CN107169405A - Method and device based on binocular camera vivo identification - Google Patents
Method and device based on binocular camera vivo identification Download PDFInfo
- Publication number
- CN107169405A CN107169405A CN201710160685.XA CN201710160685A CN107169405A CN 107169405 A CN107169405 A CN 107169405A CN 201710160685 A CN201710160685 A CN 201710160685A CN 107169405 A CN107169405 A CN 107169405A
- Authority
- CN
- China
- Prior art keywords
- face
- binocular camera
- key point
- facial image
- camera
- 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.)
- Granted
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
- 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
- G06V40/40—Spoof detection, e.g. liveness detection
- G06V40/45—Detection of the body part being alive
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Measurement Of Optical Distance (AREA)
Abstract
The present invention provides a kind of method based on binocular camera vivo identification, including：Using binocular camera acquisition target in visible ray with distinguishing corresponding facial image under infrared light；Extract each self-corresponding face key point in two kinds of light servant's face images；Obtain destination object and be reflected in face key point coordinate vector in the binocular camera；Ranging is carried out according to face key point coordinate vector, facial image is calculated to the distance of video camera；Under the light source of same frequency and same distance, within a preset range whether whether the luminous intensity of calculating face key point coordinate vector, be live body according to the object that result of calculation judges to provide face.The present invention also provides a kind of device based on binocular camera vivo identification.In the case where obtaining the light source frequency, the luminous intensity reflected according to unlike material under same distance differentiates whether the object is live body, without extra purchase miscellaneous equipment, saves cost of manufacture.
Description
Technical field
The present invention relates to technical field of face recognition, more particularly to a kind of method based on binocular camera vivo identification
And device.
Background technology
Constantly updated with the technology of security protection, face recognition technology is applied also more and more extensive in life.Especially in political affairs
Mansion department, frontier juncture and financial industry, there is irreplaceable intelligent safety monitoring to security protection.Face recognition technology
Reach its maturity, further extensively, still, face is easily replicated commercial applications with modes such as photo, videos, therefore to legal
The personation of user's face, is recognition of face, and especially living body faces identification Verification System constitutes important threat.In these years,
Living body faces detection technique has made some progress, but in the security reliability and cost-effectivenes of the existing method of practical application
Very high balance can not be obtained.
However, existing living body faces identification technology, mainly detects whether to meet face by a common camera
Feature, the entity head portrait such as the plastic cement being still easily counterfeited is out-tricked.Also have plenty of by professional infra-red radiation imaging lens,
By scanning the trickle biological characteristic of living human face, in addition it is trickle to the vascular distribution inside live body face can be seen.But
This equipment is very expensive, and this, which has been resulted in, can only be adapted to some specific occasions, and can not be widely used.
The content of the invention
The shortcoming of prior art, binocular camera live body is based on it is an object of the invention to provide one kind in view of the above
The method and device of identification, for solving that the problem of whether face object is live body differentiated in the prior art.
In order to achieve the above objects and other related objects, the present invention provides a kind of side based on binocular camera vivo identification
Method, including：
Using binocular camera acquisition target in visible ray with distinguishing corresponding facial image under infrared light；
Extract each self-corresponding face key point in two kinds of light frequency servant's face images；
Obtain destination object and be reflected in face key point coordinate vector in the binocular camera；
Ranging is carried out according to face key point coordinate vector, facial image is calculated to the distance of video camera；
Under the light source of same frequency and same distance, whether the luminous intensity of face key point coordinate vector is calculated default
In the range of, whether it is live body according to the object that result of calculation judges to provide face.
Another object of the present invention is to provide a kind of device based on binocular camera vivo identification, including：
Acquisition module, using binocular camera acquisition target in visible ray with distinguishing corresponding facial image under infrared light；
Extraction module, for extracting each self-corresponding face key point in two kinds of light frequency servant's face images；
Acquisition module, face key point coordinate vector in the binocular camera is reflected in for obtaining destination object；
Computing module, for according to face key point coordinate vector carry out ranging, calculate facial image to video camera away from
From；
Processing module, under the light source of same frequency and same distance, calculates the luminous intensity of face key point coordinate vector
Whether within a preset range, whether the object for judging to provide face according to result of calculation is live body.
As described above, the method and device based on binocular camera vivo identification of the present invention, has the advantages that：
By the present invention in that with the facial image of binocular camera acquisition target, obtaining object reflection in binocular camera
Face key point coordinate vector in facial image, destination object is calculated to binocular camera by face key point coordinate vector
Distance, obtain the light source frequency in the case of, this pair is differentiated according to the luminous intensity that unlike material reflects under same distance
As if no is live body, without extra purchase miscellaneous equipment, such as：Multi-frequency light source, multi-frequency receiver, save system
Make cost.
Brief description of the drawings
Fig. 1 is shown as a kind of method flow diagram based on binocular camera vivo identification that the present invention is provided；
Fig. 2 is shown as one kind of the invention provided and is based on binocular camera range measurement principle figure；
Fig. 3 is shown as step S5 flow charts in a kind of method based on binocular camera vivo identification in Fig. 1；
Fig. 4-a, 4-b are shown as the face object of skin and paper material respectively in 1450nm light sources and 850nm light source
The corresponding reflective light intensity graph of a relation of each comfortable different distance；
It is corresponding with each comfortable different distance of 850nm light source that Fig. 5 is shown as a kind of 1450nm light sources of the invention provided
Reflective light intensity graph of a relation；
Fig. 6 is shown as a kind of apparatus structure block diagram in binocular camera vivo identification that the present invention is provided；
Fig. 7 is shown as the structural frames of processing module in a kind of device based on binocular camera ranging that the present invention is provided
Figure.
Component label instructions：
1 acquisition module
2 extraction modules
3 acquisition modules
4 computing modules
5 processing modules
51 processing units
52 judging units
Embodiment
Illustrate embodiments of the present invention below by way of specific instantiation, those skilled in the art can be by this specification
Disclosed content understands other advantages and effect of the present invention easily.The present invention can also pass through specific realities different in addition
The mode of applying is embodied or practiced, the various details in this specification can also based on different viewpoints with application, without departing from
Various modifications or alterations are carried out under the spirit of the present invention.It should be noted that, in the case where not conflicting, following examples and implementation
Feature in example can be mutually combined.
It should be noted that the diagram provided in following examples only illustrates the basic structure of the present invention in a schematic way
Think, then in schema only display with relevant component in the present invention rather than according to component count, shape and the size during actual implement
Draw, it is actual when implementing, and kenel, quantity and the ratio of each component can be a kind of random change, and its assembly layout kenel
It is likely more complexity.
Referring to Fig. 1, a kind of method flow diagram based on binocular camera vivo identification that the present invention is provided is shown as, bag
Include：
Step S1, using binocular camera acquisition target in visible ray with distinguishing corresponding facial image under infrared light；
Wherein, the binocular camera one of them be visible light camera, another is thermal camera, for same
Object distinguishes recorded video information, detects that the human face region of the video information generates corresponding facial image.
Step S2, extracts each self-corresponding face key point in two kinds of light frequency servant's face images；
Wherein, the recognition methods based on geometric properties, is described according to the gamma characteristic perspective view and feature of facial image recognition
The algorithmic preliminaries matched determine the position of face each several part.Then, accurately determined using sciagraphy and template matching method
The position of pupil and other facial characteristics, so as to reach the purpose for extracting face key point.
Step S3, obtains destination object and is reflected in face key point coordinate vector in the binocular camera；
Wherein, binocular camera is corresponded to respectively according to selected object in visible ray with distinguishing corresponding face figure under infrared light
Picture, determines its face key point coordinate vector of the correspondence in each facial image.
Step S4, ranging is carried out according to face key point coordinate vector, calculates facial image to the distance of video camera；
Wherein, by the same face key feature points of the facial image corresponding to binocular camera, based on binocular tri-dimensional
Feel ranging, calculate facial image to the distance of video camera.
Step S5, under the light source of same frequency and same distance, calculating the luminous intensity of face key point coordinate vector is
It is no within a preset range, according to result of calculation judge provide face object whether be live body.
By the present invention in that with the facial image of binocular camera acquisition target, obtaining object reflection in binocular camera
Face key point coordinate vector in facial image, destination object is calculated to binocular camera by face key point coordinate vector
Distance, obtain the light source frequency in the case of, this pair is differentiated according to the luminous intensity that unlike material reflects under same distance
As if no is live body, without extra purchase miscellaneous equipment, such as：Multi-frequency light source, multi-frequency receiver, save system
Make cost.
In the present embodiment, also include before step S 4：Key point to same face by the way of frame is average is sat
Mark vector is averaged, and calculates the average coordinates value for obtaining each key point.Two relative to traditional binocular camera are taken the photograph
The face that camera is detected directly extracts face key point and obtains its coordinate of the correspondence on image, it is to avoid because binocular camera shooting
The difference of machine visual angle difference, illumination effect and infrared/visible ray can cause critical point detection to be forbidden, then or, binocular camera
The deviation of several pixels occurs in the testing result for being directed to same key point, and condition is turned what focal length of camera and baseline were fixed
Under, it is easy to influence distance measurement result.And by the way of frame is average, the image such as continuous 3 or 5 frames, for the key of same face
Point vectorial coordinate is averaged, and calculates the average coordinates value of each key point, so that preferably stablize key point, it is effective to reduce
Distance caused by crucial point tolerance is floated.
In the present embodiment, as shown in Fig. 2 being based on binocular camera range measurement principle figure, bag for one kind that the present invention is provided
The mathematical modeling of a set of perfect standard binocular camera is included, x (Left) and x (Right) represent that same point is imaged in left and right respectively
Horizontal level on machine picture, is the video camera that two parameter identicals are placed in parallel, wherein, one is infrared ray, another
For visible ray, it is respectively focus in the coordinate of real object, baseline distance B two ends correspondence left images that P points, which are, they and P points it
Between correspondence in the imaging point of left and right figure, depth and parallax are inversely.F is the focal length of binocular camera, and T is binocular camera shooting
The baseline distance of machine.Parallax is defined as d=x (Right)-x (Left).Depth Z values can be derived using similar triangles
Wherein, influence of the baseline distance of binocular camera to ranging is larger, and baseline distance is bigger, and range accuracy is higher.
As shown in figure 3, being shown as step S5 flows in a kind of method based on binocular camera vivo identification in Fig. 1
Figure, including：
Step S5.1, under the same distance of same frequency, the light intensity that the facial image according to corresponding to unlike material is received
Degree is different；The luminous intensity of face key point coordinate vector is calculated using Lambertian reflection models；
Wherein, the light source of the same frequency can use wave band simultaneously for 1450nm and 850nm light source, obtain object-point
The intensity of reflected light at (x, y) place can be represented：
I (x, y)=A0 (x, y) * r (x, y) * cos θ (x, y) (1)
A0 (x, y) represents the luminous intensity received at point (x, y) place, and r (x, y) represents the material reflectivity at point (x, y) place,
Angle between the normal vector and receiver at θ (x, y) expressions face point (x, y) place, wherein, light intensity decays are represented by A0=A
θ-cd, wherein, A is light source intensity, and c is the decay factor in air, and d is the distance between light source and receiver, and we can be with
It is D (d) this simplified formula, it is a monotonous descending function on distance between light source and receiver, is rewritten into
Formula (2)：
I (x, y)=A (x, y) * r (x, y) * cos θ (x, y) * D (d) (2)
The luminous intensity received in a specified range can be obtained in the following manner, wherein, AVE is variance
Value：
Represent in the luminous intensity and material reflectivity and distance dependent under same light source, received, it is same in same distance
Under one material, the luminous intensity of the different frequency received is different, and under the same distance of same frequency, the difference received
The luminous intensity of material is different, and such as Fig. 4-a, 4-b are respectively indicated as skin and the face object of paper material exists respectively
The corresponding reflective light intensity graph of a relation of each comfortable different distance of 1450nm light sources and 850nm light source, wherein, Fig. 4-a be skin with
The light intensity that the face object of paper material is received under 1450nm light sources in different distance respectively, Fig. 4-b are skin and paper material
The light intensity that the face object of matter is received under 850nm light sources in different distance respectively, with equidistant non-skin material face (paper
Matter photo) light intensity that substantially reflects is higher than the face of skin material.Fig. 5 for a kind of 1450nm light sources for providing of the present invention with
Each comfortable different distance of 850nm light source corresponding reflective light intensity graph of a relation, wherein, there are high-quality photo, quality general
The reflective light intensity of real human face respectively under different light sources under photo and skin, by being 20 to 40cm this model in distance
Enclose in value, can clearly distinguish the face face of skin material and papery material, that is, whether the object for distinguishing offer face is living
Body.
The above method is necessary not only for two kinds of extra non-visible light sources, in addition it is also necessary to corresponding receiver, product design
Trouble.And can not be operated in the existing equipment of current user.Preferred Lambertian reflection models, pin in the application
Be not only for the luminous intensity that the same area is received it is relevant with material refractive index, meanwhile, be also the monotone decreasing letter on distance
Number, therefore, the binocular camera system of a visible ray and a thermal camera composition utilize the infrared photography under 850nm
Machine gathers face or scraps of paper face intensity of reflected light (gray value) under this frequency, meanwhile, estimate people using binocular camera
Face make use of the average strategy of frame to stablize crucial point coordinates as far as possible to the distance of video camera, pass through stable crucial point coordinates
Face is just stabilized to the distance of video camera.Distance by obtained luminous intensity (gray value) and now, by the data of collection
Do one and divide judgement.
Whether within a preset range step S5.2, judge the luminous intensity, if it is, the object for providing the face is
Live body；If it is not, then the object for providing face is not live body.
In the present embodiment, the light source of same frequency is selected, is reflected according to the light source of different frequency under different distance
Gray value, can significantly distinguish pixel, reach differentiate object whether be live body purpose.If luminous intensity (gray value) is pre-
If in scope, then judging the object for live body, if luminous intensity (gray value) not within a preset range, judges that the object is not
Live body.
Specifically, in the present embodiment, using grader, such as SVM is trained, you can whether differentiation is live body, typically
Coverage between 34~90cm.The reflective light intensity image selected in this application is the baseline distance based on binocular camera
It is acquired during for 17mm, and baseline distance 100mm or bigger baseline distance binocular camera shooting system are typically used, it can further improve
Differentiate face whether be live body accuracy.
As shown in fig. 6, for another object of the present invention is to provide a kind of device based on binocular camera vivo identification,
Including：
Acquisition module 1, using binocular camera acquisition target in visible ray with distinguishing corresponding facial image under infrared light；
Extraction module 2, for extracting each self-corresponding face key point in two kinds of light servant's face images；
Acquisition module 3, face key point coordinate vector in the binocular camera is reflected in for obtaining destination object；
Computing module 4, for according to face key point coordinate vector carry out ranging, calculate facial image to video camera away from
From；
Processing module 5, under the light source of same frequency and same distance, calculates the luminous intensity of face key point coordinate vector
Whether within a preset range, whether the object for judging to provide face according to result of calculation is live body.
As shown in fig. 7, being the structure of processing module in a kind of device based on binocular camera ranging of the invention provided
Block diagram, including：
Processing unit 51, under the same distance of same frequency, the facial image according to corresponding to unlike material to be received
Luminous intensity it is different；The luminous intensity of face key point coordinate vector is calculated using Lambertian reflection models；
Judging unit 52, for whether within a preset range to judge the luminous intensity, if it is, providing the face
Object is live body；If it is not, then the object for providing face is not live body.
In summary, by the present invention in that with the facial image of binocular camera acquisition target, obtaining object reflection double
Face key point coordinate vector in the facial image of lens camera, calculates destination object by face key point coordinate vector and arrives
The distance of binocular camera, in the case where obtaining the light source frequency, the light intensity reflected according to unlike material under same distance
Degree differentiates whether the object is live body, without extra purchase miscellaneous equipment, such as：Multi-frequency light source, multi-frequency are received
Device, saves cost of manufacture.So, the present invention effectively overcomes various shortcoming of the prior art and has high industrial exploitation value
Value.
The above-described embodiments merely illustrate the principles and effects of the present invention, not for the limitation present invention.It is any ripe
Know the personage of this technology all can carry out modifications and changes under the spirit and scope without prejudice to the present invention to above-described embodiment.Cause
This, those of ordinary skill in the art is complete without departing from disclosed spirit and institute under technological thought such as
Into all equivalent modifications or change, should by the present invention claim be covered.
Claims (10)
1. a kind of method based on binocular camera vivo identification, it is characterised in that including：
Using binocular camera acquisition target in visible ray with distinguishing corresponding facial image under infrared light；
Extract each self-corresponding face key point in two kinds of light frequency servant's face images；
Obtain destination object and be reflected in face key point coordinate vector in the binocular camera；
Ranging is carried out according to face key point coordinate vector, facial image is calculated to the distance of video camera；
Under the light source of same frequency and same distance, whether the luminous intensity of face key point coordinate vector is calculated in preset range
It is interior, whether it is live body according to the object that result of calculation judges to provide face.
2. the method according to claim 1 based on binocular camera vivo identification, it is characterised in that described according to face
Before the step of key point coordinate vector carries out ranging, in addition to：
The key point coordinate vector of same face is averaged by the way of frame is average, calculates and obtains the flat of each key point
Equal coordinate value.
3. the method according to claim 1 based on binocular camera vivo identification, it is characterised in that the utilization binocular
Camera acquisition object visible ray with infrared light distinguish corresponding facial image the step of, including：
One of them is visible light camera to the binocular camera, and another is thermal camera, is distinguished for same target
Recorded video information, detects that the human face region of the video information generates corresponding facial image.
4. the method according to claim 1 based on binocular camera vivo identification, it is characterised in that the calculating face
Image to video camera apart from the step of, including：
By the same face key feature points of the facial image corresponding to binocular camera, based on binocular stereo vision ranging, meter
Facial image is calculated to the distance of video camera.
5. the method according to claim 1 based on binocular camera vivo identification, it is characterised in that the calculating face
Within a preset range whether whether the luminous intensity of key point coordinate vector, be living according to the object that result of calculation judges to provide face
The step of body, including：
Under the same distance of same frequency, the luminous intensity that the facial image according to corresponding to unlike material is received is different；Using
Lambertian reflection models calculate the luminous intensity of face key point coordinate vector；
Whether within a preset range the luminous intensity is judged, if it is, the object for providing the face is live body；If no
It is that then the object of offer face is not live body.
6. a kind of device based on binocular camera vivo identification, it is characterised in that including：
Acquisition module, using binocular camera acquisition target in visible ray with distinguishing corresponding facial image under infrared light；
Extraction module, for extracting each self-corresponding face key point in two kinds of light frequency servant's face images；
Acquisition module, face key point coordinate vector in the binocular camera is reflected in for obtaining destination object；
Computing module, for carrying out ranging according to face key point coordinate vector, calculates facial image to the distance of video camera；
Processing module, under the light source of same frequency and same distance, whether the luminous intensity of calculating face key point coordinate vector
Within a preset range, whether the object that root judges to provide face according to result of calculation is live body.
7. the device according to claim 6 based on binocular camera vivo identification, it is characterised in that the computing module
Include before：
Optimization module, is averaged by the way of frame is average to the key point coordinate vector of same face, and calculating obtains each
The average coordinates value of key point.
8. the device according to claim 6 based on binocular camera vivo identification, it is characterised in that the acquisition module
Specifically include：
One of them is visible light camera to the binocular camera, and another is thermal camera, is distinguished for same target
Recorded video information, detects that the human face region of the video information generates corresponding facial image.
9. the device according to claim 6 based on binocular camera vivo identification, it is characterised in that the computing module
Specifically include：
By the same face key feature points of the facial image corresponding to binocular camera, based on binocular stereo vision ranging, meter
Facial image is calculated to the distance of video camera.
10. the device according to claim 6 based on binocular camera vivo identification, it is characterised in that the processing mould
Block includes：
Processing unit, under the same distance of same frequency, the light intensity that the facial image according to corresponding to unlike material is received
Degree is different；The luminous intensity of face key point coordinate vector is calculated using Lambertian reflection models；
Judging unit, for whether within a preset range to judge the luminous intensity, if it is, the object for providing the face is
Live body；If it is not, then the object for providing face is not live body.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710160685.XA CN107169405B (en) | 2017-03-17 | 2017-03-17 | Method and device for living body identification based on binocular camera |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710160685.XA CN107169405B (en) | 2017-03-17 | 2017-03-17 | Method and device for living body identification based on binocular camera |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107169405A true CN107169405A (en) | 2017-09-15 |
| CN107169405B CN107169405B (en) | 2020-07-03 |
Family
ID=59848776
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710160685.XA Active CN107169405B (en) | 2017-03-17 | 2017-03-17 | Method and device for living body identification based on binocular camera |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107169405B (en) |
Cited By (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107832712A (en) * | 2017-11-13 | 2018-03-23 | 深圳前海微众银行股份有限公司 | Biopsy method, device and computer-readable recording medium |
| CN107992811A (en) * | 2017-11-27 | 2018-05-04 | 北京小米移动软件有限公司 | Face identification method and device |
| CN108535252A (en) * | 2018-02-23 | 2018-09-14 | 广州市派客朴食信息科技有限责任公司 | A kind of binocular stereo vision food recognition methods |
| CN108629305A (en) * | 2018-04-27 | 2018-10-09 | 朱旭辉 | A kind of face recognition method |
| CN108629298A (en) * | 2018-04-23 | 2018-10-09 | Oppo广东移动通信有限公司 | Face identification method, electronic device and non-volatile computer readable storage medium storing program for executing |
| CN109376643A (en) * | 2018-10-16 | 2019-02-22 | 杭州悉住信息科技有限公司 | Face identification method and system |
| CN109376595A (en) * | 2018-09-14 | 2019-02-22 | 杭州宇泛智能科技有限公司 | Monocular RGB camera in-vivo detection method and system based on human eye attention |
| CN109685014A (en) * | 2018-12-25 | 2019-04-26 | 努比亚技术有限公司 | Face recognition method, device, mobile terminal and storage medium |
| CN110163097A (en) * | 2019-04-16 | 2019-08-23 | 深圳壹账通智能科技有限公司 | Discrimination method, device, electronic equipment and the storage medium of three-dimensional head portrait true or false |
| CN110765923A (en) * | 2019-10-18 | 2020-02-07 | 腾讯科技（深圳）有限公司 | Face living body detection method, device, equipment and storage medium |
| CN110796067A (en) * | 2019-10-27 | 2020-02-14 | 恒大智慧科技有限公司 | Automatic early warning method, device and storage medium for vehicle starting in intelligent community |
| CN110826366A (en) * | 2018-08-10 | 2020-02-21 | 北京魔门塔科技有限公司 | Face image acquisition system for data analysis at night |
| CN110909693A (en) * | 2019-11-27 | 2020-03-24 | 深圳市华付信息技术有限公司 | 3D face living body detection method and device, computer equipment and storage medium |
| CN111079473A (en) * | 2018-10-19 | 2020-04-28 | 北京奇虎科技有限公司 | Gender identification method, gender identification device, electronic equipment and computer-readable storage medium |
| CN111209870A (en) * | 2020-01-09 | 2020-05-29 | 杭州涂鸦信息技术有限公司 | Binocular living body camera rapid registration method, system and device thereof |
| CN111382654A (en) * | 2018-12-29 | 2020-07-07 | 北京市商汤科技开发有限公司 | Image processing method and apparatus, and storage medium |
| CN111444763A (en) * | 2020-02-24 | 2020-07-24 | 珠海格力电器股份有限公司 | Security control method and device, storage medium and air conditioner |
| CN111780673A (en) * | 2020-06-17 | 2020-10-16 | 杭州海康威视数字技术股份有限公司 | Distance measurement method, device and equipment |
| CN111881727A (en) * | 2020-06-16 | 2020-11-03 | 深圳数联天下智能科技有限公司 | Live body discrimination method, device and equipment based on thermal imaging and storage medium |
| WO2020237483A1 (en) * | 2019-05-27 | 2020-12-03 | 深圳市汇顶科技股份有限公司 | Optical sensor, apparatus and method for facial recognition, and electronic device |
| CN112036222A (en) * | 2019-06-04 | 2020-12-04 | 厦门星宸科技有限公司 | Face identification system and method |
| CN112070021A (en) * | 2020-09-09 | 2020-12-11 | 深圳数联天下智能科技有限公司 | Distance measurement method, distance measurement system, distance measurement equipment and storage medium based on face detection |
| CN112254821A (en) * | 2020-10-16 | 2021-01-22 | 盈合(深圳)机器人与自动化科技有限公司 | Method and device for compensating body temperature detection precision through visual ranging |
| CN112419399A (en) * | 2019-08-23 | 2021-02-26 | 北京七鑫易维信息技术有限公司 | Image ranging method, device, equipment and storage medium |
| CN112488018A (en) * | 2020-12-09 | 2021-03-12 | 巽腾(广东)科技有限公司 | Binocular in-vivo detection method, device, equipment and storage medium |
| CN112504472A (en) * | 2020-11-26 | 2021-03-16 | 浙江大华技术股份有限公司 | Thermal imager, thermal imaging method and storage medium |
| CN112580578A (en) * | 2020-12-28 | 2021-03-30 | 珠海亿智电子科技有限公司 | Binocular living camera face ranging method and system |
| CN113158877A (en) * | 2021-04-16 | 2021-07-23 | 上海云从企业发展有限公司 | Imaging deviation analysis and biopsy method, imaging deviation analysis and biopsy device, and computer storage medium |
| CN113834571A (en) * | 2020-06-24 | 2021-12-24 | 杭州海康威视数字技术股份有限公司 | Target temperature measurement method, device and temperature measurement system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104834901A (en) * | 2015-04-17 | 2015-08-12 | 北京海鑫科金高科技股份有限公司 | Binocular stereo vision-based human face detection method, device and system |
| 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 |
| CN105260731A (en) * | 2015-11-25 | 2016-01-20 | 商汤集团有限公司 | Human face living body detection system and method based on optical pulses |
| CN106372601A (en) * | 2016-08-31 | 2017-02-01 | 上海依图网络科技有限公司 | In vivo detection method based on infrared visible binocular image and device |
| CN106372629A (en) * | 2016-11-08 | 2017-02-01 | 汉王科技股份有限公司 | Living body detection method and device |
-
2017
- 2017-03-17 CN CN201710160685.XA patent/CN107169405B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104834901A (en) * | 2015-04-17 | 2015-08-12 | 北京海鑫科金高科技股份有限公司 | Binocular stereo vision-based human face detection method, device and system |
| 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 |
| CN105260731A (en) * | 2015-11-25 | 2016-01-20 | 商汤集团有限公司 | Human face living body detection system and method based on optical pulses |
| CN106372601A (en) * | 2016-08-31 | 2017-02-01 | 上海依图网络科技有限公司 | In vivo detection method based on infrared visible binocular image and device |
| CN106372629A (en) * | 2016-11-08 | 2017-02-01 | 汉王科技股份有限公司 | Living body detection method and device |
Non-Patent Citations (8)
| Title |
|---|
| GAHYUN KIM等: "Face Liveness Detection Based on Texture and Frequency Analyses", 《2015 5TH IAPR INTERNATIONAL CONFERENCE ON BIOMETRICS》 * |
| IOANNIS PAVLIDIS等: "The Imaging Issue in an Automatic Face/Disguise Detection System", 《PROCEEDINGS IEEE WORKSHOP ON COMPUTER VISION BEYOND THE VISIBLE SPECTRUM：METHODS AND APPLICATIONS》 * |
| JUKKA MAATTA等: "Face Spoofing Detection From Single Images Using Micro-Texture Analysis", 《RESEARCHGATE》 * |
| YOUNGSHIN KIM等: "Masked fake face detection using radiance measurements", 《OPTICAL SOCIETY OF AMERICA》 * |
| ZHIWEI ZHANG等: "Face Liveness Detection by Learning Multispectral Reflectance Distributions", 《FACE AND GESTURE 2011》 * |
| 李翼: "应用于人脸识别中的反照片欺骗检测方法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 王悦扬: "基于多光谱成像的人脸活体检测", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 胡妙春: "多光谱人脸活体检测特征的研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (35)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107832712A (en) * | 2017-11-13 | 2018-03-23 | 深圳前海微众银行股份有限公司 | Biopsy method, device and computer-readable recording medium |
| CN107992811A (en) * | 2017-11-27 | 2018-05-04 | 北京小米移动软件有限公司 | Face identification method and device |
| CN108535252A (en) * | 2018-02-23 | 2018-09-14 | 广州市派客朴食信息科技有限责任公司 | A kind of binocular stereo vision food recognition methods |
| CN108629298A (en) * | 2018-04-23 | 2018-10-09 | Oppo广东移动通信有限公司 | Face identification method, electronic device and non-volatile computer readable storage medium storing program for executing |
| CN108629305A (en) * | 2018-04-27 | 2018-10-09 | 朱旭辉 | A kind of face recognition method |
| CN110826366A (en) * | 2018-08-10 | 2020-02-21 | 北京魔门塔科技有限公司 | Face image acquisition system for data analysis at night |
| CN109376595A (en) * | 2018-09-14 | 2019-02-22 | 杭州宇泛智能科技有限公司 | Monocular RGB camera in-vivo detection method and system based on human eye attention |
| CN109376643A (en) * | 2018-10-16 | 2019-02-22 | 杭州悉住信息科技有限公司 | Face identification method and system |
| CN111079473A (en) * | 2018-10-19 | 2020-04-28 | 北京奇虎科技有限公司 | Gender identification method, gender identification device, electronic equipment and computer-readable storage medium |
| CN109685014A (en) * | 2018-12-25 | 2019-04-26 | 努比亚技术有限公司 | Face recognition method, device, mobile terminal and storage medium |
| CN111382654B (en) * | 2018-12-29 | 2024-04-12 | 北京市商汤科技开发有限公司 | Image processing method and device and storage medium |
| CN111382654A (en) * | 2018-12-29 | 2020-07-07 | 北京市商汤科技开发有限公司 | Image processing method and apparatus, and storage medium |
| CN110163097A (en) * | 2019-04-16 | 2019-08-23 | 深圳壹账通智能科技有限公司 | Discrimination method, device, electronic equipment and the storage medium of three-dimensional head portrait true or false |
| WO2020237483A1 (en) * | 2019-05-27 | 2020-12-03 | 深圳市汇顶科技股份有限公司 | Optical sensor, apparatus and method for facial recognition, and electronic device |
| CN112036222B (en) * | 2019-06-04 | 2023-12-29 | 星宸科技股份有限公司 | Face recognition system and method |
| CN112036222A (en) * | 2019-06-04 | 2020-12-04 | 厦门星宸科技有限公司 | Face identification system and method |
| CN112419399A (en) * | 2019-08-23 | 2021-02-26 | 北京七鑫易维信息技术有限公司 | Image ranging method, device, equipment and storage medium |
| US11972638B2 (en) | 2019-10-18 | 2024-04-30 | Tencent Technology (Shenzhen) Company Limited | Face living body detection method and apparatus, device, and storage medium |
| CN110765923B (en) * | 2019-10-18 | 2024-05-24 | 腾讯科技（深圳）有限公司 | Face living body detection method, device, equipment and storage medium |
| CN110765923A (en) * | 2019-10-18 | 2020-02-07 | 腾讯科技（深圳）有限公司 | Face living body detection method, device, equipment and storage medium |
| CN110796067A (en) * | 2019-10-27 | 2020-02-14 | 恒大智慧科技有限公司 | Automatic early warning method, device and storage medium for vehicle starting in intelligent community |
| CN110909693B (en) * | 2019-11-27 | 2023-06-20 | 深圳华付技术股份有限公司 | 3D face living body detection method, device, computer equipment and storage medium |
| CN110909693A (en) * | 2019-11-27 | 2020-03-24 | 深圳市华付信息技术有限公司 | 3D face living body detection method and device, computer equipment and storage medium |
| CN111209870A (en) * | 2020-01-09 | 2020-05-29 | 杭州涂鸦信息技术有限公司 | Binocular living body camera rapid registration method, system and device thereof |
| CN111444763A (en) * | 2020-02-24 | 2020-07-24 | 珠海格力电器股份有限公司 | Security control method and device, storage medium and air conditioner |
| CN111881727B (en) * | 2020-06-16 | 2024-02-06 | 深圳数联天下智能科技有限公司 | Living body screening method, device, equipment and storage medium based on thermal imaging |
| CN111881727A (en) * | 2020-06-16 | 2020-11-03 | 深圳数联天下智能科技有限公司 | Live body discrimination method, device and equipment based on thermal imaging and storage medium |
| CN111780673A (en) * | 2020-06-17 | 2020-10-16 | 杭州海康威视数字技术股份有限公司 | Distance measurement method, device and equipment |
| CN113834571A (en) * | 2020-06-24 | 2021-12-24 | 杭州海康威视数字技术股份有限公司 | Target temperature measurement method, device and temperature measurement system |
| CN112070021A (en) * | 2020-09-09 | 2020-12-11 | 深圳数联天下智能科技有限公司 | Distance measurement method, distance measurement system, distance measurement equipment and storage medium based on face detection |
| CN112254821A (en) * | 2020-10-16 | 2021-01-22 | 盈合(深圳)机器人与自动化科技有限公司 | Method and device for compensating body temperature detection precision through visual ranging |
| CN112504472A (en) * | 2020-11-26 | 2021-03-16 | 浙江大华技术股份有限公司 | Thermal imager, thermal imaging method and storage medium |
| CN112488018A (en) * | 2020-12-09 | 2021-03-12 | 巽腾(广东)科技有限公司 | Binocular in-vivo detection method, device, equipment and storage medium |
| CN112580578A (en) * | 2020-12-28 | 2021-03-30 | 珠海亿智电子科技有限公司 | Binocular living camera face ranging method and system |
| CN113158877A (en) * | 2021-04-16 | 2021-07-23 | 上海云从企业发展有限公司 | Imaging deviation analysis and biopsy method, imaging deviation analysis and biopsy device, and computer storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107169405B (en) | 2020-07-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107169405A (en) | Method and device based on binocular camera vivo identification | |
| US10013803B2 (en) | System and method of 3D modeling and virtual fitting of 3D objects | |
| CN106022304B (en) | A kind of real-time body's sitting posture situation detection method based on binocular camera | |
| CN106851238B (en) | Method for controlling white balance, white balance control device and electronic device | |
| CN108764071A (en) | It is a kind of based on infrared and visible images real human face detection method and device | |
| CN107018323B (en) | Control method, control device and electronic device | |
| CN106598221A (en) | Eye key point detection-based 3D sight line direction estimation method | |
| US20160252346A1 (en) | Determining three-dimensional information from projections or placement of two-dimensional patterns | |
| CN107025635A (en) | Processing method, processing unit and the electronic installation of image saturation based on the depth of field | |
| US20090304232A1 (en) | Visual axis direction detection device and visual line direction detection method | |
| CN110232389A (en) | A kind of stereoscopic vision air navigation aid based on green crop feature extraction invariance | |
| CN107273846A (en) | A kind of human somatotype parameter determination method and device | |
| CN105286871A (en) | Video processing-based body height measurement method | |
| CN105354825B (en) | The intelligent apparatus of reading matter position and its application in automatic identification read-write scene | |
| CN104661585B (en) | The method for characterizing skin volume | |
| CN108324247B (en) | Method and system for evaluating skin wrinkles at specified positions | |
| CN106991378A (en) | Facial orientation detection method, detection means and electronic installation based on depth | |
| CN105335699B (en) | Read-write scene is read and write intelligent identification and the application thereof of element three-dimensional coordinate | |
| CN105354822B (en) | The intelligent apparatus of read-write element position and application in automatic identification read-write scene | |
| US11250618B2 (en) | Method and system for estimating the geometry of a scene | |
| CN113692527B (en) | Method and device for measuring the local refractive power and/or the power distribution of an ophthalmic lens | |
| CN107122754A (en) | Posture identification method and device | |
| CN107610078A (en) | Image processing method and device | |
| CN110446967A (en) | For determining the computer implemented method of the expression at spectacle frame edge or the expression at eyeglass edge | |
| CN105354828B (en) | Read and write intelligent identification and the application thereof of reading matter three-dimensional coordinate in scene |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20200817 Address after: No.99, Jingrong South 3rd Street, Jiancha street, Tianfu New District, Chengdu 610000 China (Sichuan) pilot Free Trade Zone, Chengdu Patentee after: Sichuan Yuncong Tianfu Artificial Intelligence Technology Co., Ltd Address before: 201203 Shanghai City, Pudong New Area China Zuchongzhi Road (Shanghai) Free Trade Zone No. 1077 Building 2 room 1135-A Patentee before: SHANGHAI YUNCONG ENTERPRISE DEVELOPMENT Co.,Ltd. |