CN110298335A - Face identification system and face identification method - Google Patents
Face identification system and face identification method Download PDFInfo
- Publication number
- CN110298335A CN110298335A CN201910614136.4A CN201910614136A CN110298335A CN 110298335 A CN110298335 A CN 110298335A CN 201910614136 A CN201910614136 A CN 201910614136A CN 110298335 A CN110298335 A CN 110298335A
- Authority
- CN
- China
- Prior art keywords
- face
- rendering
- face identification
- image
- mould group
- 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 22
- 238000009877 rendering Methods 0.000 claims abstract description 42
- 238000001514 detection method Methods 0.000 claims abstract description 14
- 238000012545 processing Methods 0.000 claims abstract description 14
- 238000004891 communication Methods 0.000 claims description 6
- 230000002452 interceptive effect Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 12
- 238000005516 engineering process Methods 0.000 description 11
- 238000013461 design Methods 0.000 description 3
- 230000001815 facial effect Effects 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 241000209202 Bromus secalinus Species 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000007639 printing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
-
- 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
Landscapes
- Engineering & Computer Science (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)
- Human Computer Interaction (AREA)
- Collating Specific Patterns (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a kind of face identification system and face identification method, face identification systems, comprising: acquisition module, for acquiring the 3D rendering and 2D image of target face；Processing module is judging that 3D rendering is very 2D image to be compared with pre-stored skin detection afterwards, and export recognition result according to comparison result for judging the true and false of the 3D rendering；Acquisition module includes 3D face acquisition mould group and 2D face acquisition mould group, and 3D face acquisition mould group is used to acquire the 3D rendering of target face, and 2D face acquisition mould group is used to acquire the 2D image of target face.The present invention is by combining the judgement of 3D face detection and 2D recognition of face, judge that target face is genuine 3D rendering using 3D information, or 2D image or video, to improve antifalse effect, 2D image is recycled to be compared, to promote the accuracy of identification, not only antifalse effect is good for the face identification system in this way, while recognition accuracy is high.
Description
Technical field
The present invention relates to technical field of face recognition, more particularly to a kind of face identification system and recognition of face
Method.
Background technique
It is well known that face recognition application is widely and universal at present, application field covers family, enterprise's machine
Structure, social management, public security Guoan etc..Current face recognition technology is 2D facial image identification technology at present --- pass through
Common camera, camera, mobile phone etc. acquire facial image, carry out comparison of classification in systems.With being constantly progressive for system, especially
The importing of its artificial intelligence technology (neural network, deep learning etc.), the accuracy of Face recognition are distinguished considerably beyond human eye
The accuracy of knowledge becomes one of maximum bright spot of artificial intelligence application.
But identification accuracy does not simultaneously solve anti-fake problem.The problem of face identification system maximum at present, is exactly so-called
" picture attack " cheats face that is, using the face picture or mobile phone, plate, the screen face picture of computer or video of printing
Automatic recognition system can break through almost all of face currently on the market by the various pictures and video prepared meticulously really
Automatic system.So this is the current maximum pain spot of this market application, therefore 3D face identification system comes into being.
Current 3D automatic human face recognition system is generally divided into three parts:
One, 3D face information acquire, now there are three types of common technique acquisition face 3D information: structured light technique, TOF technology with
And binocular determination techniques.By these types of technology, the 3D information of face can be collected；
Two, 3D face models: by above-mentioned several collected 3D face informations of technology, special software being needed to carry out 3D face
Modeling generates 3D faceform；
Three, 3D Face recognition: by special 3D face recognition algorithms, being compared identification to 3D face template, completes
Judgement.
3D face technology can solve 2D picture or video attack problem really, but they have following limitation:
First is that several 3D information acquiring technologies, although each be all on theoretical principle it is disclosed, in specific implementation
Without unified standard, each manufacturer is all that designed, designed proprietary system is acquired, this causes initial data (Raw data) that can not lead to
With；
Second is that 3D modeling needs algorithm software, because Raw data is inconsistent, the 3D modeling algorithm software of each family is affirmed also not
Together, thus generate 3D face template, also can not be general；
Third is that the accuracy and uniqueness of 3D face template, are temporarily confirmed extensively not yet, so, it is automatic to 3D face
The accuracy of recognizer is currently to leave a question open.In addition to the accuracy and uniqueness of 3D face template are not confirmed, mention above
And 3D face template do not have unified standard, cause to be difficult to collect and construct huge 3D face template library, to training algorithm (packet
Include deep learning), this is that the accuracy of 3D Face recognition algorithm fails to obtain the main reason for industry is generally acknowledged at present.No
Huge database is trained and is fed, and the progress of recognizer will very slowly.
Therefore, how to design that a kind of antifalse effect is good, at the same the high face recognition scheme of recognition accuracy be one urgently
Problem to be solved.
Summary of the invention
The features and advantages of the present invention partly state in the following description, or can from the description it is clear that or
Person can pass through practice present invention study.
It is good that the object of the present invention is to provide a kind of antifalse effects, while the face identification system and face that recognition accuracy is high
Recognition methods.
It is as follows that the present invention solves technical solution used by above-mentioned technical problem: providing a kind of face identification system, comprising:
Acquisition module, for acquiring the 3D rendering and 2D image of target face；
Processing module for judging the true and false of the 3D rendering, and is judging that the 3D rendering is very afterwards by the 2D image
It is compared with pre-stored skin detection, and recognition result is exported according to comparison result.
The acquisition module includes 3D face acquisition mould group and 2D face acquisition mould group, and 3D face acquisition mould group is for acquiring
The 3D rendering of target face, 2D face acquisition mould group are used to acquire the 2D image of target face.
The face identification system further includes the output module connecting with the processing module, and the recognition result passes through institute
Output module is stated to be exported.
The output module include serial ports, USB interface, TCP/IP interface, WIFI communication mould group, in bluetooth communication mould group
It is one or more.
The face identification system further includes the interactive module connecting with the output module.
The processing module is also used to judging that the 3D rendering is false output recognition result later.
The present invention also provides a kind of face identification methods, comprising the following steps:
Acquire the 3D rendering and 2D image of target face；
Judge the true and false of the 3D rendering；
If the 3D rendering is true, then the 2D image is compared with pre-stored skin detection, and according to comparison
As a result recognition result is exported.
If comparing successfully, pass through；If comparing failure, do not pass through.
If the 3D rendering is vacation, do not pass through.
If comparing successfully, pass through；If continuous compare repeatedly failure, do not pass through.
The present invention judges that target face is using 3D information by combining the judgement of 3D face detection and 2D recognition of face
Genuine 3D rendering or 2D image or video recycle 2D image to be compared, to mention to improve antifalse effect
The accuracy of identification is risen, not only antifalse effect is good for the face identification system in this way, while recognition accuracy is high.
Detailed description of the invention
Fig. 1 is the schematic diagram of face identification system in the embodiment of the present invention.
Fig. 2 is the flow chart of face identification method in the embodiment of the present invention.
Specific embodiment
As shown in Figure 1, the face identification system proposed in the embodiment of the present invention, including acquisition module 10 and processing module
20, acquisition module 10 is used to acquire the 3D rendering and 2D image of target face.Processing module 20 for judging the true and false of 3D rendering,
Judging that 3D rendering is that very 2D image is compared with pre-stored skin detection afterwards, and exports according to comparison result
Recognition result, and judging that 3D rendering is false output recognition result later.By the way that the judgement of 3D face detection and 2D face are known
It does not combine, judges that target face is genuine 3D rendering or 2D image or video using 3D information is judged, to improve anti-
Pseudo- effect recycles 2D image to be compared, to promote the accuracy of identification, the face identification system is not only anti-fake in this way
Effect is good, while recognition accuracy is high.
Comparison result is success or failure, and recognition result is to pass through or do not pass through.When comparison result is successfully, recognition result
To pass through；When comparison result is failure, recognition result is not pass through.Judge that 3D rendering is to export after vacation not passing through.
Skin detection, the i.e. various characteristic points of face, characteristic area, feature line and angle etc..
In the present embodiment, acquisition module 10 includes that 3D face acquisition mould group 11 and 2D face acquire mould group 12, and 3D face is adopted
Collection mould group 11 is used to acquire the 3D rendering of target face, and 2D face acquisition mould group 12 is used to acquire the 2D image of target face.
3D face acquisition mould group 11 can be structured light technique, TOF(flight time) technology, binocular determination techniques and its
Any one of his 3D information acquiring technology, but it is not limited to these types of technology.3D face acquires mould group 11 and measures skill using binocular
When art, 3D face acquisition mould group 11 and 2D face acquisition 12 Integration Design of mould group is integrated.
2D face acquisition mould group 12 takes the photograph camera lens and headlamp including near infrared device, visible light pair.
Processing module 20 has calculation processing platform and storage unit, and is integrated with 2D facial image algorithm, 3D face figure
As judging software.Processing module 20 has the function of 3D rendering judgement and 2D Face recognition, and comprehensive according to the result of the two
Determine, obtains final recognition result.
Face identification system further includes the output module 30 connecting with processing module 20, and recognition result passes through the output mould
Block is exported.Output module 30 is including in serial ports, USB interface, TCP/IP interface, WIFI communication mould group, bluetooth communication mould group
It is one or more.
Processing module 20 is nested on output module 30 in design, and the two can also be designed as to a module, form
On be combined into one, functionally distinguish.
Face identification system further includes the interactive module 40 connecting with output module 30, for interacting with user.It hands over
Mutual module includes one of display screen, keyboard, radio-frequency card read head or a variety of.
As shown in Fig. 2, the present invention also provides a kind of face identification methods, comprising the following steps:
Acquire the 3D rendering and 2D image of target face；
Judge the true and false of the 3D rendering；
If 3D rendering is true, then 2D image is compared with pre-stored skin detection, and according to comparison result come defeated
Recognition result out.
By the above method, 3D recognition of face and 2D recognition of face are combined, judge target person using 3D rendering is judged
Face is genuine 3D rendering or 2D image or video, to improve antifalse effect, 2D image is recycled to be compared, thus
The accuracy of identification is promoted, not only antifalse effect is good for the face identification system in this way, while recognition accuracy is high.
The detailed process of the face identification method is as follows:
Step S1, acquires the 3D rendering and 2D image of target face, then executes step S2；
Step S2 judges the true and false of 3D rendering, if 3D rendering is true, execution step S3；If 3D rendering is false, execution step S4；
2D image is compared with pre-stored skin detection, then executes step S5 by step S3；
Step S4, does not pass through；
Step S5, if compare successfully, if comparing successfully (has and the matched face of target face), execute step S6；If
Failure (i.e. with the matched face of target face) is compared, step S4 or step S3 is executed, compares that multiple (number can if continuous
To be set according to application scenarios) failure, execute step S4；
Step S6, passes through.
Face identification system and face identification method proposed by the present invention, by the judgement of 3D face detection and 2D recognition of face knot
It closes, judges that target face is genuine 3D rendering or 2D image or video using 3D information is judged, to improve anti-fake effect
Fruit recycles 2D image to be compared, to promote the accuracy of identification, the face identification system not only antifalse effect in this way
It is good, while recognition accuracy is high；And this 3D face detection judgement and 2D recognition of face combine, relative to complete 3D face
Identification also has system more simplified, cost is lower, speed faster, more low-power consumption, performance be more preferable and the advantages such as smaller volume, tool
There is broad mass market prospect.
Preferred embodiments of the present invention have been described above with reference to the accompanying drawings, and those skilled in the art do not depart from the scope of the present invention
And essence, there are many variations to implement the present invention.For example, it is shown as part of one embodiment or describes
Feature can be used for another embodiment to obtain another embodiment.The above is only a preferred and feasible embodiment of the present invention, not
Therefore limiting the scope of the invention, it is all with equivalence changes made by description of the invention and accompanying drawing content, it is both contained in
Within interest field of the invention.
Claims (10)
1. a kind of face identification system characterized by comprising
Acquisition module, for acquiring the 3D rendering and 2D image of target face；
Processing module for judging the true and false of the 3D rendering, and is judging that the 3D rendering is very afterwards by the 2D image
It is compared with pre-stored skin detection, and recognition result is exported according to comparison result.
2. face identification system according to claim 1, which is characterized in that the acquisition module includes 3D face acquisition mould
Group and 2D face acquire mould group, and 3D face acquisition mould group is used to acquire the 3D rendering of target face, and 2D face acquisition mould group is used for
Acquire the 2D image of target face.
3. face identification system according to claim 1, which is characterized in that the face identification system further include with it is described
The output module of processing module connection, the recognition result are exported by the output module.
4. face identification system according to claim 3, which is characterized in that the output module includes that serial ports, USB connect
One of mouth, TCP/IP interface, WIFI communication mould group, bluetooth communication mould group are a variety of.
5. face identification system according to claim 1 or 3, which is characterized in that the face identification system further include with
The interactive module of the output module connection.
6. face identification system according to claim 1, which is characterized in that the processing module is also used to described in the judgement
3D rendering is false output recognition result later.
7. a kind of face identification method, which comprises the following steps:
Acquire the 3D rendering and 2D image of target face；
Judge the true and false of the 3D rendering；
If the 3D rendering is true, then the 2D image is compared with pre-stored skin detection, and according to comparison
As a result recognition result is exported.
8. face identification method according to claim 7, which is characterized in that if comparing successfully, pass through；It is lost if comparing
It loses, does not then pass through.
9. face identification method according to claim 7, which is characterized in that if the 3D rendering is vacation, do not pass through.
10. face identification method according to claim 7, which is characterized in that if comparing successfully, pass through；If continuous ratio
To multiple failure, then do not pass through.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910614136.4A CN110298335A (en) | 2019-07-09 | 2019-07-09 | Face identification system and face identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910614136.4A CN110298335A (en) | 2019-07-09 | 2019-07-09 | Face identification system and face identification method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110298335A true CN110298335A (en) | 2019-10-01 |
Family
ID=68030793
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910614136.4A Pending CN110298335A (en) | 2019-07-09 | 2019-07-09 | Face identification system and face identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110298335A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013131407A1 (en) * | 2012-03-08 | 2013-09-12 | 无锡中科奥森科技有限公司 | Double verification face anti-counterfeiting method and device |
| WO2017162076A1 (en) * | 2016-03-24 | 2017-09-28 | 北京握奇数据股份有限公司 | Face identification method and system |
| CN107832677A (en) * | 2017-10-19 | 2018-03-23 | 深圳奥比中光科技有限公司 | Face identification method and system based on In vivo detection |
| CN109068119A (en) * | 2018-09-18 | 2018-12-21 | 信利光电股份有限公司 | A kind of camera module structure |
| CN109255319A (en) * | 2018-09-02 | 2019-01-22 | 珠海横琴现联盛科技发展有限公司 | For the recognition of face payment information method for anti-counterfeit of still photo |
| CN109522798A (en) * | 2018-10-16 | 2019-03-26 | 平安科技（深圳）有限公司 | Video anticounterfeiting method, system, device based on vivo identification and can storage medium |
-
2019
- 2019-07-09 CN CN201910614136.4A patent/CN110298335A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013131407A1 (en) * | 2012-03-08 | 2013-09-12 | 无锡中科奥森科技有限公司 | Double verification face anti-counterfeiting method and device |
| WO2017162076A1 (en) * | 2016-03-24 | 2017-09-28 | 北京握奇数据股份有限公司 | Face identification method and system |
| CN107832677A (en) * | 2017-10-19 | 2018-03-23 | 深圳奥比中光科技有限公司 | Face identification method and system based on In vivo detection |
| CN109255319A (en) * | 2018-09-02 | 2019-01-22 | 珠海横琴现联盛科技发展有限公司 | For the recognition of face payment information method for anti-counterfeit of still photo |
| CN109068119A (en) * | 2018-09-18 | 2018-12-21 | 信利光电股份有限公司 | A kind of camera module structure |
| CN109522798A (en) * | 2018-10-16 | 2019-03-26 | 平安科技（深圳）有限公司 | Video anticounterfeiting method, system, device based on vivo identification and can storage medium |
Non-Patent Citations (3)
| Title |
|---|
| 蔡维克;: "生物识别技术的新星――三维人脸识别技术", 智能建筑电气技术, vol. 1, no. 05, pages 42 - 43 * |
| 陈继民等: "3D打印基础教程", 国防工业出版社, pages: 26 - 29 * |
| 陈继民等: "应用模式识别技术导论", 31 October 2004, 上海交通大学出版社, pages: 107 - 108 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11380119B2 (en) | Pose-aligned networks for deep attribute modeling | |
| CN112651348B (en) | Identity authentication method and device and storage medium | |
| US9607138B1 (en) | User authentication and verification through video analysis | |
| CN108124486A (en) | Face living body detection method based on cloud, electronic device and program product | |
| CN106991390A (en) | A kind of hand-held testimony of a witness Compare System and method based on deep learning | |
| CN107341481A (en) | It is identified using structure light image | |
| CN101558431A (en) | Face authentication device | |
| US10915739B2 (en) | Face recognition device, face recognition method, and computer readable storage medium | |
| CN107844742B (en) | Facial image glasses minimizing technology, device and storage medium | |
| CN111144284B (en) | Method and device for generating depth face image, electronic equipment and medium | |
| CN106897659A (en) | The recognition methods of blink motion and device | |
| CN110796101A (en) | Face recognition method and system of embedded platform | |
| CN109871751A (en) | Attitude appraisal procedure, device and storage medium based on facial expression recognition | |
| RU2315352C2 (en) | Method and system for automatically finding three-dimensional images | |
| CN112580472A (en) | Rapid and lightweight face recognition method and device, machine readable medium and equipment | |
| CN108416298A (en) | A kind of scene judgment method and terminal | |
| RU2316051C2 (en) | Method and system for automatically checking presence of a living human face in biometric safety systems | |
| CN106156739B (en) | A kind of certificate photo ear detection and extracting method based on face mask analysis | |
| CN111582145A (en) | Biometric identification method, electronic device, and computer-readable storage medium | |
| CN116758643A (en) | Method and device for detecting deeply forged face image | |
| CN110298335A (en) | Face identification system and face identification method | |
| CN115311723A (en) | Living body detection method, living body detection device and computer-readable storage medium | |
| CN110866508B (en) | Method, device, terminal and storage medium for identifying form of target object | |
| CN113536914A (en) | Object tracking identification method, system, equipment and medium | |
| CN114373213A (en) | Juvenile identity recognition method and device based on face 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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200806 Address after: 523000, 26, 188 Industrial Road, Pingshan Town, Guangdong, Dongguan, Tangxia Applicant after: Entropy Technology Co., Ltd Address before: 361003, Xiamen Software Park, Fujian Province, three, Chengyi North Street, No. 22, 8, 01 units Applicant before: ZKWEWIN (XIAMEN) INTEGRATED CIRCUIT Co.,Ltd. |
|
| TA01 | Transfer of patent application right |