CN110047184A - A kind of auth method and access control system of anti-recording attack - Google Patents
A kind of auth method and access control system of anti-recording attack Download PDFInfo
- Publication number
- CN110047184A CN110047184A CN201910332894.7A CN201910332894A CN110047184A CN 110047184 A CN110047184 A CN 110047184A CN 201910332894 A CN201910332894 A CN 201910332894A CN 110047184 A CN110047184 A CN 110047184A
- Authority
- CN
- China
- Prior art keywords
- personnel
- voice
- verified
- access control
- control system
- 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 28
- 230000001815 facial effect Effects 0.000 claims abstract description 34
- 230000001755 vocal effect Effects 0.000 claims abstract description 13
- 238000012795 verification Methods 0.000 claims abstract description 12
- 230000004888 barrier function Effects 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 5
- 238000010191 image analysis Methods 0.000 claims description 2
- 230000015572 biosynthetic process Effects 0.000 abstract description 6
- 238000003786 synthesis reaction Methods 0.000 abstract description 6
- 238000003491 array Methods 0.000 description 4
- 230000005764 inhibitory process Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001066 destructive effect Effects 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/20—Individual registration on entry or exit involving the use of a pass
- G07C9/22—Individual registration on entry or exit involving the use of a pass in combination with an identity check of the pass holder
- G07C9/25—Individual registration on entry or exit involving the use of a pass in combination with an identity check of the pass holder using biometric data, e.g. fingerprints, iris scans or voice recognition
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/30—Individual registration on entry or exit not involving the use of a pass
- G07C9/32—Individual registration on entry or exit not involving the use of a pass in combination with an identity check
- G07C9/37—Individual registration on entry or exit not involving the use of a pass in combination with an identity check using biometric data, e.g. fingerprints, iris scans or voice 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)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Collating Specific Patterns (AREA)
Abstract
The present invention provides a kind of auth methods of anti-recording attack, the described method comprises the following steps: obtaining the facial image of personnel to be verified and determine its facial positions;It acquires the voice of personnel to be verified and determines sound source position;Judge whether facial positions and sound source position are consistent to judge whether it is my sounding;It treats verifying personnel and carries out voice print verification;The present invention also provides a kind of access control systems of anti-recording attack, comprising: image capture module, voice acquisition module, door interlock switch module and main control module.The present invention passes through in person whether sounding and vocal print are verified, improve the judgement for treating verifying personnel's real speech, it can be effectively prevent situations such as pretending to be speaker's identity, attacking access control system using recording or synthesis voice, improve the safety of access control system.
Description
Technical field
The present invention relates to access control system field, in particular to the auth method of a kind of anti-recording attack and gate inhibition system
System.
Background technique
As the improvement of people's living standards, more stringent requirements are proposed for people couple and public place and house security, peace
Anti- problem has become people's gradually focus of attention, and security device is also increasingly valued by people, various gate inhibitions
Lock also emerges one after another, and existing access control system needs user according to screen display content using the random mode for generating dynamic digital
Text is read out to realize enabling, however some destructive means for access control system also emerge one after another, and such as pretend to be speaker
Identity records speaker's voice or attacks access control system by synthesis voice, and such case makes the safety of access control system
It is threatened at great, to reduce the guarantee to user security.
Summary of the invention
The object of the present invention is to provide the auth methods and access control system of a kind of anti-recording attack.
The present invention is to solve existing access control system safety is lower, exists and pretend to be speaker's identity, record speaker
Voice passes through the problem of synthesis voice attacks access control system.
To achieve the purpose of the present invention, the technical solution adopted by the present invention is that:
A kind of auth method of anti-recording attack, the described method comprises the following steps:
A, it obtains the facial image of personnel to be verified and determines its facial positions;
B, it acquires the voice of personnel to be verified and determines sound source position;
C, it is whether consistent with sound source position to judge facial positions, if unanimously, being judged as my sounding and executing step D,
If inconsistent, it is judged as non-sounding in person and verifying does not pass through;
D, verifying personnel are treated and carry out voice print verification.
Further, facial image progress image procossing and image analysis are measured and the face of personnel to be verified is calculated
Portion's height and position, and vertical facial dimension position is compared with sound source position.
Further, the step B includes being acquired respectively from the voice that verifying personnel are treated in multiple and different positions, root
The sound source position of personnel to be verified is calculated in the time difference that voice is received according to different location.
Further, the step B further include: acquire and monitor personnel to be verified in the voice process of personnel to be verified in real time
Whether facial front has barrier to block.
Further, the voiceprint of the preparatory typing user of the step D, to the voice of collected personnel to be verified into
Row voiceprint extraction is simultaneously compared with the voiceprint of preparatory typing.
Further, after passing through voice print verification the method also includes: personnel to be verified, access control system door lock is opened.
The present invention also provides a kind of access control system of anti-recording attack, the access control system applies a kind of anti-recording
The auth method of attack, comprising:
Image capture module: for obtaining the facial image of personnel to be verified and determining its facial positions;
Voice acquisition module: for acquiring voice messaging and extracting voiceprint according to voice messaging;
Door interlock switch module: for personnel to be verified by opening access control system door lock after voice print verification;
Main control module: voice print verification is carried out for treating verifying personnel, and verifies the facial positions and sound of personnel to be verified
Whether source position is consistent.
Preferably, described image acquisition module is camera, and the voice acquisition module includes at least three microphone
Array.
The auth method of the anti-recording attack of one kind of the invention and having the beneficial effect that for access control system:
1, the method for the present invention to whether my sounding and whether my vocal print judges, be judged as my sounding and I
Vocal print can just be realized by verifying and be opened the door, and improved the judgement for treating verifying personnel's real speech, can be effectively prevent pretending to be
It talks about personal part, using recording or synthesizing situations such as voice attacks access control system, improves the safety of access control system.
2, the present invention monitors in front of personnel's face to be verified whether have barrier screening in real time during acquiring user speech
Gear, prevents that personnel to be verified from will record or synthesis voice is put in facial positions and plays out, and improves the accuracy rate of verifying.
3, the present invention can be improved sound source by multiple microphone arrays including at least three or more microphone arrays
The accuracy of position.
Detailed description of the invention
Fig. 1: the flow diagram of the method for the present invention;
Fig. 2: access control system module relationship schematic diagram of the invention.
Specific embodiment
Existing access control system safety is lower, exists and pretends to be speaker's identity, records speaker's voice or pass through synthesis
Voice attacks the problem of access control system.So the present invention proposes new scheme, it is right with reference to the accompanying drawing more clearly to indicate
The present invention is described in detail.
Present embodiments provide the auth method and access control system of a kind of anti-recording attack.
Referring to fig. 2, the access control system of the anti-recording attack of one kind described in the present embodiment, the access control system include:
For obtaining the facial image of personnel to be verified and determining that its facial positions, monitoring personnel's face to be verified front are
It is no to have the image capture module that barrier blocks;
For acquiring voice messaging and according to the voice acquisition module of voice messaging extraction voiceprint;
For personnel to be verified by opening the door interlock switch module of access control system door lock after voice print verification;
Facial positions for storing voiceprint, treating verifying personnel progress voice print verification and verify personnel to be verified
With the whether consistent main control module of sound source position.
Described image acquisition module, voice acquisition module, door interlock switch module are all connected with the main control module.
Three microphone arrays are arranged in voice acquisition module in the present embodiment, and the microphone array is separately mounted to gate inhibition
Upper left side, upper right side and the middle lower section of system.
Certainly, the microphone array is not limited only to three, can according to need and is arranged three in access control system surrounding position
A above microphone array, the voice of personnel to be verified is acquired by multiple microphone arrays, can be improved and judge sound source position
The accuracy set.
Image capture module described in the present embodiment is camera, and the camera is installed on above access control system.
Referring to Fig. 1, it is described it is anti-recording attack auth method the following steps are included:
Step A, it obtains the facial image of personnel to be verified and determines its facial positions:
The facial image that face recognition technology obtains personnel to be verified is acquired and passed through by the camera;
The facial image of the personnel to be verified adopted is transmitted to main control module and carries out image procossing and image point to it
Analysis, finally measures and is calculated the facial positions of personnel to be verified;
The main control module calculates the personnel face to be verified according to image information combination image height, image distance and object distance
The height of portion position.
Step B, it acquires the voice of personnel to be verified and determines sound source position:
User issues voice, and access control system passes through the microphone array point that its upper left side, upper right side and middle lower section is arranged in
It is not acquired from the voice messaging that three different directions treat verifying personnel simultaneously;
Array receives time difference of voice to the main control module according to the three microphones, and the sound of personnel to be verified is calculated
Source position;
Auditory localization is a kind of using microphone array reception voice signal, and is carried out using means such as signal processings to it
Analysis processing, the final technology for determining sound source position.Estimate that sound source position mainly divides according to the time difference that sound reaches
For two steps: first estimating that voice signal reaches the time difference of each microphone array, and then closed with mathematical method according to geometry
System calculates, and obtains multiple independent time delay estimated values, the estimation of any one time delay for the voice position in three bit spaces
It is worth a corresponding secondary, cubic equation, the coordinate of sound source can be calculated by solving equation.
The step B further include: monitor personnel to be verified in real time in the voice process that camera acquires personnel to be verified
Whether facial front has barrier to block;If having detected, barrier is blocked, I does not pass through in sounding verifying, needs witness to be tested
The step of member re-starts voice collecting and verifies.
Main control module carries out feature extraction to the facial image in the present embodiment, judges whether the feature extracted is complete,
If imperfect, then it is assumed that be to there is barrier to block.For example, complete face characteristic includes: eye feature, mouth feature, nose
Feature, face mask feature;If lacking mouth feature in the feature extracted, then it is assumed that feature is imperfect, is determined as there is barrier
It blocks and verifies and do not pass through.
Step C, whether facial positions described in judgment step A and sound source position described in step B are consistent, to sentence
Whether disconnected be my sounding:
Whether the main control module comparison judges vertical facial dimension position consistent with sound source position, if unanimously, being judged as this
Human hair sound simultaneously continues to execute step D, if inconsistent, be judged as non-sounding in person and verifying does not pass through.
Step D, verifying personnel are treated and carry out voice print verification:
The voiceprint of the preparatory typing user of step D carries out vocal print to the voice of collected personnel to be verified and mentions
It takes and is compared with the voiceprint of preparatory typing.
The voiceprint of preparatory typing and user;
The microphone array carries out voiceprint extraction to the voice of collected personnel to be verified, and main control module will extract
Vocal print be compared with user's voiceprint of preparatory typing, if vocal print is consistent, be judged as my vocal print, if inconsistent,
Then non-vocal print in person.
Wherein, the user refers to user relevant to access control system application scenarios, such as: the application scenarios of access control system
For cell, then the user is the resident in the cell;The application scenarios of access control system are office building, then the user is
Office worker in office building.
Can determine whether collected voice is my vocal print and whether collected voice is this by above step
Human hair sound, if voice messaging can pass through verifying with my vocal print for my sounding;After verifying, main control module access control
The door-lock opening of system, user can enter;
If whether my vocal print, whether in my sounding there are any one verifying is unsanctioned, main control module is not beaten
Enabling access control system.
Access control system provided by the invention only needs subscriber station in front of access control system and issues phonetic order, and system can be voluntarily
Authentication is carried out to it, to realize that gate inhibition opens or is not turned on.
Present invention incorporates whether my sounding and whether my vocal print is judged, improve that treat verifying personnel true
The judgement of voice can effectively prevent situations such as pretending to be speaker's identity, attacking access control system using recording or synthesis voice,
Improve the safety of access control system.
Above embodiments are only to illustrate technical solution of the present invention rather than its limitations, although above-described embodiment pair
The present invention has carried out specific description, and related technical personnel should be appreciated that and can still carry out to a specific embodiment of the invention
Modification or equivalent replacement, and without departing from any modification of spirit and scope of the invention and equivalent replacement, it should all cover at this
Among the scope of the claims of invention.
Claims (8)
1. a kind of auth method of anti-recording attack, which is characterized in that the described method comprises the following steps:
A, it obtains the facial image of personnel to be verified and determines its facial positions;
B, it acquires the voice of personnel to be verified and determines sound source position;
C, it is whether consistent with sound source position to judge facial positions, if unanimously, being judged as my sounding and executing step D, if not
Unanimously, then it is judged as non-sounding in person and verifying does not pass through;
D, verifying personnel are treated and carry out voice print verification.
2. the auth method of the anti-recording attack of one kind according to claim 1, which is characterized in that facial image into
Row image procossing and image analysis measure and are calculated the vertical facial dimension position of personnel to be verified, and by vertical facial dimension position with
Sound source position is compared.
3. the auth method of the anti-recording attack of one kind according to claim 1, which is characterized in that the step B packet
It includes and is acquired respectively from the voice that verifying personnel are treated in multiple and different positions, the time difference of voice is received according to different location,
The sound source position of personnel to be verified is calculated.
4. the auth method of the anti-recording attack of one kind according to claim 1, which is characterized in that the step B is also
It include: to monitor whether personnel's face to be verified front has barrier to block in the voice process for acquire personnel to be verified in real time.
5. the auth method of the anti-recording attack of one kind according to claim 1, which is characterized in that the step D is pre-
The voiceprint of first typing user, the voice progress voiceprint extraction to collected personnel to be verified and the vocal print with preparatory typing
Information is compared.
6. the auth method of the anti-recording attack of one kind according to claim 1, which is characterized in that the method is also wrapped
It includes: after personnel to be verified pass through voice print verification, opening access control system door lock.
7. a kind of access control system of anti-recording attack, the access control system is using as claimed in any one of claims 1 to 6 one
The auth method of the anti-recording attack of kind characterized by comprising
Image capture module: for obtaining the facial image of personnel to be verified and determining its facial positions;
Voice acquisition module: for acquiring voice messaging and extracting voiceprint according to voice messaging;
Door interlock switch module: for personnel to be verified by opening access control system door lock after voice print verification;
Main control module: voice print verification is carried out for treating verifying personnel, and verifies facial positions and the sound source position of personnel to be verified
It whether consistent sets.
8. the access control system of the anti-recording attack of one kind according to claim 7, which is characterized in that described image acquisition module
For camera, the voice acquisition module includes at least three microphone array.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910332894.7A CN110047184A (en) | 2019-04-24 | 2019-04-24 | A kind of auth method and access control system of anti-recording attack |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910332894.7A CN110047184A (en) | 2019-04-24 | 2019-04-24 | A kind of auth method and access control system of anti-recording attack |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110047184A true CN110047184A (en) | 2019-07-23 |
Family
ID=67278920
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910332894.7A Pending CN110047184A (en) | 2019-04-24 | 2019-04-24 | A kind of auth method and access control system of anti-recording attack |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110047184A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111951437A (en) * | 2020-08-13 | 2020-11-17 | 安徽信息工程学院 | Automatic door lock control system |
CN112102546A (en) * | 2020-08-07 | 2020-12-18 | 浙江大华技术股份有限公司 | Man-machine interaction control method, talkback calling method and related device |
CN113053397A (en) * | 2021-03-04 | 2021-06-29 | 常州分音塔科技有限公司 | Recording attack prevention identity authentication method, device and system |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN202995914U (en) * | 2012-07-10 | 2013-06-12 | 中国银联股份有限公司 | Payment device and system based on image and audio information |
CN103955981A (en) * | 2014-05-15 | 2014-07-30 | 南宁思飞电子科技有限公司 | Access control device |
US9489949B2 (en) * | 1999-10-04 | 2016-11-08 | Dialware Inc. | System and method for identifying and/or authenticating a source of received electronic data by digital signal processing and/or voice authentication |
CN106572049A (en) * | 2015-10-09 | 2017-04-19 | 腾讯科技(深圳)有限公司 | Identity verifying apparatus and method |
CN106709402A (en) * | 2015-11-16 | 2017-05-24 | 优化科技(苏州)有限公司 | Living person identity authentication method based on voice pattern and image features |
CN107767137A (en) * | 2016-08-23 | 2018-03-06 | 中国移动通信有限公司研究院 | A kind of information processing method, device and terminal |
CN207337499U (en) * | 2017-08-08 | 2018-05-08 | 上海博泰悦臻电子设备制造有限公司 | A kind of combination vocal print and the tripper of recognition of face |
-
2019
- 2019-04-24 CN CN201910332894.7A patent/CN110047184A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9489949B2 (en) * | 1999-10-04 | 2016-11-08 | Dialware Inc. | System and method for identifying and/or authenticating a source of received electronic data by digital signal processing and/or voice authentication |
CN202995914U (en) * | 2012-07-10 | 2013-06-12 | 中国银联股份有限公司 | Payment device and system based on image and audio information |
CN103955981A (en) * | 2014-05-15 | 2014-07-30 | 南宁思飞电子科技有限公司 | Access control device |
CN106572049A (en) * | 2015-10-09 | 2017-04-19 | 腾讯科技(深圳)有限公司 | Identity verifying apparatus and method |
CN106709402A (en) * | 2015-11-16 | 2017-05-24 | 优化科技(苏州)有限公司 | Living person identity authentication method based on voice pattern and image features |
CN107767137A (en) * | 2016-08-23 | 2018-03-06 | 中国移动通信有限公司研究院 | A kind of information processing method, device and terminal |
CN207337499U (en) * | 2017-08-08 | 2018-05-08 | 上海博泰悦臻电子设备制造有限公司 | A kind of combination vocal print and the tripper of recognition of face |
Non-Patent Citations (2)
Title |
---|
傅万钧,张维力编著: "《应用电视技术》", 31 January 1996, 国防工业出版社 * |
潇潇洒洒131499: ""网上开户APP操作流程和使用说明"", 《百度文库HTTPS://WENKU.BAIDU.COM/VIEW/91055267657D27284B73F242336C1EB91A37338C.HTML?FR=SEARCH-1_INCOME1#》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112102546A (en) * | 2020-08-07 | 2020-12-18 | 浙江大华技术股份有限公司 | Man-machine interaction control method, talkback calling method and related device |
CN111951437A (en) * | 2020-08-13 | 2020-11-17 | 安徽信息工程学院 | Automatic door lock control system |
CN111951437B (en) * | 2020-08-13 | 2022-05-17 | 安徽信息工程学院 | Automatic door lock control system |
CN113053397A (en) * | 2021-03-04 | 2021-06-29 | 常州分音塔科技有限公司 | Recording attack prevention identity authentication method, device and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104834849B (en) | Dual-factor identity authentication method and system based on Application on Voiceprint Recognition and recognition of face | |
US20180146370A1 (en) | Method and apparatus for secured authentication using voice biometrics and watermarking | |
Villalba et al. | Speaker verification performance degradation against spoofing and tampering attacks | |
CN110047184A (en) | A kind of auth method and access control system of anti-recording attack | |
CA2188975C (en) | Method and apparatus employing audio and video data from an individual for authentication purposes | |
JP6106373B2 (en) | Method and system for speaker identification verification | |
CN103475490B (en) | A kind of auth method and device | |
CN106599660A (en) | Terminal safety verification method and terminal safety verification device | |
US20070038460A1 (en) | Method and system to improve speaker verification accuracy by detecting repeat imposters | |
GB2541466A (en) | Replay attack detection | |
CN111881726B (en) | Living body detection method and device and storage medium | |
EP2913799A2 (en) | System and method having biometric identification intrusion and access control | |
Chetty | Biometric liveness checking using multimodal fuzzy fusion | |
CN105426723A (en) | Voiceprint identification, face identification and synchronous in-vivo detection-based identity authentication method and system | |
Chetty et al. | Audio-visual multimodal fusion for biometric person authentication and liveness verification | |
Cristani et al. | Look at who’s talking: Voice activity detection by automated gesture analysis | |
CN109101949A (en) | A kind of human face in-vivo detection method based on colour-video signal frequency-domain analysis | |
Shang et al. | Enabling secure voice input on augmented reality headsets using internal body voice | |
CN109346085A (en) | A kind of prison supervising platform based on Application on Voiceprint Recognition | |
Shang et al. | Voice liveness detection for voice assistants using ear canal pressure | |
JP2017044778A (en) | Authentication device | |
Yampolskiy | Mimicry attack on strategy-based behavioral biometric | |
CN111243600A (en) | Voice spoofing attack detection method based on sound field and field pattern | |
Chetty et al. | " Liveness" Verification in Audio-Video Authentication | |
Zhu et al. | Liveness detection using time drift between lip movement and voice |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190723 |
|
RJ01 | Rejection of invention patent application after publication |