehensive score Score：
Score=α × Scoref+(1-α)×Scorev c)
In formula a), μf、σfRespectively in advance to the calculated average of a large amount of fingerprint recognition scores, standard deviation, RfBe with
Fingerprint recognition false rejection rate FRRf(preset value) corresponding value, RfBased on F (Rf；0,1)=FRRfTry to achieve, F (x；0,
1) be according to normal distribution N (0, the cumulative distribution function for 1) obtaining, ScorefFor certification fingerprint score；
In formula b), μv、σvRespectively in advance to the calculated average of a large amount of Application on Voiceprint Recognition scores, standard deviation, RvBe with
Application on Voiceprint Recognition false rejection rate FRRv(preset value) corresponding value, RvBased on F (Rv；0,1)=FRRvTry to achieve, F (x；0,
1) be according to normal distribution N (0, the cumulative distribution function for 1) obtaining, ScorevFor certification vocal print score；
In formula c), α for it is interval (0,1) between a numerical value, α is arithmetic number, for adjusting certification comprehensive score
The more reference fingerprints of Score recognize score, or more reference Application on Voiceprint Recognition scores.
The span of certification comprehensive score Score isIn actual enforcement, can be according to practical application needs
Design setting threshold value T, when Score is more than or equal to T, it is believed that fingerprint and vocal print both are from the user claimed, certification
Pass through, otherwise certification does not pass through.
In practice, fingerprint recognition score f and Application on Voiceprint Recognition score v are carried out COMPREHENSIVE CALCULATING to obtain certification comprehensive score
The method of Score is not limited to above-mentioned, can also have other methods to try to achieve Score.
The invention allows for a kind of finger vocal print harvester arrived used in the double authentication methods of above-mentioned fingerprint and vocal print,
As shown in Figures 2 and 3, the present invention refers to that vocal print harvester 10 is included for gathering the fingerprint capturer 12 of user fingerprint, being used for
The collection mike 13 of user voice, governor circuit 11, fingerprint capturer 12, mike 13 signal port respectively with master control
The corresponding signal port connection of circuit 11, the PORT COM of governor circuit 11 is via communication interface 17 and finger vocal print collaboration certification system
System 20 carries out Local or Remote communication, refers to that vocal print collaboration Verification System 20 is used for fingerprint self-identifying, vocal print self-identifying, fingerprint is known
Other score is carried out COMPREHENSIVE CALCULATING and draws certification comprehensive score and made most based on certification comprehensive score with Application on Voiceprint Recognition score
Lifelong part judges.Such as Fig. 3, refer to vocal print collaboration Verification System 20 and be used to store the finger vocal print synthesis of Fingerprint Model and sound-groove model
Data base 30 is connected.
Such as Fig. 2, the present invention refer to that vocal print harvester 10 may also include display screen 14, speaker 15, display lamp 16, display screen
14th, speaker 15, the signal port of display lamp 16 are connected with the corresponding signal port of governor circuit 11 respectively.
In actually used finger vocal print harvester 10, refer to that vocal print harvester 10 waits user to press fingerprint first, work as inspection
Measure after user presses fingerprint, voice collecting is triggered while fingerprint is gathered.During collection voice, vocal print collection is generally referred to
Device 10 generates one section of text and shows on display screen 14, then requires that user says this section of text.When user lifts finger
Or at the end of speech detection, while terminating voice collecting and fingerprint collecting.
Speak using different modes prompting user in practice, and while prompting or mike should be opened after a while
13 collections for carrying out voice.
Prompting user utterance is included but is not limited to：1) spoken with the prompting user of display lamp 16；2) with display
Shield 14 display reminding languages, guiding user is spoken；3) with 15 play cuing language of speaker, guiding user is spoken；4) with top
Use while wantonly 2 kinds or wantonly 3 kinds in formula.
In the present invention, fingerprint recognition is referred to for the fingerprint mould set up by the fingerprint of the user for collecting
Type, using known algorithm for recognizing fingerprint, compares with the Fingerprint Model reserved in vocal print integrated database 30 is referred to, realizes referring to
The identification of stricture of vagina, obtains fingerprint recognition score f.Application on Voiceprint Recognition is referred to be set up for the voice of the user for passing through to collect
The sound-groove model for coming, using known voiceprint recognition algorithm, is carried out with the sound-groove model reserved in vocal print integrated database 30 is referred to
Compare, realize the identification of vocal print, obtain Application on Voiceprint Recognition score v.
In actual use, such as Fig. 3, multiple finger vocal print harvesters 10 are simultaneously operable, by finger vocal print collaboration Verification System
20 pairs of multiple finger vocal print harvesters 10 carry out synergic adjustment.
In the present invention, refer to that vocal print collaboration Verification System 20 may include microprocessor and peripheral circuit, belong to known systems,
Concrete composition is not described in detail here.
The present invention is gathered and final by fingerprint recognition and vocal print speech recognition are combined, with fingerprint collecting triggering vocal print
The method for carrying out comprehensive descision, realizes fast and accurately double authentication to the identity of user, effectively prevent fingerprint sleeve
Use, solve the unsafe problems of single creature feature identification, either local authentication or long-distance identity-certifying are accurate
Really property, safety and reliability are obtained for very big raising, and misidentification rate is less than 0.0001%.
The above is presently preferred embodiments of the present invention and its know-why used, for those skilled in the art
For, without departing from the spirit and scope of the present invention, it is any based on technical solution of the present invention on the basis of equivalent change
Change, simply replacement etc. obviously changes, belong within the scope of the present invention.
Claims (3)
1. double authentication methods of a kind of fingerprint and vocal print, it is characterised in that it includes step：
1) fingerprint is gathered, and voice collecting is triggered while fingerprint is gathered；
2) the user fingerprint to collecting carries out fingerprint recognition, obtains fingerprint recognition score f, while to the user for collecting
Voice carries out Application on Voiceprint Recognition, obtains Application on Voiceprint Recognition score v；
3) COMPREHENSIVE CALCULATING is carried out to fingerprint recognition score f and Application on Voiceprint Recognition score v, the certification for obtaining judging as identity is comprehensively obtained
Divide Score；
4) identity of user is judged based on certification comprehensive score Score：If Score is more than or equal to given threshold,
Think that fingerprint and vocal print both are from the user claimed, certification passes through；If Score is less than given threshold, certification is not
Pass through；
Wherein, based on following formula a)-c) COMPREHENSIVE CALCULATING is carried out to fingerprint recognition score f and Application on Voiceprint Recognition score v, it is comprehensive to obtain certification
Close score Score：
Score=α × Scoref+(1-α)×Scorev c)
In formula a), μf、σfRespectively in advance to the calculated average of a large amount of fingerprint recognition scores, standard deviation, RfIt is and fingerprint
Identification false rejection rate FRRfCorresponding value, RfBased on F (Rf；0,1)=FRRfTry to achieve, F (x；0, it is 1) according to normal distribution N
(0, the cumulative distribution function for 1) obtaining；
In formula b), μv、σvRespectively in advance to the calculated average of a large amount of Application on Voiceprint Recognition scores, standard deviation, RvIt is and vocal print
Identification false rejection rate FRRvCorresponding value, RvBased on F (Rv；0,1)=FRRvTry to achieve；
In formula c), α for it is interval (0,1) between a numerical value.
2. double authentication methods of fingerprint as claimed in claim 1 and vocal print, it is characterised in that：
The span of certification comprehensive score Score is
3. double authentication methods of fingerprint as claimed in claim 1 and vocal print, it is characterised in that：
The voice that the voice of collection is said based on the text for showing for user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510047966.5A CN104573462B (en) | 2015-01-30 | 2015-01-30 | Fingerprint and voiceprint dual-authentication method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510047966.5A CN104573462B (en) | 2015-01-30 | 2015-01-30 | Fingerprint and voiceprint dual-authentication method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104573462A CN104573462A (en) | 2015-04-29 |
| CN104573462B true CN104573462B (en) | 2017-05-03 |
Family
ID=53089503
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510047966.5A Active CN104573462B (en) | 2015-01-30 | 2015-01-30 | Fingerprint and voiceprint dual-authentication method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104573462B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3508998A1 (en) * | 2018-01-03 | 2019-07-10 | Samsung Electronics Co., Ltd. | Electronic device, control method thereof, and computer readable recording medium |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9813906B2 (en) * | 2014-11-12 | 2017-11-07 | Qualcomm Incorporated | Mobile device to provide enhanced security based upon contextual sensor inputs |
| CN105590045B (en) * | 2015-09-14 | 2018-09-04 | 中国银联股份有限公司 | A kind of identity identifying method and terminal of environment self-adaption |
| CN105224850A (en) * | 2015-10-24 | 2016-01-06 | 北京进化者机器人科技有限公司 | Combined right-discriminating method and intelligent interactive system |
| CN105429969B (en) * | 2015-11-09 | 2019-08-13 | 普天智能照明研究院有限公司 | A kind of user ID authentication method and equipment |
| CN108880815A (en) * | 2017-05-12 | 2018-11-23 | 阿里巴巴集团控股有限公司 | Auth method, device and system |
| CN107295192B (en) * | 2017-07-13 | 2020-03-24 | Oppo广东移动通信有限公司 | Unlocking control method and related product |
| CN107463819B (en) * | 2017-07-14 | 2020-03-03 | Oppo广东移动通信有限公司 | Unlocking processing method and related product |
| CN107517298B (en) * | 2017-07-21 | 2020-08-14 | Oppo广东移动通信有限公司 | Unlocking method and related product |
| CN107463822B (en) * | 2017-07-21 | 2021-04-02 | Oppo广东移动通信有限公司 | Biometric pattern control method and related product |
| CN107545166B (en) * | 2017-08-24 | 2021-04-16 | Oppo广东移动通信有限公司 | Biometric identification method and related product |
| CN109346085B (en) * | 2018-10-29 | 2021-09-28 | 合肥赛为智能有限公司 | Prison supervision platform based on voiceprint recognition |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2229305B (en) * | 1989-03-13 | 1993-05-12 | British Telecomm | Pattern recognition |
| CN1221160A (en) * | 1997-11-28 | 1999-06-30 | 日本电气株式会社 | Personal identification system using fingerprint |
| US6243695B1 (en) * | 1998-03-18 | 2001-06-05 | Motorola, Inc. | Access control system and method therefor |
| CN101414351A (en) * | 2008-11-03 | 2009-04-22 | 章毅 | Fingerprint recognition system and control method |
| CN102045162A (en) * | 2009-10-16 | 2011-05-04 | 电子科技大学 | Personal identification system of permittee with tri-modal biometric characteristic and control method thereof |
| CN103237030A (en) * | 2013-04-25 | 2013-08-07 | 深圳市中兴移动通信有限公司 | Biological recognition-based user authentication method and system |
| CN103606047A (en) * | 2013-11-22 | 2014-02-26 | 深圳市亚略特生物识别科技有限公司 | Password management system |
-
2015
- 2015-01-30 CN CN201510047966.5A patent/CN104573462B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2229305B (en) * | 1989-03-13 | 1993-05-12 | British Telecomm | Pattern recognition |
| CN1221160A (en) * | 1997-11-28 | 1999-06-30 | 日本电气株式会社 | Personal identification system using fingerprint |
| US6243695B1 (en) * | 1998-03-18 | 2001-06-05 | Motorola, Inc. | Access control system and method therefor |
| CN101414351A (en) * | 2008-11-03 | 2009-04-22 | 章毅 | Fingerprint recognition system and control method |
| CN102045162A (en) * | 2009-10-16 | 2011-05-04 | 电子科技大学 | Personal identification system of permittee with tri-modal biometric characteristic and control method thereof |
| CN103237030A (en) * | 2013-04-25 | 2013-08-07 | 深圳市中兴移动通信有限公司 | Biological recognition-based user authentication method and system |
| CN103606047A (en) * | 2013-11-22 | 2014-02-26 | 深圳市亚略特生物识别科技有限公司 | Password management system |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3508998A1 (en) * | 2018-01-03 | 2019-07-10 | Samsung Electronics Co., Ltd. | Electronic device, control method thereof, and computer readable recording medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104573462A (en) | 2015-04-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104573462B (en) | Fingerprint and voiceprint dual-authentication method | |
| CN107492382B (en) | Voiceprint information extraction method and device based on neural network | |
| CN104143326B (en) | A kind of voice command identification method and device | |
| Singh et al. | Applications of speaker recognition | |
| US7788101B2 (en) | Adaptation method for inter-person biometrics variability | |
| CN106790054A (en) | Interactive authentication system and method based on recognition of face and Application on Voiceprint Recognition | |
| CN107240397A (en) | A kind of smart lock and its audio recognition method and system based on Application on Voiceprint Recognition | |
| TW201342365A (en) | Method of using voice emotion or excitation level to assist distinguishing sex or age of voice signal | |
| CN103426428A (en) | Speech recognition method and speech recognition system | |
| US8965068B2 (en) | Apparatus and method for discriminating disguised face | |
| CN110246485B (en) | Sample data acquisition method, terminal equipment and medium based on voice recognition model | |
| CN107346568B (en) | Authentication method and device of access control system | |
| CN109766785A (en) | A kind of biopsy method and device of face | |
| CN106888204A (en) | Implicit identity identifying method based on natural interaction | |
| CN109171644A (en) | Health control method, device, computer equipment and storage medium based on voice recognition | |
| CN110738998A (en) | Voice-based personal credit evaluation method, device, terminal and storage medium | |
| CN111062021B (en) | Method and device for identity authentication based on wearable equipment | |
| CN103390305A (en) | A text-prompt type voiceprint access control system | |
| US20150269930A1 (en) | Spoken word generation method and system for speech recognition and computer readable medium thereof | |
| CN108376215A (en) | A kind of identity identifying method | |
| CN111046810A (en) | Data processing method and processing device | |
| CN109858366A (en) | Identity identifying method and device | |
| US20210027777A1 (en) | Method for monitoring phonation and system thereof | |
| CN111179919B (en) | Method and device for determining aphasia type | |
| CN102237089B (en) | Method for reducing error identification rate of text irrelevant speaker identification system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |