CN109977756A - A kind of online In vivo detection system - Google Patents
A kind of online In vivo detection system Download PDFInfo
- Publication number
- CN109977756A CN109977756A CN201910076348.1A CN201910076348A CN109977756A CN 109977756 A CN109977756 A CN 109977756A CN 201910076348 A CN201910076348 A CN 201910076348A CN 109977756 A CN109977756 A CN 109977756A
- Authority
- CN
- China
- Prior art keywords
- module
- face
- vivo
- online
- identification 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.)
- Withdrawn
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
- G06V40/172—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)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a kind of online In vivo detection systems, including vivo identification module, picture recognition module, video identification module, preprocessing module, face basic information collection module, face quality information acquisition module, online interface detection module, central processing module, data storage module and result display module.The beneficial effects of the present invention are: preprocessing module is to vivo identification module, geometric relationship between picture recognition module and the extracted human face region characteristic point of video identification module is analyzed and processed, extracted information is targetedly selected, avoid influence of the disturbing factor to testing result, face basic information collection module includes to face frame position, face Space Rotating angle, the information such as face confidence level are acquired, convenient for constructing the three-dimensional information of face, face quality information acquisition module judges blocking for face, illumination, fuzziness, the quality informations such as integrity degree, for judging whether the face uploaded complies with standard.
Description
Technical field
The present invention relates to a kind of In vivo detection, specially a kind of online In vivo detection system belongs to biological identification technology neck
Domain.
Background technique
With the further leap of artificial intelligence technology, artificial intelligence product more and more applies to real daily life, such as
Recognition of face and human face identification technology widely apply to the fields such as security protection, finance, In vivo detection be one of its key technology and
Important component, In vivo detection are for determining that target is that the technology of lived individual can be identified by In vivo detection
Target is living body, and the abiotic object such as non-photograph, is to guarantee the safe and reliable important means of face authentication result.Living body inspection
Survey purpose is i.e. correct to be distinguished real human face and attacks face, wherein attack face includes human face photo attack, the playback of face screen
The various attacks means such as attack, the attack of 3D face mask.
Existing online In vivo detection system, one, detection approach are more single, therefore cause the practicality poor, no
Convenient for promote, secondly, the face information for being recognized, can not the characteristic point to human face region targetedly mentioned
Take, and then will lead to disturbing factor when detecting and testing result is impacted, influence detection precision, thirdly, attack
Person synthesizes human face three-dimensional model in conjunction with three-dimensional imaging software using each plane picture on computer or smart machine, and shows
On the screen, the threedimensional model in screen makes specified movement according to prompt, can also be with successful attack face real-name authentication system
System, leads to the failure of human face in-vivo detection method.
Summary of the invention
The object of the invention is that providing a kind of online In vivo detection system to solve the above-mentioned problems.
The present invention is through the following technical solutions to achieve the above objectives: a kind of online In vivo detection system, including living body are known
Other module, picture recognition module, video identification module, preprocessing module, face basic information collection module, face quality information
Acquisition module, online interface detection module, central processing module, data storage module and result display module;The living body is known
Other module, picture recognition module and video identification module are in arranged in parallel, and the preprocessing module is arranged in vivo identification mould
Block, picture recognition module and video identification module and face basic information collection module and face quality information acquisition module it
Between, and the input terminal of the preprocessing module is defeated with vivo identification module, picture recognition module and video identification module respectively
Outlet is attached, and the output end of the preprocessing module is connected to face basic information collection module and face quality letter
The input terminal of acquisition module is ceased, and the face basic information collection module is set with face quality information acquisition module in parallel
It sets, the output end of the face basic information collection module and face quality information acquisition module is connected to central processing module
Input terminal, the input terminal of the online interface detection module and the output end of central processing module are attached, the data storage
The input terminal of storing module and the output end of central processing module are attached, the input terminal and centre of the result display module
The output end of reason module is attached.
Preferably, in order to make the system have a variety of identification methods, the vivo identification module is based on camera and carries out people
Face identification, picture recognition module are based on optical flow method and carry out recognition of face, and video identification module is based on SVM classifier or PLS is carried out
Recognition of face.
Preferably, the influence in order to avoid disturbing factor to testing result, the preprocessing module to vivo identification module,
Geometric relationship between picture recognition module and the extracted human face region characteristic point of video identification module carries out at analysis
Reason.
Preferably, for the ease of the three-dimensional information of building face, the face basic information collection module includes to face
Frame position, face Space Rotating angle, the information such as face confidence level are acquired.
Preferably, in order to judge whether the face uploaded complies with standard, the face quality information acquisition module judges people
The quality informations such as the blocking of face, illumination, fuzziness, integrity degree.
Preferably, described in order to which collected face information to be compared with the face in data storage module
Online interface detection module is equipped with similarity threshold values, and electrically connect with data storage module.
The beneficial effects of the present invention are: the online In vivo detection system design is rationally, vivo identification module is based on camera
Carry out recognition of face, picture recognition module be based on optical flow method carry out recognition of face, video identification module be based on SVM classifier or
PLS carries out recognition of face, so that the system is had a variety of identification methods, and then be applicable in a variety of environment and detected, preprocessing module
To the geometry between vivo identification module, picture recognition module and the extracted human face region characteristic point of video identification module
Relationship is analyzed and processed, and is targetedly selected extracted information, avoids disturbing factor to the shadow of testing result
It rings, face basic information collection module includes to face frame position, face Space Rotating angle, and the information such as face confidence level carry out
Acquisition, convenient for constructing the three-dimensional information of face, face quality information acquisition module judges the blocking of face, illumination, fuzziness, complete
The quality informations such as whole degree, for judging whether the face uploaded complies with standard, online interface detection module is equipped with similarity threshold values,
And electrically connect with data storage module, collected face information and the face in data storage module can be compared
It is right, and judge whether similarity is more than set threshold values, and then realize the on-line checking of living body.
Detailed description of the invention
Fig. 1 is schematic structural view of the invention.
In figure: 1, vivo identification module, 2, picture recognition module, 3, video identification module, 4, preprocessing module, 5, face
Basic information collection module, 6, face quality information acquisition module, 7, online interface detection module, 8, central processing module, 9,
Data storage module and 10, result display module.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Referring to Fig. 1, a kind of online In vivo detection system, including vivo identification module 1, picture recognition module 2, video are known
Other module 3, preprocessing module 4, face basic information collection module 5, face quality information acquisition module 6, line interface detect
Module 7, central processing module 8, data storage module 9 and result display module 10;The vivo identification module 1, picture recognition
Module 2 and video identification module 3 are in arranged in parallel, and the preprocessing module 4 is arranged in vivo identification module 1, picture recognition
Between module 2 and video identification module 3 and face basic information collection module 5 and face quality information acquisition module 6, and it is described
The input terminal of preprocessing module 4 respectively with the output end of vivo identification module 1, picture recognition module 2 and video identification module 3 into
Row connection, the output end of the preprocessing module 4 is connected to face basic information collection module 5 and face quality information is adopted
Collect the input terminal of module 6, and the face basic information collection module 5 is in be arranged in parallel with face quality information acquisition module 6,
The face basic information collection module 5 and the output end of face quality information acquisition module 6 are connected to central processing module 8
The output end of input terminal, the input terminal and central processing module 8 of the online interface detection module 7 is attached, the data
The input terminal of storage module 9 and the output end of central processing module 8 are attached, the input terminal of the result display module 10 with
The output end of central processing module 8 is attached.
The vivo identification module 1 is based on camera and carries out recognition of face, and picture recognition module 2 is based on optical flow method and carries out people
Face identification, video identification module 3 is based on SVM classifier or PLS carries out recognition of face, and the system is made to have a variety of identification methods,
And then be applicable in a variety of environment and detected, the preprocessing module 4 knows vivo identification module 1, picture recognition module 2 and video
Geometric relationship between the extracted human face region characteristic point of other module 3 is analyzed and processed, to extracted information into
Row targetedly selection, avoids influence of the disturbing factor to testing result, and the face basic information collection module 5 includes pair
Face frame position, face Space Rotating angle, the information such as face confidence level are acquired, convenient for constructing the three-dimensional information of face,
The face quality information acquisition module 6 judges the quality informations such as the blocking of face, illumination, fuzziness, integrity degree, for judging
Whether the face of upload complies with standard, the online interface detection module 7 be equipped with similarity threshold values, and with data storage module 9
It electrically connects, collected face information can be compared with the face in data storage module 9, and judge similarity
Whether it is more than set threshold values, and then realizes the on-line checking of living body.
Working principle: when using the online In vivo detection system, according to detection environment, vivo identification module 1, figure are selected
Piece identification module 2 or video identification module 3 is one such or a variety of carry out recognitions of face, and pass through 4 pairs of institutes of preprocessing module
Geometric relationship between the human face region characteristic point of extraction is analyzed and processed, and then online interface detection module 7 will adopt
The face information collected is compared with the face in data storage module 9, and judges whether similarity is more than set valve
Value, and then realize the on-line checking of living body, it finally will test structure and shown via result display module 10.
It is obvious to a person skilled in the art that invention is not limited to the details of the above exemplary embodiments, Er Qie
In the case where without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, the present embodiments are to be considered as illustrative and not restrictive, and the scope of the present invention is by appended power
Benefit requires rather than above description limits, it is intended that all by what is fallen within the meaning and scope of the equivalent elements of the claims
Variation is included within the present invention.Any reference signs in the claims should not be construed as limiting the involved claims.
In addition, it should be understood that although this specification is described in terms of embodiments, but not each embodiment is only wrapped
Containing an independent technical solution, this description of the specification is merely for the sake of clarity, and those skilled in the art should
It considers the specification as a whole, the technical solutions in the various embodiments may also be suitably combined, forms those skilled in the art
The other embodiments being understood that.
Claims (6)
1. a kind of online In vivo detection system, it is characterised in that: including vivo identification module (1), picture recognition module (2), view
Frequency identification module (3), preprocessing module (4), face basic information collection module (5), face quality information acquisition module (6),
Online interface detection module (7), central processing module (8), data storage module (9) and result display module (10);The work
Body identification module (1), picture recognition module (2) and video identification module (3) are in arranged in parallel, the preprocessing module (4)
It is arranged in vivo identification module (1), picture recognition module (2) and video identification module (3) and face basic information collection module
(5) between face quality information acquisition module (6), and the input terminal of the preprocessing module (4) respectively with vivo identification mould
The output end of block (1), picture recognition module (2) and video identification module (3) is attached, the preprocessing module (4) it is defeated
Outlet is connected to the input terminal of face basic information collection module (5) and face quality information acquisition module (6), and described
Face basic information collection module (5) with face quality information acquisition module (6) in being arranged in parallel, adopt by the face basic information
The output end of collection module (5) and face quality information acquisition module (6) is connected to the input terminal of central processing module (8), described
The output end of the input terminal and central processing module (8) of online interface detection module (7) is attached, the data storage module
(9) input terminal and the output end of central processing module (8) are attached, and the input terminal of the result display module (10) is in
The output end of centre processing module (8) is attached.
2. a kind of online In vivo detection system according to claim 1, it is characterised in that: the vivo identification module (1)
Recognition of face is carried out based on camera, picture recognition module (2) is based on optical flow method and carries out recognition of face, video identification module (3)
Recognition of face is carried out based on SVM classifier or PLS.
3. a kind of online In vivo detection system according to claim 1, it is characterised in that: the preprocessing module (4) is right
Between vivo identification module (1), picture recognition module (2) and the extracted human face region characteristic point of video identification module (3)
Geometric relationship is analyzed and processed.
4. a kind of online In vivo detection system according to claim 1, it is characterised in that: the face basic information collection
Module (5) includes to face frame position, face Space Rotating angle, and the information such as face confidence level are acquired.
5. a kind of online In vivo detection system according to claim 1, it is characterised in that: the face quality information acquisition
Module (6) judges the quality informations such as the blocking of face, illumination, fuzziness, integrity degree.
6. a kind of online In vivo detection system according to claim 1, it is characterised in that: the online interface detection module
(7) it is equipped with similarity threshold values, and is electrically connect with data storage module (9).
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910076348.1A CN109977756A (en) | 2019-01-26 | 2019-01-26 | A kind of online In vivo detection system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910076348.1A CN109977756A (en) | 2019-01-26 | 2019-01-26 | A kind of online In vivo detection system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109977756A true CN109977756A (en) | 2019-07-05 |
Family
ID=67076774
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910076348.1A Withdrawn CN109977756A (en) | 2019-01-26 | 2019-01-26 | A kind of online In vivo detection system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109977756A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110929583A (en) * | 2019-10-26 | 2020-03-27 | 湖北讯獒信息工程有限公司 | High-detection-precision face recognition method |
CN110956103A (en) * | 2019-11-20 | 2020-04-03 | 湖南检信智能科技有限公司 | Image feature extraction method based on face fuzzy judgment correction |
-
2019
- 2019-01-26 CN CN201910076348.1A patent/CN109977756A/en not_active Withdrawn
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110929583A (en) * | 2019-10-26 | 2020-03-27 | 湖北讯獒信息工程有限公司 | High-detection-precision face recognition method |
CN110956103A (en) * | 2019-11-20 | 2020-04-03 | 湖南检信智能科技有限公司 | Image feature extraction method based on face fuzzy judgment correction |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108009528B (en) | Triple Loss-based face authentication method and device, computer equipment and storage medium | |
CN107609383B (en) | 3D face identity authentication method and device | |
CN108985134B (en) | Face living body detection and face brushing transaction method and system based on binocular camera | |
CN106780906B (en) | A kind of testimony of a witness unification recognition methods and system based on depth convolutional neural networks | |
Islam et al. | Efficient detection and recognition of 3D ears | |
CN103426016B (en) | Method and device for authenticating second-generation identity card | |
CN105740780B (en) | Method and device for detecting living human face | |
US20090135188A1 (en) | Method and system of live detection based on physiological motion on human face | |
CN107590430A (en) | Biopsy method, device, equipment and storage medium | |
CN105930709A (en) | Method and apparatus for applying human face identification technology to witness testimony consistency check | |
CN102262727A (en) | Method for monitoring face image quality at client acquisition terminal in real time | |
CN110688901A (en) | Face recognition method and device | |
CN112364827B (en) | Face recognition method, device, computer equipment and storage medium | |
CN207264409U (en) | The testimony of a witness veritifies device | |
CN101556717A (en) | ATM intelligent security system and monitoring method | |
CN108734067A (en) | A kind of authentication method, system and camera that the testimony of a witness compares | |
CN103996033B (en) | Human identification method based on tracking of human face five-sense-organ coordinates | |
CN110555931A (en) | Face detection and gate inhibition system device based on deep learning recognition | |
CN107194361A (en) | Two-dimentional pose detection method and device | |
CN102629320A (en) | Ordinal measurement statistical description face recognition method based on feature level | |
CN107609515B (en) | Double-verification face comparison system and method based on Feiteng platform | |
CN110503760A (en) | Access control method and access control system | |
CN108875556A (en) | Method, apparatus, system and the computer storage medium veritified for the testimony of a witness | |
CN111862413A (en) | Method and system for realizing epidemic situation resistant non-contact multidimensional identity rapid identification | |
CN111710031A (en) | Method for breaking password of intelligent terminal device by counterfeiting portrait |
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 | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20190705 |
|
WW01 | Invention patent application withdrawn after publication |