CN107066942A - A kind of living body faces recognition methods and system - Google Patents
A kind of living body faces recognition methods and system Download PDFInfo
- Publication number
- CN107066942A CN107066942A CN201710124964.0A CN201710124964A CN107066942A CN 107066942 A CN107066942 A CN 107066942A CN 201710124964 A CN201710124964 A CN 201710124964A CN 107066942 A CN107066942 A CN 107066942A
- Authority
- CN
- China
- Prior art keywords
- living body
- body faces
- video frame
- frame images
- submodule
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06V40/40—Spoof detection, e.g. liveness detection
- G06V40/45—Detection of the body part being alive
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Biomedical Technology (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of living body faces recognition methods, including step:The video frame images that acquisition camera is shot;Whether it is living body faces image that video frame images are recognized by the convolutional neural networks trained.The invention also discloses a kind of living body faces identifying system, including photographing module, acquisition module, living body faces detection module, acquisition module is connected with photographing module, living body faces detection module respectively, wherein:The video that acquisition module is shot to photographing module carries out sampling and obtains video frame images;Whether living body faces detection module is living body faces image by the convolutional neural networks detection identification video frame images trained.Brain of the present invention using the deep learning neuron network simulation mankind, discriminate whether it is living body faces by training neutral net, largely allow computer to pass through " intuition " to differentiate living body faces or photo, rather than the algorithm of design, this avoid the defect of algorithm, the accuracy rate of identification is substantially increased.
Description
Technical field
The invention belongs to technical field of face recognition, more particularly to a kind of living body faces recognition methods and system.
Background technology
The safety in utilization of living creature characteristic recognition system is people's question of common concern, and people are to living things feature recognition system
The confidence of system and receiving are heavily dependent on the robustness, low error rate and anti-deception ability of system.Therefore In vivo detection
It is the critical function for detecting and refusing counterfeit identity characteristic in living creature characteristic recognition system.Having in face identification system can
It is certainly most common by way of photo or video in all deceptions that can be faced.If there is no live body people
Face detection ensure, can be cheated and be passed through with a photo, one section of video, then such recognition of face have what it is actual answer
With valueTherefore, also there is serious potential safety hazard in face recognition technology at present.Such as, in the security product of smart home,
It is widespread practice by recognition of face certification, but recognition of face is the problem of have one very big, when someone cheats peace with photo
During anti-camera, sometimes seem helpless.
In in the prior art, patent No. CN201510633817《Living body faces recognition methods and device》In, taken the photograph by double
As head gathers view data, face appearance is extracted by certain algorithm in the two pictures data then gathered according to dual camera
Depth information determines whether it is real face, because photo is plane, is no depth information.But this tradition is calculated
Method is unlikely to be flawless, and this method easily causes erroneous judgement in true use, especially under complex environment, such as
In the case that illumination is poor, accuracy rate is not high.
The content of the invention
The present invention provides a kind of living body faces recognition methods and system, can avoid using photo or video containing face
To gain certification by cheating, security of system is improved, while shortening recognition time, recognition accuracy is improved.
A kind of living body faces recognition methods of the present invention includes:
The video frame images that S100 acquisition cameras are shot;
S200 recognizes whether the video frame images are living body faces image by the convolutional neural networks trained.
The invention provides a kind of living body faces detection method based on convolutional neural networks, this method can differentiate face
Image is living body faces image or photo (or video), so as to prevent disabled user from using photo, the video of validated user
Cheated.Traditional living body faces detection algorithm is all based on manual feature extraction, and a kind of effective manual feature needs
It is lot more time to design, and algorithm is also the presence of certain defect, there is certain influence on accuracy rate, and convolutional Neural net
Network does not need hand-designed feature, it is only necessary to planned network structure, training parameter.
Further, step is also included before the step S100:
S010 gathers the living body faces image pattern and human face photo sample for training by camera, and is divided
Class;
S020 passes through living body faces image pattern, human face photo sample described in the deep learning of convolutional neural networks, study
The living body faces identification model of living body faces and photo can be told by being obtained after training.
Training sample, if it is desired to if high resolution, the quantity of sample is The more the better naturally.Due to the model of training
Need that shooting can be told is living body faces or photo, therefore is accomplished by when training carrying out classification based training, is passed through
Camera shoots the living body faces image of living body faces acquisition as living body faces image pattern, and labeled as living body faces, leads to
The facial image crossed camera shooting human face photo (or video) and obtained shines as human face photo sample, and labeled as face
Piece, so that convolutional neural networks classification learning and training are allowed, so that living body faces and photo can be distinguished quickly.
Further, the step S200 includes step:
S210 carries out image procossing to the video frame images;
S220 carries out Face datection to the video frame images after processing, judges whether the video frame images contain people
Face, if then entering next step;
Video frame images after the processing as the input of the living body faces identification model, are obtained identification point by S230
Class result.
Further, the image procossing described in the step S210 includes carrying out light benefit to the video frame images
Repay, greyscale transformation, histogram equalization, normalization, geometric correction, filtering and Edge contrast.
Pretreatment is carried out to image can be more using improving recognition speed and efficiency.
Further, the camera is dual camera.
Detected the invention also discloses a kind of living body faces identifying system, including photographing module, acquisition module, living body faces
Module, the acquisition module is connected with the photographing module, living body faces detection module respectively, wherein:The acquisition module pair
The video that the photographing module is shot carries out sampling and obtains video frame images;The living body faces detection module is by having trained
Whether the convolutional neural networks detection identification video frame images are living body faces image.
Further, the living body faces detection module includes study submodule, learns what submodule was connected with described, living
Body recognition of face submodule, wherein:The acquisition module gathers the living body faces image for training by the photographing module
Sample and human face photo sample, and classified;The study submodule passes through live body described in convolutional neural networks deep learning
Facial image sample, human face photo sample, and the result of training is given to the living body faces identification submodule so that the work
Body recognition of face submodule can make a distinction to living body faces image and human face photo.
Further, the living body faces detection module also includes:Image procossing submodule, Face datection submodule, institute
State Face datection submodule respectively with described image processing submodule, living body faces identification submodule to be connected, the living body faces
Detection sub-module is connected with described image processing submodule, wherein:Described image processing submodule enters to the video frame images
Row image procossing;The video frame images that the Face datection submodule handles described image after submodule processing carry out face inspection
Survey, judge whether the video frame images contain face, if so, then the living body faces recognize submodule to the frame of video
Image is identified, and whether judge the video frame images is living body faces image.
Further, described image processing module carries out light compensation, greyscale transformation, histogram to the video frame images
Equalization, normalization, geometric correction, filtering and Edge contrast.
Further, the photographing module includes at least two cameras.
The present invention has the beneficial effect that:
The present invention is using the deep learning method study living body faces data based on convolutional neural networks, the one of deep learning
A little network structures simulate the brain of people, and by the depth and convolution of network, good effect is reached in living body faces identification field,
It can avoid gaining certification by cheating using video or photo containing face, improve security of system, while when can shorten identification
Between, improve recognition accuracy.And by using the brain of the deep learning neuron network simulation mankind, sentenced by training neutral net
Not whether to be not photo, largely allow computer to pass through " intuition " to differentiate photo, rather than the algorithm designed, thus be avoided that
The defect of algorithm, substantially increases the accuracy rate of identification.And deep learning network can be by learning under complex environment
Image pattern so that preferable effect is produced under complex environment.
Brief description of the drawings
Technical scheme in order to illustrate the embodiments of the present invention more clearly, makes required in being described below to embodiment
Accompanying drawing is briefly introduced, it should be apparent that, drawings in the following description are only some embodiments of the present invention, for this
For the those of ordinary skill in field, without having to pay creative labor, it can also be obtained according to these accompanying drawings
His accompanying drawing.
Fig. 1 is a kind of flow chart of living body faces recognition methods embodiment one of the invention;
Fig. 2 is a kind of another embodiment flow chart of living body faces recognition methods of the invention;
Fig. 3 is a kind of block diagram of living body faces identifying system embodiment one of the invention;
Fig. 4 is a kind of another embodiment block diagram of living body faces identifying system of the invention.
Embodiment
In order that the object, technical solutions and advantages of the present invention are clearer, below in conjunction with accompanying drawing the present invention is made into
One step it is described in detail, it is clear that described embodiment is only embodiment of the invention a part of, rather than whole implementation
Example.Based on the embodiment in the present invention, what those of ordinary skill in the art were obtained under the premise of creative work is not made
All other embodiment, belongs to the scope of protection of the invention.
The invention discloses a kind of living body faces recognition methods, as shown in figure 1, including step:
The video frame images that S100 acquisition cameras are shot;
S200 recognizes whether the video frame images are living body faces image by the convolutional neural networks trained.
Convolutional neural networks are different from traditional method for detecting human face, and it is by directly acting on input sample, using sample
Original training network simultaneously finally realizes Detection task.It is the method for detecting human face of non-parameter type, can save conventional method
The a series of complex process of middle modeling, parameter Estimation and parametric test, reconstruction model etc..
The convolutional neural networks trained, due to having carried out learning training to it, shooting is judged therefore, it is possible to quick
What head was shot is living body faces.Because photo is plane, light is fixed.And real face is 3-dimensional, in light
More features will be produced under line, the real human face obtained by dual camera will include this feature, and photo is without this
Plant feature.We take deep learning method to train neutral net to capture this feature.
Using convolutional neural networks come before carrying out living body faces identification, it is necessary to be instructed to the convolutional neural networks
Practice, specifically, including step:
S010 gathers the living body faces image pattern and human face photo sample for training by camera, and is divided
Class;
S020 passes through living body faces image pattern, human face photo sample described in the deep learning of convolutional neural networks, study
The living body faces identification model of living body faces and photo can be told by being obtained after training.
Training method is very simple, and we input substantial amounts of photo to deep learning network, identifies it for photo.And input true
Real facial image (i.e. living body faces image) arrives deep learning network, identifies it for living body faces.Passing through substantial amounts of training
Afterwards, it is photo that our network, which will learn to what, and what is living body faces.For example, we can be used by two cameras
The image of collection, wherein gathering one group of image 100000 for real human face (i.e. living body faces) to (photo of a camera 1
A pair) photo with a camera 2 is.Gather 100000 pairs of the image that one group is human face photo.This two groups of photos we will
Carry out classification learning.When choosing the image of photo and real human face, we use the picture under different illumination conditions, including appoint
Anticipate size, position, posture, direction, the colour of skin, the real human face image and human face photo of facial expression and illumination condition.So that being
System is respectively provided with high accuracy rate in the case of various be likely to occur.
Another embodiment of the inventive method, as shown in Fig. 2 including step:
S010 gathers the living body faces image pattern and human face photo sample for training by camera, and is divided
Class;
S020 passes through living body faces image pattern, human face photo sample described in the deep learning of convolutional neural networks, study
The living body faces identification model of living body faces and photo can be told by being obtained after training;
The video frame images that S100 acquisition cameras are shot;
S210 carries out image procossing to the video frame images;
S220 carries out Face datection to the video frame images after processing, judges whether the video frame images contain people
Face, if then entering next step;
Video frame images after the processing as the input of the living body faces identification model, are obtained identification point by S230
Class result.
Face datection step is primarily used to judge whether video frame images contain face.Face datection can use many
Kind of mode is differentiated, it is only necessary to which whether can detect in image just can be with containing face.Such as, camera is collected
Video frame images, are carried out after the image procossings such as greyscale transformation, filtering process, high-quality gray-scale map are obtained, then to gray-scale map
Haar-Like wavelet character values quickly are calculated using integration, the discrete AdaBoost (Adaptive trained are applied to
Boosting) grader, discriminates whether it is face.Haar-like features, i.e., the Haar features that many people often say, are computers
A kind of conventional feature of visual field describes operator, available for face description.Obtain after Haar-Like wavelet character values, use
The discrete AdaBoost graders trained carry out recognition of face.So-called grader, just refers to face and non-face herein
The algorithm classified, on the basis of AdaBoost algorithms, pedestrian is entered using Haar-like wavelet characters and integrogram method
Face is detected.It is worth noting that, the method in the present invention on Face datection is not limited to the method mentioned in the present embodiment, it is other
The existing method that can realize Face datection.
If it is judged that the video frame images of collection do not contain face, then also with regard to without carrying out live body people below
Face certification, only detect containing after face, just determine whether the video frame images whether be shoot living body faces figure
Picture.Due to convolutional neural networks the feature of deep learning living body faces and during training classification for people face photo feature, by
This obtains the living body faces identification model that can quickly distinguish that the video frame images are living body faces or photo.Only need by
Video frame images after Face datection are directly inputted in the living body faces identification model, you can quickly export recognition result.
Preferably, image procossing described in above-mentioned steps S210 include carrying out the video frame images light compensation,
Greyscale transformation, histogram equalization, normalization, geometric correction, filtering and Edge contrast.
The original image that system is obtained tends not to directly use due to being limited and random disturbances by various conditions,
The image preprocessings such as gray correction, noise filtering must be carried out to it in the early stage of image procossing.For facial image
Speech, its preprocessing process is mainly including the light compensation of facial image, greyscale transformation, histogram equalization, normalization, geometry school
Just, filter and sharpen etc..Before video frame images are identified by living body faces identification model, first to facial image
Pre-processed, can effectively improve final recognition efficiency and the degree of accuracy.
Preferably, the camera described in any of the above-described embodiment of the method can use dual camera.Due to a shooting
The discrimination of the individual human face plane picture of head collection is influenceed by ambient light, acquisition angles, expression etc. factor, therefore
Receive by larger limitation.And these problems then can be preferably overcome if being gathered by dual camera.
Based on identical technical concept, the embodiment of the present invention also provides a kind of living body faces identifying system, and the system can be held
Row above method embodiment, specifically, the embodiment one of living body faces identifying system of the present invention is as shown in figure, including shooting mould
Block, acquisition module, living body faces detection module, the acquisition module respectively with the photographing module, living body faces detection module
It is connected, wherein:The video that the acquisition module is shot to the photographing module carries out sampling and obtains video frame images;The live body
Face detection module recognizes whether the video frame images are living body faces image by the convolutional neural networks detection trained.
Camera is used for shooting video, and is sampled in the video that acquisition module is then shot from camera, gathers video
Two field picture, living body faces detection module then be used for detect collection video frame images whether be shoot living body faces image.
Present system uses the brain of the deep learning neuron network simulation mankind, is by training neutral net to differentiate
No is living body faces, largely allows computer to pass through " intuition " to differentiate living body faces, rather than the algorithm designed, so
The defect of algorithm is avoided, the accuracy rate of identification is substantially increased.
On the basis of said system embodiment one, the living body faces detection module include study submodule, with it is described
Learn what submodule was connected, living body faces identification submodule, wherein:The acquisition module is gathered by the photographing module to be used for
The living body faces image pattern and human face photo sample of training, and classified;The study submodule passes through convolutional Neural net
Living body faces image pattern, human face photo sample described in network deep learning, and the result of training is given to the living body faces knowledge
Small pin for the case module so that the living body faces identification submodule can make a distinction to living body faces image and human face photo.
Preferably, the living body faces detection module also includes on the basis of above-described embodiment:Image procossing submodule, people
Face detection sub-module, the Face datection submodule recognize submodule phase with described image processing submodule, living body faces respectively
Even, the living body faces detection sub-module is connected with described image processing submodule, wherein:Described image handles submodule to institute
State video frame images and carry out image procossing;The Face datection submodule handles described image the frame of video after submodule processing
Image carries out Face datection, judges whether the video frame images contain face, if so, the then living body faces identification submodule
The video frame images are identified block, and whether judge the video frame images is living body faces image.
First pass through Face datection determines whether contain face in video frame images, can just be carried out if the face contained next
The living body faces identification of step.
Described image processing module in above-described embodiment, which carries out image procossing to the video frame images, to be included carrying out light
Line compensation, greyscale transformation, histogram equalization, normalization, geometric correction, filtering and Edge contrast.
Image preprocessing for face is to be based on Face datection result, and image is handled and feature is finally served
The process of extraction.The original image that system is obtained tends not to directly make due to being limited and random disturbances by various conditions
With, it is necessary to the image preprocessings such as gray correction, noise filtering are carried out to it in the early stage of image procossing.For facial image
For, its preprocessing process mainly includes light compensation, greyscale transformation, histogram equalization, normalization, the geometry of facial image
Correction, filtering and sharpening etc..
Photographing module described in any of the above-described system embodiment includes at least two cameras.Single camera typically can
Influenceed by illumination condition, acquisition angles, human face expression etc., and at least two cameras can then reduce this to a certain extent
A little limited influences.The present invention shoots picture by least two cameras of photographing module, and because photo is plane, light is
Fixed.And real face is 3-dimensional, more features will be produced under light, will be obtained by least two cameras
Real human face will include this feature, and photo is without this feature.
, but those skilled in the art once know basic creation although preferred embodiments of the present invention have been described
Property concept, then can make other change and modification to these embodiments.So, appended claims are intended to be construed to include excellent
Select embodiment and fall into having altered and changing for the scope of the invention.
Obviously, those skilled in the art can carry out the essence of various changes and modification without departing from the present invention to the present invention
God and scope.So, if these modifications and variations of the present invention belong to the scope of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to comprising including these changes and modification.
Claims (10)
1. a kind of living body faces recognition methods, it is characterised in that including step:
The video frame images that S100 acquisition cameras are shot;
S200 recognizes whether the video frame images are living body faces image by the convolutional neural networks trained.
2. a kind of living body faces recognition methods according to claim 1, it is characterised in that also wrapped before the step S100
Include step:
S010 gathers the living body faces image pattern and human face photo sample for training by camera, and is classified;
S020 passes through living body faces image pattern, human face photo sample, learning training described in the deep learning of convolutional neural networks
The living body faces identification model of living body faces and photo can be told by obtaining afterwards.
3. a kind of living body faces recognition methods according to claim 2, it is characterised in that the step S200 includes step
Suddenly:
S210 carries out image procossing to the video frame images;
S220 carries out Face datection to the video frame images after processing, judges whether the video frame images contain face, if
It is then to enter next step;
Video frame images after the processing as the input of the living body faces identification model, are obtained identification classification knot by S230
Really.
4. a kind of living body faces recognition methods according to claim 3, it is characterised in that described in the step S210
Image procossing includes carrying out light compensation, greyscale transformation, histogram equalization, normalization, geometry school to the video frame images
Just, filtering and Edge contrast.
5. a kind of living body faces recognition methods according to claim any one of 1-4, it is characterised in that the camera is
Dual camera.
6. a kind of living body faces identifying system, it is characterised in that including photographing module, acquisition module, living body faces detection module,
The acquisition module is connected with the photographing module, living body faces detection module respectively, wherein:
The video that the acquisition module is shot to the photographing module carries out sampling and obtains video frame images;
The living body faces detection module by the detection of the convolutional neural networks trained recognize the video frame images whether be
Living body faces image.
7. a kind of living body faces identifying system according to claim 6, it is characterised in that the living body faces detection module
The living body faces being connected including study submodule, with the study submodule recognize submodule, wherein:
The acquisition module gathers the living body faces image pattern and human face photo sample for training by the photographing module,
And classified;
It is described study submodule by living body faces image pattern, human face photo sample described in convolutional neural networks deep learning,
And the result of training is given to the living body faces identification submodule so that the living body faces identification submodule can be to live body people
Face image makes a distinction with human face photo.
8. a kind of living body faces identifying system according to claim 7, it is characterised in that the living body faces detection module
Also include:Image procossing submodule, Face datection submodule, the Face datection submodule handle submodule with described image respectively
Block, living body faces identification submodule are connected, and the living body faces detection sub-module is connected with described image processing submodule, its
In:
Described image handles submodule and carries out image procossing to the video frame images;
The video frame images that the Face datection submodule handles described image after submodule processing carry out Face datection, judge
Whether the video frame images contain face, if so, then the living body faces identification submodule enters to the video frame images
Whether row identification, it is living body faces image to judge the video frame images.
9. a kind of living body faces identifying system according to claim 8, it is characterised in that described image processing module is to institute
Video frame images are stated to carry out at light compensation, greyscale transformation, histogram equalization, normalization, geometric correction, filtering and sharpening
Reason.
10. a kind of living body faces identifying system according to claim any one of 6-9, it is characterised in that the shooting mould
Block includes at least two cameras.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710124964.0A CN107066942A (en) | 2017-03-03 | 2017-03-03 | A kind of living body faces recognition methods and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710124964.0A CN107066942A (en) | 2017-03-03 | 2017-03-03 | A kind of living body faces recognition methods and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107066942A true CN107066942A (en) | 2017-08-18 |
Family
ID=59621906
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710124964.0A Pending CN107066942A (en) | 2017-03-03 | 2017-03-03 | A kind of living body faces recognition methods and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107066942A (en) |
Cited By (45)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107545248A (en) * | 2017-08-24 | 2018-01-05 | 北京小米移动软件有限公司 | Biological characteristic biopsy method, device, equipment and storage medium |
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 |
CN107832735A (en) * | 2017-11-24 | 2018-03-23 | 百度在线网络技术(北京)有限公司 | Method and apparatus for identifying face |
CN107944416A (en) * | 2017-12-06 | 2018-04-20 | 成都睿码科技有限责任公司 | A kind of method that true man's verification is carried out by video |
CN108182409A (en) * | 2017-12-29 | 2018-06-19 | 北京智慧眼科技股份有限公司 | Biopsy method, device, equipment and storage medium |
CN108230257A (en) * | 2017-11-15 | 2018-06-29 | 北京市商汤科技开发有限公司 | Image processing method, device, electronic equipment and storage medium |
CN108416324A (en) * | 2018-03-27 | 2018-08-17 | 百度在线网络技术(北京)有限公司 | Method and apparatus for detecting live body |
CN108470169A (en) * | 2018-05-23 | 2018-08-31 | 国政通科技股份有限公司 | Face identification system and method |
CN108537152A (en) * | 2018-03-27 | 2018-09-14 | 百度在线网络技术(北京)有限公司 | Method and apparatus for detecting live body |
CN108701228A (en) * | 2018-04-18 | 2018-10-23 | 深圳阜时科技有限公司 | Identification authentication method, identification authentication device and electronic equipment |
CN108710841A (en) * | 2018-05-11 | 2018-10-26 | 杭州软库科技有限公司 | A kind of face living body detection device and method based on MEMs infrared sensor arrays |
CN108769504A (en) * | 2018-03-20 | 2018-11-06 | 北京德融汇科技有限公司 | A kind of infrared camera that function is activated with In vivo detection applied to ATM |
CN108875546A (en) * | 2018-04-13 | 2018-11-23 | 北京旷视科技有限公司 | Face auth method, system and storage medium |
CN108875652A (en) * | 2018-06-26 | 2018-11-23 | 四川斐讯信息技术有限公司 | User's scene analysis device and method |
CN108898112A (en) * | 2018-07-03 | 2018-11-27 | 东北大学 | A kind of near-infrared human face in-vivo detection method and system |
CN108944650A (en) * | 2018-08-14 | 2018-12-07 | 浙江安谐智能科技有限公司 | A kind of car light open state method of discrimination based on long-and-short distant light irradiation principle |
CN109117755A (en) * | 2018-07-25 | 2019-01-01 | 北京飞搜科技有限公司 | A kind of human face in-vivo detection method, system and equipment |
CN109190530A (en) * | 2018-08-21 | 2019-01-11 | 朱常林 | One kind being based on recognition of face big data algorithm |
CN109299690A (en) * | 2018-09-21 | 2019-02-01 | 浙江中正智能科技有限公司 | A method of video real-time face accuracy of identification can be improved |
CN109376694A (en) * | 2018-11-23 | 2019-02-22 | 重庆中科云丛科技有限公司 | A kind of real-time face biopsy method based on image procossing |
CN109508694A (en) * | 2018-12-10 | 2019-03-22 | 上海众源网络有限公司 | A kind of face identification method and identification device |
CN109543529A (en) * | 2018-10-19 | 2019-03-29 | 北京陌上花科技有限公司 | Biopsy method and device |
CN109766806A (en) * | 2018-12-28 | 2019-05-17 | 深圳奥比中光科技有限公司 | Efficient face identification method and electronic equipment |
CN109784148A (en) * | 2018-12-06 | 2019-05-21 | 北京飞搜科技有限公司 | Biopsy method and device |
CN109858375A (en) * | 2018-12-29 | 2019-06-07 | 深圳市软数科技有限公司 | Living body faces detection method, terminal and computer readable storage medium |
CN110020631A (en) * | 2019-04-11 | 2019-07-16 | 乐清市风杰电子科技有限公司 | A kind of boarding gate verifying bench and method based on face recognition |
CN110287767A (en) * | 2019-05-06 | 2019-09-27 | 深圳市华付信息技术有限公司 | Can attack protection biopsy method, device, computer equipment and storage medium |
CN110298230A (en) * | 2019-05-06 | 2019-10-01 | 深圳市华付信息技术有限公司 | Silent biopsy method, device, computer equipment and storage medium |
CN110458025A (en) * | 2019-07-11 | 2019-11-15 | 南京邮电大学 | A kind of personal identification and localization method based on binocular camera |
CN110557584A (en) * | 2018-05-31 | 2019-12-10 | 杭州海康威视数字技术股份有限公司 | image processing method and device, and computer readable storage medium |
CN110674730A (en) * | 2019-09-20 | 2020-01-10 | 华南理工大学 | Monocular-based face silence living body detection method |
CN110766092A (en) * | 2019-10-31 | 2020-02-07 | 浪潮金融信息技术有限公司 | Method for integrating multi-vision equipment on self-service terminal equipment |
CN110991307A (en) * | 2019-11-27 | 2020-04-10 | 北京锐安科技有限公司 | Face recognition method, device, equipment and storage medium |
WO2020135125A1 (en) * | 2018-12-27 | 2020-07-02 | 杭州海康威视数字技术股份有限公司 | Living body detection method and device |
CN111382607A (en) * | 2018-12-28 | 2020-07-07 | 北京三星通信技术研究有限公司 | Living body detection method and device and face authentication system |
CN111428577A (en) * | 2020-03-03 | 2020-07-17 | 电子科技大学 | Face living body judgment method based on deep learning and video amplification technology |
WO2020220127A1 (en) * | 2019-04-29 | 2020-11-05 | Active Witness Corp. | Security systems and processes involving biometric authentication |
CN112215187A (en) * | 2020-10-21 | 2021-01-12 | 广州市晶华精密光学股份有限公司 | Intelligent automobile door opening method and device, intelligent automobile and storage medium |
CN112257685A (en) * | 2020-12-08 | 2021-01-22 | 成都新希望金融信息有限公司 | Face copying recognition method and device, electronic equipment and storage medium |
CN112364329A (en) * | 2020-12-09 | 2021-02-12 | 山西三友和智慧信息技术股份有限公司 | Face authentication system and method combining heart rate detection |
CN113256298A (en) * | 2020-02-10 | 2021-08-13 | 深圳市光鉴科技有限公司 | Payment system with 3D face recognition and using method |
CN113255401A (en) * | 2020-02-10 | 2021-08-13 | 深圳市光鉴科技有限公司 | 3D face camera device |
CN113313856A (en) * | 2020-02-10 | 2021-08-27 | 深圳市光鉴科技有限公司 | Door lock system with 3D face recognition function and using method |
US11321963B2 (en) | 2018-01-04 | 2022-05-03 | Hangzhou Hikvision Digital Technology Co., Ltd. | Face liveness detection based on neural network model |
US11735018B2 (en) | 2018-03-11 | 2023-08-22 | Intellivision Technologies Corp. | Security system with face recognition |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103593598A (en) * | 2013-11-25 | 2014-02-19 | 上海骏聿数码科技有限公司 | User online authentication method and system based on living body detection and face recognition |
CN103605964A (en) * | 2013-11-25 | 2014-02-26 | 上海骏聿数码科技有限公司 | Face detection method and system based on image on-line learning |
CN105224924A (en) * | 2015-09-29 | 2016-01-06 | 小米科技有限责任公司 | Living body faces recognition methods and device |
CN105956572A (en) * | 2016-05-15 | 2016-09-21 | 北京工业大学 | In vivo face detection method based on convolutional neural network |
US20160350611A1 (en) * | 2015-04-29 | 2016-12-01 | Beijing Kuangshi Technology Co., Ltd. | Method and apparatus for authenticating liveness face, and computer program product thereof |
CN106203305A (en) * | 2016-06-30 | 2016-12-07 | 北京旷视科技有限公司 | Human face in-vivo detection method and device |
-
2017
- 2017-03-03 CN CN201710124964.0A patent/CN107066942A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103593598A (en) * | 2013-11-25 | 2014-02-19 | 上海骏聿数码科技有限公司 | User online authentication method and system based on living body detection and face recognition |
CN103605964A (en) * | 2013-11-25 | 2014-02-26 | 上海骏聿数码科技有限公司 | Face detection method and system based on image on-line learning |
US20160350611A1 (en) * | 2015-04-29 | 2016-12-01 | Beijing Kuangshi Technology Co., Ltd. | Method and apparatus for authenticating liveness face, and computer program product thereof |
CN105224924A (en) * | 2015-09-29 | 2016-01-06 | 小米科技有限责任公司 | Living body faces recognition methods and device |
CN105956572A (en) * | 2016-05-15 | 2016-09-21 | 北京工业大学 | In vivo face detection method based on convolutional neural network |
CN106203305A (en) * | 2016-06-30 | 2016-12-07 | 北京旷视科技有限公司 | Human face in-vivo detection method and device |
Cited By (59)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107545248B (en) * | 2017-08-24 | 2021-04-02 | 北京小米移动软件有限公司 | Biological characteristic living body detection method, device, equipment and storage medium |
CN107545248A (en) * | 2017-08-24 | 2018-01-05 | 北京小米移动软件有限公司 | Biological characteristic biopsy method, device, equipment and storage medium |
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 |
CN108230257A (en) * | 2017-11-15 | 2018-06-29 | 北京市商汤科技开发有限公司 | Image processing method, device, electronic equipment and storage medium |
CN107832735A (en) * | 2017-11-24 | 2018-03-23 | 百度在线网络技术(北京)有限公司 | Method and apparatus for identifying face |
CN107944416A (en) * | 2017-12-06 | 2018-04-20 | 成都睿码科技有限责任公司 | A kind of method that true man's verification is carried out by video |
CN108182409A (en) * | 2017-12-29 | 2018-06-19 | 北京智慧眼科技股份有限公司 | Biopsy method, device, equipment and storage medium |
CN108182409B (en) * | 2017-12-29 | 2020-11-10 | 智慧眼科技股份有限公司 | Living body detection method, living body detection device, living body detection equipment and storage medium |
US11321963B2 (en) | 2018-01-04 | 2022-05-03 | Hangzhou Hikvision Digital Technology Co., Ltd. | Face liveness detection based on neural network model |
US11735018B2 (en) | 2018-03-11 | 2023-08-22 | Intellivision Technologies Corp. | Security system with face recognition |
CN108769504A (en) * | 2018-03-20 | 2018-11-06 | 北京德融汇科技有限公司 | A kind of infrared camera that function is activated with In vivo detection applied to ATM |
CN108416324B (en) * | 2018-03-27 | 2022-02-25 | 百度在线网络技术(北京)有限公司 | Method and apparatus for detecting living body |
CN108537152B (en) * | 2018-03-27 | 2022-01-25 | 百度在线网络技术(北京)有限公司 | Method and apparatus for detecting living body |
CN108537152A (en) * | 2018-03-27 | 2018-09-14 | 百度在线网络技术(北京)有限公司 | Method and apparatus for detecting live body |
CN108416324A (en) * | 2018-03-27 | 2018-08-17 | 百度在线网络技术(北京)有限公司 | Method and apparatus for detecting live body |
CN108875546A (en) * | 2018-04-13 | 2018-11-23 | 北京旷视科技有限公司 | Face auth method, system and storage medium |
CN108701228A (en) * | 2018-04-18 | 2018-10-23 | 深圳阜时科技有限公司 | Identification authentication method, identification authentication device and electronic equipment |
CN108710841A (en) * | 2018-05-11 | 2018-10-26 | 杭州软库科技有限公司 | A kind of face living body detection device and method based on MEMs infrared sensor arrays |
CN108710841B (en) * | 2018-05-11 | 2021-06-15 | 杭州软库科技有限公司 | Human face living body detection device and method based on MEMs infrared array sensor |
CN108470169A (en) * | 2018-05-23 | 2018-08-31 | 国政通科技股份有限公司 | Face identification system and method |
CN110557584B (en) * | 2018-05-31 | 2022-04-26 | 杭州海康威视数字技术股份有限公司 | Image processing method and device, and computer readable storage medium |
CN110557584A (en) * | 2018-05-31 | 2019-12-10 | 杭州海康威视数字技术股份有限公司 | image processing method and device, and computer readable storage medium |
CN108875652A (en) * | 2018-06-26 | 2018-11-23 | 四川斐讯信息技术有限公司 | User's scene analysis device and method |
CN108898112A (en) * | 2018-07-03 | 2018-11-27 | 东北大学 | A kind of near-infrared human face in-vivo detection method and system |
CN109117755B (en) * | 2018-07-25 | 2021-04-30 | 北京飞搜科技有限公司 | Face living body detection method, system and equipment |
CN109117755A (en) * | 2018-07-25 | 2019-01-01 | 北京飞搜科技有限公司 | A kind of human face in-vivo detection method, system and equipment |
CN108944650A (en) * | 2018-08-14 | 2018-12-07 | 浙江安谐智能科技有限公司 | A kind of car light open state method of discrimination based on long-and-short distant light irradiation principle |
CN109190530A (en) * | 2018-08-21 | 2019-01-11 | 朱常林 | One kind being based on recognition of face big data algorithm |
CN109299690A (en) * | 2018-09-21 | 2019-02-01 | 浙江中正智能科技有限公司 | A method of video real-time face accuracy of identification can be improved |
CN109543529A (en) * | 2018-10-19 | 2019-03-29 | 北京陌上花科技有限公司 | Biopsy method and device |
CN109376694A (en) * | 2018-11-23 | 2019-02-22 | 重庆中科云丛科技有限公司 | A kind of real-time face biopsy method based on image procossing |
CN109784148A (en) * | 2018-12-06 | 2019-05-21 | 北京飞搜科技有限公司 | Biopsy method and device |
CN109508694B (en) * | 2018-12-10 | 2020-10-27 | 上海众源网络有限公司 | Face recognition method and recognition device |
CN109508694A (en) * | 2018-12-10 | 2019-03-22 | 上海众源网络有限公司 | A kind of face identification method and identification device |
WO2020135125A1 (en) * | 2018-12-27 | 2020-07-02 | 杭州海康威视数字技术股份有限公司 | Living body detection method and device |
US11682231B2 (en) | 2018-12-27 | 2023-06-20 | Hangzhou Hikvision Digital Technology Co., Ltd. | Living body detection method and device |
CN109766806A (en) * | 2018-12-28 | 2019-05-17 | 深圳奥比中光科技有限公司 | Efficient face identification method and electronic equipment |
CN111382607A (en) * | 2018-12-28 | 2020-07-07 | 北京三星通信技术研究有限公司 | Living body detection method and device and face authentication system |
CN109858375B (en) * | 2018-12-29 | 2023-09-26 | 简图创智(深圳)科技有限公司 | Living body face detection method, terminal and computer readable storage medium |
CN109858375A (en) * | 2018-12-29 | 2019-06-07 | 深圳市软数科技有限公司 | Living body faces detection method, terminal and computer readable storage medium |
CN110020631A (en) * | 2019-04-11 | 2019-07-16 | 乐清市风杰电子科技有限公司 | A kind of boarding gate verifying bench and method based on face recognition |
WO2020220127A1 (en) * | 2019-04-29 | 2020-11-05 | Active Witness Corp. | Security systems and processes involving biometric authentication |
CN110287767A (en) * | 2019-05-06 | 2019-09-27 | 深圳市华付信息技术有限公司 | Can attack protection biopsy method, device, computer equipment and storage medium |
CN110298230A (en) * | 2019-05-06 | 2019-10-01 | 深圳市华付信息技术有限公司 | Silent biopsy method, device, computer equipment and storage medium |
CN110458025A (en) * | 2019-07-11 | 2019-11-15 | 南京邮电大学 | A kind of personal identification and localization method based on binocular camera |
CN110458025B (en) * | 2019-07-11 | 2022-10-14 | 南京邮电大学 | Target identification and positioning method based on binocular camera |
CN110674730A (en) * | 2019-09-20 | 2020-01-10 | 华南理工大学 | Monocular-based face silence living body detection method |
CN110766092A (en) * | 2019-10-31 | 2020-02-07 | 浪潮金融信息技术有限公司 | Method for integrating multi-vision equipment on self-service terminal equipment |
CN110766092B (en) * | 2019-10-31 | 2022-08-05 | 浪潮金融信息技术有限公司 | Method for integrating multi-vision equipment on self-service terminal equipment |
CN110991307B (en) * | 2019-11-27 | 2023-09-26 | 北京锐安科技有限公司 | Face recognition method, device, equipment and storage medium |
CN110991307A (en) * | 2019-11-27 | 2020-04-10 | 北京锐安科技有限公司 | Face recognition method, device, equipment and storage medium |
CN113313856A (en) * | 2020-02-10 | 2021-08-27 | 深圳市光鉴科技有限公司 | Door lock system with 3D face recognition function and using method |
CN113255401A (en) * | 2020-02-10 | 2021-08-13 | 深圳市光鉴科技有限公司 | 3D face camera device |
CN113256298A (en) * | 2020-02-10 | 2021-08-13 | 深圳市光鉴科技有限公司 | Payment system with 3D face recognition and using method |
CN111428577B (en) * | 2020-03-03 | 2022-05-03 | 电子科技大学 | Face living body judgment method based on deep learning and video amplification technology |
CN111428577A (en) * | 2020-03-03 | 2020-07-17 | 电子科技大学 | Face living body judgment method based on deep learning and video amplification technology |
CN112215187A (en) * | 2020-10-21 | 2021-01-12 | 广州市晶华精密光学股份有限公司 | Intelligent automobile door opening method and device, intelligent automobile and storage medium |
CN112257685A (en) * | 2020-12-08 | 2021-01-22 | 成都新希望金融信息有限公司 | Face copying recognition method and device, electronic equipment and storage medium |
CN112364329A (en) * | 2020-12-09 | 2021-02-12 | 山西三友和智慧信息技术股份有限公司 | Face authentication system and method combining heart rate detection |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107066942A (en) | A kind of living body faces recognition methods and system | |
WO2020151489A1 (en) | Living body detection method based on facial recognition, and electronic device and storage medium | |
CN102419819B (en) | Method and system for recognizing human face image | |
CN108985134B (en) | Face living body detection and face brushing transaction method and system based on binocular camera | |
CN109543526B (en) | True and false facial paralysis recognition system based on depth difference characteristics | |
CN106897673B (en) | Retinex algorithm and convolutional neural network-based pedestrian re-identification method | |
CN107423690A (en) | A kind of face identification method and device | |
CN107577987A (en) | Identity authentication method, system and device | |
CN106778664A (en) | The dividing method and its device of iris region in a kind of iris image | |
CN107798279B (en) | Face living body detection method and device | |
CN106709450A (en) | Recognition method and system for fingerprint images | |
CN111462379A (en) | Access control management method, system and medium containing palm vein and face recognition | |
US9449217B1 (en) | Image authentication | |
CN105426843A (en) | Single-lens palm vein and palmprint image acquisition apparatus and image enhancement and segmentation method | |
CN108446687B (en) | Self-adaptive face vision authentication method based on interconnection of mobile terminal and background | |
CN110555380A (en) | Finger vein identification method based on Center Loss function | |
CN109255319A (en) | For the recognition of face payment information method for anti-counterfeit of still photo | |
CN109815797A (en) | Biopsy method and device | |
CN113011253B (en) | Facial expression recognition method, device, equipment and storage medium based on ResNeXt network | |
CN107516083A (en) | A kind of remote facial image Enhancement Method towards identification | |
CN108846269A (en) | One kind is towards manifold identity identifying method and identification authentication system | |
CN113469143A (en) | Finger vein image identification method based on neural network learning | |
CN109522865A (en) | A kind of characteristic weighing fusion face identification method based on deep neural network | |
CN107862298A (en) | It is a kind of based on the biopsy method blinked under infrared eye | |
Villariña et al. | Palm vein recognition system using directional coding and back-propagation neural network |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170818 |