CN106203369A - Active stochastic and dynamic for anti-counterfeiting recognition of face instructs generation system - Google Patents
Active stochastic and dynamic for anti-counterfeiting recognition of face instructs generation system Download PDFInfo
- Publication number
- CN106203369A CN106203369A CN201610566605.6A CN201610566605A CN106203369A CN 106203369 A CN106203369 A CN 106203369A CN 201610566605 A CN201610566605 A CN 201610566605A CN 106203369 A CN106203369 A CN 106203369A
- Authority
- CN
- China
- Prior art keywords
- face
- stochastic
- dynamic
- module
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- 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
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
-
- 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
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Collating Specific Patterns (AREA)
Abstract
Active stochastic and dynamic for anti-counterfeiting recognition of face instructs generation system, face detection module, for locating human face, and extracts feature and is stored in data base.Face detection module triggers stochastic and dynamic directive generation module, generates the stochastic and dynamic instruction combination needing to be completed by target face, human eye, mouth.After stochastic and dynamic instruction sends, user to be identified, under system voice is pointed out, makes corresponding actions on request, and described action can be verified one by one by stochastic and dynamic command verification module.Target tracking module utilizes video frequency object tracking technology to follow the tracks of face, eye and mouth region continuously.After being differentiated by stochastic and dynamic command verification module, the face characteristic that face detection module is extracted, it is admitted to face recognition module and completes final authentication identification.The present invention is by increasing active stochastic and dynamic directive generation module, and stochastic and dynamic based on video tracking technology instruction reading module so that face identification system possesses effectively to put pretends to be function, substantially increases the safety of system.
Description
Technical field
The present invention relates to recognition of face anti-counterfeiting technical field, a kind of active for anti-counterfeiting recognition of face
Stochastic and dynamic instruction generation system.
Background technology
In recent years, face recognition technology is achieved with developing on a large scale very much and applying.But the face identification system that presently, there are, not
There are the deceptive practices that the non-living body information such as the most anti-photo or the video of pretending to be technology to differentiate to utilize shooting in advance are carried out.And
Current test alive needs to be equipped with special equipment, and the general network photographic head that domestic consumer is held by this is inapplicable, this
Greatly constrain the extensive application of face authentication system.Meanwhile, personation means variation brings to the research of detection technique
The biggest challenge.The personation fraud that face authentication system is conventional can be summarized as three classes:
1), the photo of validated user；
2), the video of validated user；
3), the threedimensional model of validated user.
To three of the above fraud, from the point of view of fidelity, photo and the video threedimensional model that compares is true to nature；From acquisition
For in approach, photo can pass through network, biographic information, the approach such as take on the sly easily gets, and video can also pass through pin hole
Photographic head easily photographs, and makes the threedimensional model more difficulty approaching true man's appearance.Therefore, photo and video are to take advantage of
Deceive the means that identification system is the most easy-to-use.Relatively for photo, video contains the life of the live bodies such as head movement, face action, nictation
Reason information, so the threat to the system of identification is bigger.If personation video is play before photographic head, usual people also is difficult to distinguish
Go out video or live body.At present, the detection technique of living body faces mainly has:
1) three-dimensional depth information analysis；
2) the physiological behavior detection of nictation and head movement etc.；
3) Fourier analysis；
4) Thermal Infra-Red etc..
From head movement, calculate the method for three-dimensional depth information and difference is lived by the blink detection method of physiological behavior of people
Body and photo are effective, but the most invalid for the video impersonation attack containing head movement and nictation.To certain famous brand name pen domestic
Remembering that the recognition of face power-on management system evaluation in this finds, work board, the notebook computer view screen of recorded video is even
The sketch picture of Freehandhand-drawing can easily be out-tricked identification system (http://my.tv.sohu.com/us/63365741/
32159567.shtml).And distinguish live body and photo with Fourier analysis, little according to the high fdrequency component being photo face
In living body faces, this method depends on the quality of image, and to light sensitive.Face's blood vessel is obtained with Thermal Infra-Red
The method of figure or face's thermogram then needs to add extra equipment.Present most recognition of face is based upon single
The image that photographic head obtains, does not the most increase extra detection equipment and realizes resisting the method that video attacks and become first-selected, its
Advantage is to be readily integrated in existing system.
Summary of the invention
The present invention provides a kind of active stochastic and dynamic for anti-counterfeiting recognition of face to instruct generation system, by increasing
Active stochastic and dynamic directive generation module, and stochastic and dynamic based on video tracking technology instruction reading module so that
Face identification system possesses effectively to put pretends to be function, substantially increases the safety of system.
The technical solution used in the present invention is:
Active stochastic and dynamic for anti-counterfeiting recognition of face instructs generation system, including face detection module, target
Tracking module, stochastic and dynamic directive generation module, stochastic and dynamic command verification module, face recognition module.
Described face detection module, for locating human face, and extracts feature and is stored in data base；
Face detection module triggers stochastic and dynamic directive generation module, generates and needs to be completed by target face, human eye, mouth
Stochastic and dynamic instruction combination；
After stochastic and dynamic instruction sends, user to be identified, under system voice is pointed out, makes corresponding actions on request, described
Action can be verified one by one by stochastic and dynamic command verification module；
Target tracking module utilizes video frequency object tracking technology to follow the tracks of face, eye and mouth region continuously；
If user to be identified is in dynamic instruction proof procedure, show suddenly video or other stage properties of recording, will
Destroy the seriality following the tracks of target, can be found in time by system, and terminate proof procedure；
After being differentiated by stochastic and dynamic command verification module, the face characteristic that face detection module is extracted, it is admitted to face
Identification module completes final authentication identification.
Each user can be obtained multiple samples pictures by face detection module.
When multiple faces occur, the human face target that only selecting scale is maximum is as target to be identified, the face that yardstick is maximum
Image represents the human face target near photographic head.
The type of stochastic and dynamic instruction, sequentially, length, execution time be all that dynamic random generates.
Target tracking module have employed and detects the on-line study tracking combined with tracking, utilizes random Haar feature
Extract object feature value, utilize random forest grader to realize the real-time detection of target to be tracked, in combination with KLT tracking
Target is tracked, follows the tracks of result and screen further and real-time update Sample Storehouse through detector, it is achieved on-line study.
The target tracking module face to tracing into, eye, mouth, utilize light stream to add up its motion vector, utilize the mesh that KLT provides
The direction of mark light stream result, it is achieved the interpretation that these are instructed.
A kind of active stochastic and dynamic for anti-counterfeiting recognition of face of the present invention instructs generation system, by increasing actively
The stochastic and dynamic directive generation module of formula, and stochastic and dynamic based on video tracking technology instruction reading module so that face
Identification system possesses effectively to put pretends to be function, substantially increases the safety of system.
Accompanying drawing explanation
Fig. 1 is the block diagram of system of the present invention.
Detailed description of the invention
Active stochastic and dynamic for anti-counterfeiting recognition of face instructs generation system, including face detection module, target
Tracking module, stochastic and dynamic directive generation module, stochastic and dynamic command verification module, face recognition module.
Operation principle:
First it is the sample characteristics storehouse typing of user's facial image.First user shows face, is imaged by common monocular
Head obtains video sequence, and system utilizes face detection module locating human face, and extracts feature and be stored in data base.In order to effectively build
Vertical Sample Storehouse, each user can be obtained multiple samples pictures by face detection module.
When identified object shows face, capture human face target by common camera.Face capture uses Viola-
Jones all-purpose detector completes.The present invention is only for single recognition of face, therefore, if there is multiple face to occur simultaneously, only selects chi
The human face target of degree maximum is as target to be identified.Because the facial image of yardstick maximum represents the face near photographic head
Target.
After system detects effective face, effective face here, refer to be detected simultaneously by eyes and face region
Front face target, Based PC A technology extracts human face target projection coefficient in each main composition, as face characteristic.Entering
Before the identification that row is final, first triggered stochastic and dynamic directive generation module by face detection module, generate and need by target person
The stochastic and dynamic instruction combination that face, human eye (left and right), mouth complete.Here " at random " includes two aspects, be first face,
Eye, mouth action type and the randomness of order.Show orientation, limit, upper and lower, left and right face image as turned one's head, open one's mouth, left and right,
Eyes close.Type coding corresponding to each action is as shown in table 1.
The type of action coding that the instruction of table 1 stochastic and dynamic is corresponding
| Type of action | Left face | Right face | Upper face | Lower face | Open one's mouth | Left eye closes | Right eye closes | Eyes close |
| Action encodes | A | B | C | D | E | F | G | H |
The length of stochastic and dynamic instruction and order are all that dynamic random generates, such as ACDH, GHCCB, EEFGGH.The opposing party
Face, the deadline interval of each action is random setting, completes as being probably 1,2,3 seconds.Dynamic instruction type, suitable
Sequence, length, the randomness of execution time so that user cannot utilize the video that records in advance reset to perform deceptive practices,
Because the number of combinations of this stochastic and dynamic instruction is huge, it is impossible to all store in advance.
With a length of 4 citings of fixed instruction, 4 continuous actions, the kind of stochastic and dynamic job sequence just has 84=4096
Kind；If command length increases to 8, then there are 16777216 kinds of combinations.If mixing again the execution time, when the most each action keeps
Between, system can keep certain action with voice message user until terminating, and can increase the most again 3 degree of freedom, be equivalent to action
Extended-type to 24 kinds (as a example by 3 kinds of execution time), this can the number of combinations of further exponential increase job sequence so that
Disabled user cannot realize employing checking instruction video sequence, reaches the anti-effect pretended to be.
After stochastic and dynamic instruction sends, user to be identified makes corresponding actions under system voice is pointed out on request, these
Action can be verified one by one by stochastic and dynamic command verification module.
In order to effectively verify that each instruction improves security of system, target tracking module of the present invention further simultaneously, utilization regards
Face, eye and mouth region are followed the tracks of by target following technology continuously frequently.If user to be identified is at dynamic instruction proof procedure
In show suddenly video or other stage properties of recording, the seriality following the tracks of target will be destroyed, this can be found in time by system,
And terminate proof procedure.
The video frequency object tracking technology that in the present invention, target tracking module is used, can use general monotrack skill
Art, as detected the track algorithm combined with Kalman filtering based on Blob；Pure track algorithm based on light stream can also be used,
Such as KLT algorithm, these are all classical conventional track algorithms.If photographic head shooting environmental is complex, can use detection with
The on-line study tracking that track combines, such as TLD.TLD utilizes random Haar feature extraction object feature value, utilizes the most gloomy
Woods grader realizes the real-time detection of target to be tracked, is tracked target in combination with KLT tracking, follows the tracks of result warp
Cross detector to screen further and real-time update Sample Storehouse, it is achieved on-line study, can reach preferable tracking effect.According to face
Follow the tracks of result, can calculate face area occur relative motion vectors, thus judge current face be left face, right face, on
Face still descends face, left and right, the action that comes back, bow of these face area correspondence numbers of people.
In the present invention, after human face region is detected, human eye and face region may utilize the general detection of Viola-Jones
Device is found.The detection open eyes, close one's eyes, open one's mouth, shut up, uses Viola-Jones all-purpose detector to complete too.At this
In invention, select 5000 positive samples (ocular opened and the mouth region of Guan Bi) and 10000 negative samples by differentiating
This (ocular of Guan Bi and the mouth region opened) trains the Adaboost grader in Viola-Jones, it is achieved open
Close one's eyes, an identification shut up.
After being differentiated by stochastic and dynamic command verification module, face detection module can extract face characteristic, then by feature
Send into face recognition module, complete final authentication identification.In the present invention, face characteristic extracts and selects Gabor amplitude
Feature, then utilizes LBP to extract the statistical nature of Gabor characteristic, finally by with the face that existed in face characteristic storehouse
Feature carries out coupling and realizes identifying.In the present invention, in the feature extraction algorithm in face detection module and face recognition module
Recognizer be to cooperate with carrying out, other face recognition algorithms are equally applicable.
Claims (6)
1. for anti-counterfeiting recognition of face active stochastic and dynamic instruction generation system, including face detection module, target with
Track module, stochastic and dynamic directive generation module, stochastic and dynamic command verification module, face recognition module, it is characterised in that: described
Face detection module, for locating human face, and extracts feature and is stored in data base；Face detection module triggers stochastic and dynamic instruction
Generation module, generates the stochastic and dynamic instruction combination needing to be completed by target face, human eye, mouth；Stochastic and dynamic instruction sends
After, user to be identified, under system voice is pointed out, makes corresponding actions on request, and described action can be by stochastic and dynamic command verification
Module is verified one by one；Target tracking module utilizes video frequency object tracking technology to follow the tracks of face, eye and mouth region continuously；
If user to be identified is in dynamic instruction proof procedure, shows suddenly video or other stage properties of recording, tracking will be destroyed
The seriality of target, can be found in time by system, and terminate proof procedure；After being differentiated by stochastic and dynamic command verification module,
The face characteristic that face detection module is extracted, is admitted to face recognition module and completes final authentication identification.
The most according to claim 1 for the active stochastic and dynamic instruction generation system of anti-counterfeiting recognition of face, its feature
It is: each user can be obtained multiple samples pictures by face detection module.
The most according to claim 1 for the active stochastic and dynamic instruction generation system of anti-counterfeiting recognition of face, its feature
Being: when multiple faces occur, the human face target that only selecting scale is maximum is as target to be identified, the facial image that yardstick is maximum
Represent the human face target near photographic head.
The most according to claim 1 for the active stochastic and dynamic instruction generation system of anti-counterfeiting recognition of face, its feature
Be: the type of stochastic and dynamic instruction, sequentially, length, execution time be all that dynamic random generates, and combination can infinitely be expanded
Exhibition.
The most according to claim 1 for the active stochastic and dynamic instruction generation system of anti-counterfeiting recognition of face, its feature
It is: target tracking module have employed and detects the on-line study tracking combined with tracking, utilizes random Haar feature to carry
Take object feature value, utilize random forest grader to realize the real-time detection of target to be tracked, in combination with KLT tracking pair
Target is tracked, and follows the tracks of result and screens further and real-time update Sample Storehouse through detector, it is achieved on-line study.
The most according to claim 1 for the active stochastic and dynamic instruction generation system of anti-counterfeiting recognition of face, its feature
It is: the target tracking module face to tracing into, eye, mouth, utilizes light stream to add up its motion vector, utilize the target that KLT provides
The direction of light stream result, it is achieved the interpretation that these are instructed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610566605.6A CN106203369A (en) | 2016-07-18 | 2016-07-18 | Active stochastic and dynamic for anti-counterfeiting recognition of face instructs generation system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610566605.6A CN106203369A (en) | 2016-07-18 | 2016-07-18 | Active stochastic and dynamic for anti-counterfeiting recognition of face instructs generation system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106203369A true CN106203369A (en) | 2016-12-07 |
Family
ID=57493990
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610566605.6A Pending CN106203369A (en) | 2016-07-18 | 2016-07-18 | Active stochastic and dynamic for anti-counterfeiting recognition of face instructs generation system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106203369A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107346422A (en) * | 2017-06-30 | 2017-11-14 | 成都大学 | A kind of living body faces recognition methods based on blink detection |
| CN107766785A (en) * | 2017-01-25 | 2018-03-06 | 丁贤根 | A kind of face recognition method |
| CN109740568A (en) * | 2019-01-21 | 2019-05-10 | 江西阳光安全设备集团有限公司 | Intelligent mobile rack with automatic damper |
| CN109977846A (en) * | 2019-03-22 | 2019-07-05 | 中国科学院重庆绿色智能技术研究院 | A kind of in-vivo detection method and system based on the camera shooting of near-infrared monocular |
| CN111368277A (en) * | 2019-11-21 | 2020-07-03 | 北汽福田汽车股份有限公司 | Vehicle starting method and device, storage medium and vehicle |
| TWI704490B (en) * | 2018-06-04 | 2020-09-11 | 和碩聯合科技股份有限公司 | Voice control device and method |
| CN111815828A (en) * | 2020-07-07 | 2020-10-23 | 中国联合网络通信集团有限公司 | Gate detection method, device and system |
| CN111860394A (en) * | 2020-07-28 | 2020-10-30 | 成都新希望金融信息有限公司 | Gesture estimation and gesture detection-based action living body recognition method |
| CN112949363A (en) * | 2019-12-11 | 2021-06-11 | 北京中电普华信息技术有限公司 | Face living body identification method and device |
| CN114283450A (en) * | 2021-12-23 | 2022-04-05 | 国网福建省电力有限公司信息通信分公司 | Identity recognition method and module for operating personnel for transformer substation |
| CN114677634A (en) * | 2022-05-30 | 2022-06-28 | 成都新希望金融信息有限公司 | Surface label identification method and device, electronic equipment and storage medium |
| CN116152936A (en) * | 2023-02-17 | 2023-05-23 | 深圳市永腾翼科技有限公司 | Face identity authentication system with interactive living body detection and method thereof |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103440479A (en) * | 2013-08-29 | 2013-12-11 | 湖北微模式科技发展有限公司 | Method and system for detecting living body human face |
| CN104751110A (en) * | 2013-12-31 | 2015-07-01 | 汉王科技股份有限公司 | Bio-assay detection method and device |
| CN105005779A (en) * | 2015-08-25 | 2015-10-28 | 湖北文理学院 | Face verification anti-counterfeit recognition method and system thereof based on interactive action |
| CN105138967A (en) * | 2015-08-05 | 2015-12-09 | 三峡大学 | Living body detection method and apparatus based on active state of human eye region |
| CN105260726A (en) * | 2015-11-11 | 2016-01-20 | 杭州海量信息技术有限公司 | Interactive video in vivo detection method based on face attitude control and system thereof |
| CN105426815A (en) * | 2015-10-29 | 2016-03-23 | 北京汉王智远科技有限公司 | Living body detection method and device |
| CN105518713A (en) * | 2015-02-15 | 2016-04-20 | 北京旷视科技有限公司 | Living human face verification method and system, computer program product |
-
2016
- 2016-07-18 CN CN201610566605.6A patent/CN106203369A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103440479A (en) * | 2013-08-29 | 2013-12-11 | 湖北微模式科技发展有限公司 | Method and system for detecting living body human face |
| CN104751110A (en) * | 2013-12-31 | 2015-07-01 | 汉王科技股份有限公司 | Bio-assay detection method and device |
| CN105518713A (en) * | 2015-02-15 | 2016-04-20 | 北京旷视科技有限公司 | Living human face verification method and system, computer program product |
| CN105138967A (en) * | 2015-08-05 | 2015-12-09 | 三峡大学 | Living body detection method and apparatus based on active state of human eye region |
| CN105005779A (en) * | 2015-08-25 | 2015-10-28 | 湖北文理学院 | Face verification anti-counterfeit recognition method and system thereof based on interactive action |
| CN105426815A (en) * | 2015-10-29 | 2016-03-23 | 北京汉王智远科技有限公司 | Living body detection method and device |
| CN105260726A (en) * | 2015-11-11 | 2016-01-20 | 杭州海量信息技术有限公司 | Interactive video in vivo detection method based on face attitude control and system thereof |
Non-Patent Citations (2)
| Title |
|---|
| 曹维华: "TLD框架下的多人脸目标跟踪算法设计与实现", 《三峡大学硕士学位论文》 * |
| 黄叶珏: "基于交互式随机动作的人脸活体检测", 《软件导刊》 * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107766785A (en) * | 2017-01-25 | 2018-03-06 | 丁贤根 | A kind of face recognition method |
| CN107346422A (en) * | 2017-06-30 | 2017-11-14 | 成都大学 | A kind of living body faces recognition methods based on blink detection |
| CN107346422B (en) * | 2017-06-30 | 2020-09-08 | 成都大学 | Living body face recognition method based on blink detection |
| TWI704490B (en) * | 2018-06-04 | 2020-09-11 | 和碩聯合科技股份有限公司 | Voice control device and method |
| US11158314B2 (en) | 2018-06-04 | 2021-10-26 | Pegatron Corporation | Voice control device and method |
| CN109740568A (en) * | 2019-01-21 | 2019-05-10 | 江西阳光安全设备集团有限公司 | Intelligent mobile rack with automatic damper |
| CN109977846A (en) * | 2019-03-22 | 2019-07-05 | 中国科学院重庆绿色智能技术研究院 | A kind of in-vivo detection method and system based on the camera shooting of near-infrared monocular |
| CN111368277A (en) * | 2019-11-21 | 2020-07-03 | 北汽福田汽车股份有限公司 | Vehicle starting method and device, storage medium and vehicle |
| CN112949363A (en) * | 2019-12-11 | 2021-06-11 | 北京中电普华信息技术有限公司 | Face living body identification method and device |
| CN111815828A (en) * | 2020-07-07 | 2020-10-23 | 中国联合网络通信集团有限公司 | Gate detection method, device and system |
| CN111860394A (en) * | 2020-07-28 | 2020-10-30 | 成都新希望金融信息有限公司 | Gesture estimation and gesture detection-based action living body recognition method |
| CN114283450A (en) * | 2021-12-23 | 2022-04-05 | 国网福建省电力有限公司信息通信分公司 | Identity recognition method and module for operating personnel for transformer substation |
| CN114677634A (en) * | 2022-05-30 | 2022-06-28 | 成都新希望金融信息有限公司 | Surface label identification method and device, electronic equipment and storage medium |
| CN116152936A (en) * | 2023-02-17 | 2023-05-23 | 深圳市永腾翼科技有限公司 | Face identity authentication system with interactive living body detection and method thereof |
| CN116152936B (en) * | 2023-02-17 | 2024-06-14 | 深圳市永腾翼科技有限公司 | Face identity authentication system with interactive living body detection and method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106203369A (en) | Active stochastic and dynamic for anti-counterfeiting recognition of face instructs generation system | |
| Jain et al. | 50 years of biometric research: Accomplishments, challenges, and opportunities | |
| Hadid et al. | Biometrics systems under spoofing attack: an evaluation methodology and lessons learned | |
| Fathy et al. | Face-based active authentication on mobile devices | |
| Parmar et al. | Face recognition methods & applications | |
| Hadid | Face biometrics under spoofing attacks: Vulnerabilities, countermeasures, open issues, and research directions | |
| Kähm et al. | 2d face liveness detection: An overview | |
| Wu et al. | Two-stream CNNs for gesture-based verification and identification: Learning user style | |
| Killioğlu et al. | Anti-spoofing in face recognition with liveness detection using pupil tracking | |
| CN108369785A (en) | Activity determination | |
| Li et al. | Mining key skeleton poses with latent svm for action recognition | |
| CN107480586B (en) | Face characteristic point displacement-based biometric photo counterfeit attack detection method | |
| Farrukh et al. | FaceRevelio: a face liveness detection system for smartphones with a single front camera | |
| Hossain et al. | Next generation identity verification based on face-gait Biometrics | |
| Damer et al. | Crazyfaces: Unassisted circumvention of watchlist face identification | |
| Ali et al. | Directional sensitivity of gaze-collinearity features in liveness detection | |
| Hossain et al. | Multimodal identity verification based on learning face and gait cues | |
| Ali et al. | Gaze stability for liveness detection | |
| Alsufyani et al. | Biometric presentation attack detection using gaze alignment | |
| Hossain et al. | Human identity verification by using physiological and behavioural biometric traits | |
| Yin et al. | Fusion of face recognition and facial expression detection for authentication: a proposed model | |
| Zhang et al. | A virtual proctor with biometric authentication for facilitating distance education | |
| Ohki et al. | Efficient spoofing attack detection against unknown sample using end-to-end anomaly detection | |
| Singh et al. | Student Surveillance System using Face Recognition | |
| Ennaama et al. | Comparative and analysis study of biometric systems |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161207 |
|
| RJ01 | Rejection of invention patent application after publication |