CN110008820A - A kind of silence biopsy method - Google Patents
A kind of silence biopsy method Download PDFInfo
- Publication number
- CN110008820A CN110008820A CN201910093824.0A CN201910093824A CN110008820A CN 110008820 A CN110008820 A CN 110008820A CN 201910093824 A CN201910093824 A CN 201910093824A CN 110008820 A CN110008820 A CN 110008820A
- Authority
- CN
- China
- Prior art keywords
- feature
- living body
- face
- face frame
- module
- 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 20
- 238000001574 biopsy Methods 0.000 title claims abstract description 11
- 238000000605 extraction Methods 0.000 claims abstract description 10
- 230000001815 facial effect Effects 0.000 claims abstract description 7
- 239000000284 extract Substances 0.000 claims abstract description 6
- 238000000513 principal component analysis Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 description 14
- 238000005516 engineering process Methods 0.000 description 8
- 238000001727 in vivo Methods 0.000 description 7
- 230000009471 action Effects 0.000 description 3
- 210000000887 face Anatomy 0.000 description 3
- 210000003128 head Anatomy 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- 241000700605 Viruses Species 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 210000000720 eyelash Anatomy 0.000 description 2
- 210000000744 eyelid Anatomy 0.000 description 2
- 238000005242 forging Methods 0.000 description 2
- 230000005021 gait Effects 0.000 description 2
- 208000015181 infectious disease Diseases 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 201000005111 ocular hyperemia Diseases 0.000 description 2
- 210000001747 pupil Anatomy 0.000 description 2
- 230000029058 respiratory gaseous exchange Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 241000593989 Scardinius erythrophthalmus Species 0.000 description 1
- 208000003443 Unconsciousness Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 208000024754 bloodshot eye Diseases 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
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
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- 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
-
- 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
- G06V40/40—Spoof detection, e.g. liveness detection
- G06V40/45—Detection of the body part being alive
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The present invention discloses a kind of silent biopsy method, include following steps: (1) face frame extracts: the positioning and extraction of face location is realized using face frame extraction module, what face frame extraction module extracted arrives input of the face frame as feature modeling；(2) face Partial Feature models: the feature of facial image is extracted using feature modeling module, to be characterized, and input of the output of feature modeling module as categorization module；(3) classify: feature is sent into classifier, realize that the classification of living body and non-living body judges.By using the method for the present invention, only need camera dynamic crawl facial image, living body judgement can be carried out, effectively solve dynamic instruction living body verify cumbersome disadvantage, reduce artificial participation amount, can be realized whether the judgement of living body.
Description
Technical field
The present invention relates to field of face identification technologies, refer in particular to a kind of silent biopsy method.
Background technique
In biological recognition system, to prevent malicious person from forging and stealing other people biological characteristic for authentication, life
Object identifying system need to have the function of In vivo detection, that is, judge whether the biological characteristic submitted comes from lived individual.
What the In vivo detection technology of general biological characteristic utilized is the physiological characteristic of people, such as living body finger print detection can be with
Temperature based on finger, perspire, information, the living body faces detection such as electric conductivity can movement, breathing, blood-shot eye illness effect based on head
Should wait information, living body iris detection can motion information based on iris chatter characteristic, eyelashes and eyelid, pupil to visible light source
Shrinkage expansion response characteristic of intensity etc..
As face recognition technology reaches its maturity, commercial applications are further extensive, however face easily uses photo, video etc.
Mode is replicated, therefore is the important threat of recognition of face Yu Verification System safety to the personation of legitimate user's face.At present
Silent biopsy method based on single photo or video frame, has been achieved for certain progress.
In vivo detection is mainly dynamic In vivo detection at present, and dynamic In vivo detection is to prevent malicious person from forging and stealing other people
Biological characteristic be used for authentication, biological recognition system need to have the function of In vivo detection, that is, judge that the biological characteristic submitted is
It is no to come from lived individual.
What general In vivo detection technology utilized is the physiological characteristic of people, such as living body finger print detection can be based on finger
Temperature perspires, the information such as electric conductivity, living body faces detection can the information such as movement, breathing, red-eye effect based on head,
Living body iris detection can motion information based on iris chatter characteristic, eyelashes and eyelid, pupil to the receipts of visible light source intensity
Reducing and expansion response characteristic etc..
Dynamic human face detects identification technology compared with other biological feature identification technique, has in practical applications natural only
To advantage: directly acquired by camera, identification process can be completed in a non-contact manner, it is convenient and efficient.Dynamic people at present
Face detection identification technology has been supplied in the fields such as finance, education, scenic spot, trip's fortune, social security.Realization process mainly passes through blink, opens
Mouth shakes the head, puts first-class combinative movement cooperation, it is ensured that operation is true living body faces, and defect is that instruction action is cumbersome, needs
Artificially cooperate on one's own initiative.
Summary of the invention
In view of this, in view of the deficiencies of the prior art, the present invention aims to provide a kind of silent living bodies to examine
Survey method can effectively solve the problem of existing dynamic biopsy method instruction action is cumbersome, needs are artificially cooperated on one's own initiative.
To achieve the above object, the present invention is using following technical solution:
A kind of silence biopsy method, includes following steps:
(1) face frame extracts: the positioning and extraction of face location is realized using face frame extraction module, face frame extracts mould
What block extracted arrives input of the face frame as feature modeling；
(2) face Partial Feature models: the feature of facial image is extracted using feature modeling module, it is special to be characterized
Levy input of the output of modeling module as categorization module；
(3) classify: feature is sent into classifier, realize that the classification of living body and non-living body judges.
Preferably, SURF is used in the step (2), is calculated and is generated Feature Descriptor, and is retouched these features using PCA
It states son and projects to principal component, then carry out principal component coding using GMM, obtain the condition code that a length is 76800, finally send
Enter the classification of SVM bis-.
Preferably, LBP feature is added while introducing PCA principal component analysis.
The present invention has obvious advantages and beneficial effects compared with the existing technology, specifically, by above-mentioned technical proposal
Known to:
By using the method for the present invention, camera dynamic crawl facial image is only needed, living body judgement can be carried out, effectively solved
Certainly dynamic instruction living body verifies cumbersome disadvantage, reduces artificial participation amount, can be realized whether the judgement of living body, without movement refer to
Cooperation is enabled, can go out in a shorter time as a result, speed is fast, whether in conscious and unconscious situation, not influence
Testing result, different and Gait Recognition can imitate and change, block without carrying, recognition speed is fast, operation the conscious day after tomorrow
It is simple and convenient, it is not necessarily to contact arrangement, it is not only hygienic without worrying the contagious infection of virus, but also safety.
Detailed description of the invention
Fig. 1 is the flow diagram of the preferred embodiments of the invention.
Specific embodiment
Present invention discloses a kind of silent biopsy methods, as shown in Figure 1, including following steps:
(1) face frame extracts: the positioning and extraction of face location is realized using face frame extraction module, face frame extracts mould
What block extracted arrives input of the face frame as feature modeling.
(2) face Partial Feature models: the feature of facial image is extracted using feature modeling module, it is special to be characterized
Levy input of the output of modeling module as categorization module.
(3) classify: feature is sent into classifier, realize that the classification of living body and non-living body judges.
In the present embodiment, SURF is used in step (2), is calculated and is generated Feature Descriptor, and utilizes PCA by these features
Description projects to principal component, then carries out principal component coding using GMM, obtains the condition code that a length is 76800, finally
SVM bis- is sent into classify.Also, LBP feature is added while introducing PCA principal component analysis, realizes the inspection again of double characteristic, to increase
The robust performance of computation system.
Main code of program of the invention:
Major Mathematics formula of the invention:
1, PCA:
Algorithm flow
It is assumed that we need characteristic dimension dropping to k dimension from n dimension.Then the execution process of PCA is as follows:
1. feature normalization balances each characteristic dimension:
μjIt is characterized the mean value of j, sjIt is characterized the standard deviation of j.
2. calculating covariance matrix ∑:
3. seeking the feature vector (eigenvectors) of ∑ by singular value decomposition (SVD):
(U, S, VT)=SVD (∑)
4. k left singular vectors before taking out from U, constitute one and about subtract matrix U reduce:
Ureduce=(u(1), u(2)..., u(k))
5. calculating new feature vector: z(i)
2、LBP
Wherein,
Design focal point of the invention is: by using the method for the present invention, only needing camera dynamic crawl facial image
Living body judgement is carried out, dynamic instruction living body is effectively solved and verifies cumbersome disadvantage, reduce artificial participation amount, can be realized and whether live
The judgement of body is not necessarily to action command and cooperates, and can go out in a shorter time as a result, speed is fast, whether consciously and unintentionally
In the case where knowledge, testing result is not influenced, different and Gait Recognition can imitate and change the conscious day after tomorrow, without carrying
Card, recognition speed is fast, simple and convenient, is not necessarily to contact arrangement, not only hygienic without worrying the contagious infection of virus, but also peace
Entirely.
The technical principle of the invention is described above in combination with a specific embodiment.These descriptions are intended merely to explain of the invention
Principle, and shall not be construed in any way as a limitation of the scope of protection of the invention.Based on the explanation herein, the technology of this field
Personnel can associate with other specific embodiments of the invention without creative labor, these modes are fallen within
Within protection scope of the present invention.
Claims (3)
1. a kind of silence biopsy method, it is characterised in that: include following steps:
(1) face frame extracts: the positioning and extraction of face location is realized using face frame extraction module, face frame extraction module mentions
What is taken arrives input of the face frame as feature modeling；
(2) face Partial Feature models: the feature of facial image is extracted using feature modeling module, to be characterized, feature is built
Input of the output of mould module as categorization module；
(3) classify: feature is sent into classifier, realize that the classification of living body and non-living body judges.
2. silence biopsy method as described in claim 1, it is characterised in that: use SURF in the step (2), calculate
Feature Descriptor is generated, and these Feature Descriptors are projected into principal component using PCA, then carries out principal component volume using GMM
Code, obtains the condition code that a length is 76800, is finally sent into SVM bis- and classifies.
3. silence biopsy method as claimed in claim 2, it is characterised in that: add while introducing PCA principal component analysis
Enter LBP feature.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910093824.0A CN110008820A (en) | 2019-01-30 | 2019-01-30 | A kind of silence biopsy method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910093824.0A CN110008820A (en) | 2019-01-30 | 2019-01-30 | A kind of silence biopsy method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110008820A true CN110008820A (en) | 2019-07-12 |
Family
ID=67165642
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910093824.0A Pending CN110008820A (en) | 2019-01-30 | 2019-01-30 | A kind of silence biopsy method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110008820A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111310177A (en) * | 2020-03-17 | 2020-06-19 | 北京安为科技有限公司 | Video monitoring equipment attack detection system based on memory behavior characteristics |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101999900A (en) * | 2009-08-28 | 2011-04-06 | 南京壹进制信息技术有限公司 | Living body detecting method and system applied to human face recognition |
| CN105023010A (en) * | 2015-08-17 | 2015-11-04 | 中国科学院半导体研究所 | Face living body detection method and system |
| CN106408037A (en) * | 2015-07-30 | 2017-02-15 | 阿里巴巴集团控股有限公司 | Image recognition method and apparatus |
| CN107798281A (en) * | 2016-09-07 | 2018-03-13 | 北京眼神科技有限公司 | A kind of human face in-vivo detection method and device based on LBP features |
| CN108564049A (en) * | 2018-04-22 | 2018-09-21 | 北京工业大学 | A kind of fast face detection recognition method based on deep learning |
| CN109101925A (en) * | 2018-08-14 | 2018-12-28 | 成都智汇脸卡科技有限公司 | Biopsy method |
-
2019
- 2019-01-30 CN CN201910093824.0A patent/CN110008820A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101999900A (en) * | 2009-08-28 | 2011-04-06 | 南京壹进制信息技术有限公司 | Living body detecting method and system applied to human face recognition |
| CN106408037A (en) * | 2015-07-30 | 2017-02-15 | 阿里巴巴集团控股有限公司 | Image recognition method and apparatus |
| CN105023010A (en) * | 2015-08-17 | 2015-11-04 | 中国科学院半导体研究所 | Face living body detection method and system |
| CN107798281A (en) * | 2016-09-07 | 2018-03-13 | 北京眼神科技有限公司 | A kind of human face in-vivo detection method and device based on LBP features |
| CN108564049A (en) * | 2018-04-22 | 2018-09-21 | 北京工业大学 | A kind of fast face detection recognition method based on deep learning |
| CN109101925A (en) * | 2018-08-14 | 2018-12-28 | 成都智汇脸卡科技有限公司 | Biopsy method |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111310177A (en) * | 2020-03-17 | 2020-06-19 | 北京安为科技有限公司 | Video monitoring equipment attack detection system based on memory behavior characteristics |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Dargan et al. | A comprehensive survey on the biometric recognition systems based on physiological and behavioral modalities | |
| Manjani et al. | Detecting silicone mask-based presentation attack via deep dictionary learning | |
| Agarwal et al. | Face recognition using principle component analysis, eigenface and neural network | |
| Chellappa et al. | Face recognition by computers and humans | |
| Bharadwaj et al. | Domain specific learning for newborn face recognition | |
| Agarwal et al. | Face recognition using eigen faces and artificial neural network | |
| Shao et al. | Genealogical face recognition based on ub kinface database | |
| Kumar et al. | Real time face recognition using adaboost improved fast PCA algorithm | |
| Wei et al. | Research on face feature extraction based on K-mean algorithm | |
| Candra et al. | Classification of facial-emotion expression in the application of psychotherapy using Viola-Jones and Edge-Histogram of Oriented Gradient | |
| Dixit et al. | A survey on facial expression recognition using machine learning techniques | |
| Ahmed et al. | A state of art for survey of combined iris and fingerprint recognition systems | |
| Cimmino et al. | M2FRED: Mobile masked face REcognition through periocular dynamics analysis | |
| Boncolmo et al. | Gender Identification Using Keras Model Through Detection of Face | |
| Aslam et al. | Gender classification based on isolated facial features and foggy faces using jointly trained deep convolutional neural network | |
| CN110008820A (en) | A kind of silence biopsy method | |
| Mustafa et al. | Cross-Cultural Facial Expression Recogniton Using Gradient Features And Support Vector Machine | |
| Roy et al. | Ear Biometric: A Deep Learning Approach | |
| Yong et al. | Facial expression monitoring system using pca-bayes classifier | |
| TW201839635A (en) | Emotion detection system and method | |
| Frank et al. | Automatic pixel selection for optimizing facial expression recognition using eigenfaces | |
| Sulaiman et al. | A systematic review on Evaluation of Driver Fatigue Monitoring Systems based on Existing Face/Eyes Detection Algorithms | |
| Rokita et al. | Multimodal biometrics by face and hand images taken by a cell phone camera | |
| Ratliff | Active appearance models for affect recognition using facial expressions | |
| Frank et al. | Optimizing eigenfaces by face masks for facial expression recognition |
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: 20190712 |
|
| RJ01 | Rejection of invention patent application after publication |