CN108875461A - A kind of human face in-vivo detection method and device - Google Patents
A kind of human face in-vivo detection method and device Download PDFInfo
- Publication number
- CN108875461A CN108875461A CN201710341619.2A CN201710341619A CN108875461A CN 108875461 A CN108875461 A CN 108875461A CN 201710341619 A CN201710341619 A CN 201710341619A CN 108875461 A CN108875461 A CN 108875461A
- Authority
- CN
- China
- Prior art keywords
- face
- image
- movement
- picture
- picture quality
- 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
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- 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
Abstract
The invention discloses a kind of human face in-vivo detection method and device, method includes：S100, the facial feature points for obtaining image；Otherwise S200, the picture quality for obtaining image carry out the processing of next frame image, re-execute the steps S100 if picture quality qualification performs the next step suddenly；The number that at least one of S300, random selection deliberate action collection movement and movement are completed is prompted to user；S400, detection user act, if user is interior at the appointed time to complete the number that randomly selected at least one movement and movement are completed in step S300, are determined as living body；Otherwise, it is determined that being non-living body.The present invention can preferably prevent the fraud of the photos and videos broadcast mode in In vivo detection, so that the reliability of In vivo detection and safety are higher.
Description
Technical field
The present invention relates to field of biological recognition more particularly to a kind of human face in-vivo detection method and devices.
Background technique
Currently, biological identification technology is widely used in security fields, it is one of the main means for authenticating user identity.Its
In, face is common a kind of biological characteristic in biological identification technology.
The method of In vivo detection is mainly to be carried out by the physiologic information on identification living body, it is using physiologic information as life
Feature is ordered to distinguish the biological characteristic forged with the non-living matter such as photo, silica gel, molded mud.In general, face In vivo detection
It is faced with three kinds of fraudulent means：Use the photo of user, the video using user, the threedimensional model using user.
It wherein, the use of the photo fraud of user is one of the most common type mode.Reason is that the face image of a people is
It is very easy to acquisition, for example, by the Internet download, captured in the unwitting situation of user by camera etc..Invasion
Person the means such as can be rotated before image capture device by facial image, be overturn, be bent, be waved and cause a kind of to be similar to user
The effect of true man removes deception biometric authentication system.At present, detect an input image be from real human face or
Person is that photo face remains a very challenging job.
Video fraud is that another has face identification system the means of very big threat, what this means showed
The effect of effect and real human face is closely similar, and face's video of user can be obtained by the pinhole cameras in face of it.
And this method has many features, such as head movement, countenance, blink movement etc..These are characterized in that photo does not have
Standby, Just because of this, this fraudulent mean is also to threaten maximum one kind to In vivo detection system；
Threedimensional model has the three-dimensional information of face, however these information are rigid, and are the absence of physiologic information, and
And the threedimensional model that copy a living person is very difficult.So photo deception and video deception are attack face living bodies
Detection system is most common, most common means and method.
Generally speaking, the mankind are when distinguishing real human face or personation face, it is easy to identify the physics of many living bodies
Feature, for example, human face expression changes, mouth variation, end rotation, eye change.However, capturing these minutias for meter
It is very difficult for calculation machine, and under the conditions of uncontrolled, it can be more difficult.
Summary of the invention
The technical problem to be solved in the present invention is that in view of the above drawbacks of the prior art, providing a kind of face living body inspection
Survey method and device.
The technical solution adopted by the present invention to solve the technical problems is：A kind of human face in-vivo detection method is constructed, including：
S100, the facial feature points for obtaining image；
Otherwise S200, the picture quality for obtaining image carry out next frame figure if picture quality qualification performs the next step suddenly
The processing of picture, re-execute the steps S100；
The number that at least one of S300, random selection deliberate action collection movement and movement are completed is prompted to user；
S400, detection user act, if user is interior at the appointed time to complete randomly selected institute in step S300
The number that at least one movement and movement are completed is stated, then is determined as living body；Otherwise, it is determined that being non-living body.
Wherein, the picture quality of acquisition image described in step S200 includes：The peak of image is obtained based on following formula
It is worth judgment criteria of the signal-to-noise ratio PSNR as picture quality and judges image matter if Y-PSNR PSNR is no more than threshold value
Amount qualification is held, and otherwise judges that picture quality is unqualified；
In formula, L takes the line number of the pixel array of 255, M expression image, and N indicates the columns of the pixel array of image, fij
Indicate the grey scale pixel value of the i-th row jth column, f 'ijFor the mean value of the entire pixel array of image, MSE indicates the entire picture of image
The gray scale mean square deviation of pixel array.
Wherein, the done movement of detection user described in step S400 is specially：The variation of facial feature points is detected, if
Variation meets randomly selected at least one variation for acting corresponding characteristic point in step S300 and then judges to complete accordingly
One-off.
Wherein, further include before the step S100：By the face picture shot in actual application environment, non-face figure
Training sample of the piece as Face datection extracts local binary feature to each training sample, and is sent into random forest cascade point
Class device carries out sample learning and training to obtain Face datection classifier；
Wherein, it is specifically included in the step S100：Any one picture is carried out using the Face datection classifier
Face datection and alignment, to return to Face datection information, the Face datection information includes whether containing face, people in picture
The position of face, size and characteristic point location information.
Wherein, further include before the step S100：Deliberate action collection is pre-saved, deliberate action collection includes blink, opens
Mouth shakes the head, nods.
A kind of face living body detection device is also claimed in the present invention, including：
Characteristic point acquiring unit, for obtaining the facial feature points of image；
Picture quality authentication unit triggers if picture quality qualification, otherwise leads to for obtaining the picture quality of image
Know that characteristic point acquiring unit carries out the processing of next frame image；
Random action selection and prompt unit, for randomly choosing the movement of at least one of deliberate action collection and movement
The number of completion is prompted to user；
Motion detection unit is acted for detecting user, if user is interior at the appointed time to complete random action choosing
Select and prompt unit it is randomly selected it is described it is at least one movement and movement complete number, then be determined as living body；Otherwise, sentence
It is set to non-living body.
Wherein, described image quality verification unit includes：
Y-PSNR computation subunit, for obtaining the Y-PSNR PSNR of image based on following formula as image
The judgment criteria of quality；
Authentication unit is used for Y-PSNR PSNR and threshold value comparison, if Y-PSNR PSNR is no more than threshold value,
Then judge that picture quality qualification is held, otherwise judges that picture quality is unqualified；
In formula, L takes the line number of the pixel array of 255, M expression image, and N indicates the columns of the pixel array of image, fij
Indicate the grey scale pixel value of the i-th row jth column, f 'ijFor the mean value of the entire pixel array of image, MSE indicates the entire picture of image
The gray scale mean square deviation of pixel array.
Wherein, the done movement of detection user is specially：Detect facial feature points variation, if variation meet with
It is motor-driven to elect and the variation of the corresponding characteristic point of the randomly selected at least one movement of prompt unit then judges to complete phase
The one-off answered.
Preferably, described device further includes：
Face datection classifier determination unit, for by the face picture shot in actual application environment, non-face figure
Training sample of the piece as Face datection extracts local binary feature to each training sample, and is sent into random forest cascade point
Class device carries out sample learning and training to obtain Face datection classifier；
Wherein, characteristic point acquiring unit is to carry out Face datection to any one picture using the Face datection classifier
And alignment, to return to Face datection information, the Face datection information include in picture whether the position containing face, face
It sets, the location information of size and characteristic point.
Wherein, described device further includes that behavior aggregate presets unit, for pre-saving deliberate action collection, deliberate action Ji Bao
Blink is included, opens one's mouth, shake the head, nodding.
Implement human face in-vivo detection method and device of the invention, has the advantages that：The present invention passes through image
Image is screened in quality testing for the first time, then when carrying out In vivo detection, system random action from deliberate action concentration
And the number of execution, it is desirable that user completes before the deadline, and therefore, user can not be cheated using photo
To pass through In vivo detection, another aspect, since detected movement is randomly selected, the repetition time of detected action request
Number be also it is randomly selected, therefore, user can not be by playing video mode come by In vivo detection, in short, the present invention can
Preferably to prevent the fraud of the photos and videos broadcast mode in In vivo detection, so that the reliability and peace of In vivo detection
Full property is higher.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
The embodiment of invention for those of ordinary skill in the art without creative efforts, can also basis
The attached drawing of offer obtains other attached drawings：
Fig. 1 is the flow chart of the preferred embodiment of human face in-vivo detection method of the invention；
Fig. 2 is the structural schematic diagram of the preferred embodiment of face living body detection device of the invention.
Specific embodiment
To facilitate the understanding of the present invention, a more comprehensive description of the invention is given in the following sections with reference to the relevant attached drawings.In attached drawing
Give exemplary embodiments of the invention.But the invention can be realized in many different forms, however it is not limited to this paper institute
The embodiment of description.On the contrary, purpose of providing these embodiments is make it is more thorough and comprehensive to the disclosure.
It should be noted that word " connected " or " connection ", not only include being connected directly two entities, it also include logical
It crosses and is indirectly connected with other entities beneficial to improvement.
Unless otherwise defined, all technical and scientific terms used herein and belong to technical field of the invention
The normally understood meaning of technical staff is identical.Term as used herein in the specification of the present invention is intended merely to description tool
The purpose of the embodiment of body, it is not intended that in the limitation present invention.
" first ", " second " used in this specification etc. includes that the term of ordinal number can be used for illustrating various constituent elements,
But these constituent elements are not limited by these terms.It is only that using the purpose of these terms and distinguishes a constituent element
In other constituent elements.For example, first constituent element can be named as under the premise of not departing from interest field of the invention
Two constituent elements, similarly, the second constituent element can also be named as the first constituent element.
For a better understanding of the technical solution of the present invention, in conjunction with appended figures and specific embodiments
Technical solution of the present invention is described in detail, it should be understood that the specific features in the embodiment of the present invention and embodiment are
To the detailed description of technical scheme, rather than the restriction to technical scheme, in the absence of conflict, this
Technical characteristic in inventive embodiments and embodiment can be combined with each other.
Human face in-vivo detection method of the invention includes：
S100, the facial feature points for obtaining image；
Face datection is to also detect that facial feature points while detecting face based on LBF method in preferred embodiment.
Specifically, obtaining image from the video sequence of shooting, face inspection is carried out to any one picture using Face datection classifier
It surveys and is aligned, to return to Face datection information, Face datection information includes：In picture whether containing face, face position,
The location information of size and characteristic point.
Wherein, Face datection classifier is predetermined by the following method：By what is shot in actual application environment
The a large amount of training samples of face picture, non-face picture as Face datection extract local binary feature to each training sample
(Local Binary Feature, LBF), and be sent into random forest cascade classifier and carry out sample learning and training, work as training
Precision reach as defined in when requiring, the Face datection classifier that is just needed.
Otherwise S200, the picture quality for obtaining image carry out next frame figure if picture quality qualification performs the next step suddenly
The processing of picture, re-execute the steps S100；
Wherein, the picture quality of the acquisition image includes：The Y-PSNR of image is obtained based on following formula
Judgment criteria of the PSNR as picture quality judges that picture quality qualification is held if Y-PSNR PSNR is no more than threshold value,
Otherwise judge that picture quality is unqualified；
In formula, L takes the line number of the pixel array of 255, M expression image, and N indicates the columns of the pixel array of image, fij
Indicate the grey scale pixel value of the i-th row jth column, f 'ijFor the mean value of the entire pixel array of image, MSE indicates the entire picture of image
The gray scale mean square deviation of pixel array.
Wherein, threshold value can according to circumstances be set, such as can be set to 30, i.e., if picture quality is greater than 30, this frame
Image is not living body, and return step S100 is needed to carry out the processing of next frame image.
The number that at least one of S300, random selection deliberate action collection movement and movement are completed is prompted to user；
Wherein, deliberate action collection pre-saves, deliberate action collection include but is not limited to blink, open one's mouth, shaking the head, point
Head.
S400, detection user act, if user is interior at the appointed time to complete randomly selected institute in step S300
The number that at least one movement and movement are completed is stated, then is determined as living body；Otherwise, it is determined that being non-living body.
Specifically, the variation of detection facial feature points, if variation meet in step S300 it is randomly selected it is described at least
A kind of variation acting corresponding characteristic point then judges to complete corresponding one-off, then is determined as living body；Otherwise, it is determined that being non-
Living body.
If then needing to judge the variation of the characteristic point of human eye for example, prompt needs to blink once in step S300, blink
The variation of the characteristic point of corresponding human eye should be：Firstly, the point set of the characteristic point of human eye is diverging when human eye is to open eyes
's；Then, when closing one's eyes, the point set of the characteristic point of human eye is collected on together；Finally, when human eye is opened eyes,
The point set of the characteristic point of human eye is diverging.I.e. only when above-mentioned variation occurs in the characteristic point of human eye, just determine to complete primary
Blink movement.
Based on the same inventive concept, the invention also discloses a kind of face living body detection device, with reference to Fig. 2, device includes：
Behavior aggregate presets unit, characteristic point acquiring unit, picture quality authentication unit, random action selection and prompt unit, movement inspection
Unit is surveyed, wherein：
Behavior aggregate presets unit, for pre-saving deliberate action collection, deliberate action collection include blink, open one's mouth, shaking the head, point
Head.
Characteristic point acquiring unit, for obtaining the facial feature points of image；
Face datection is to also detect that facial feature points while detecting face based on LBF method in preferred embodiment.
Specifically, obtaining image from the video sequence of shooting, face inspection is carried out to any one picture using Face datection classifier
It surveys and is aligned, to return to Face datection information, Face datection information includes：In picture whether containing face, face position,
The location information of size and characteristic point.
Wherein, Face datection classifier is predetermined by Face datection classifier determination unit, Face datection point
Class device determination unit is a large amount of face pictures that will be shot in actual application environment, non-face picture as the instruction of Face datection
Practice sample, local binary feature (Local Binary Feature, LBF) is extracted to each training sample, and is sent into random gloomy
Woods cascade classifier carries out sample learning and training, when requiring as defined in trained precision reaches, the people that is just needed
Face detects classifier.
Picture quality authentication unit triggers if picture quality qualification, otherwise leads to for obtaining the picture quality of image
Know that characteristic point acquiring unit carries out the processing of next frame image.Specifically, described image quality verification unit includes peak value noise
Than computation subunit and authentication unit.
Wherein, Y-PSNR computation subunit is used to obtain the Y-PSNR PSNR conduct of image based on following formula
The judgment criteria of picture quality；Authentication unit is used for by Y-PSNR PSNR and threshold value comparison, if Y-PSNR PSNR
No more than threshold value, then judges that picture quality qualification is held, otherwise judge that picture quality is unqualified.
In formula, L takes the line number of the pixel array of 255, M expression image, and N indicates the columns of the pixel array of image, fij
Indicate the grey scale pixel value of the i-th row jth column, f 'ijFor the mean value of the entire pixel array of image, MSE indicates the entire picture of image
The gray scale mean square deviation of pixel array.
Random action selection and prompt unit, for randomly choosing the movement of at least one of deliberate action collection and movement
The number of completion is prompted to user；
Motion detection unit is acted for detecting user, if user is interior at the appointed time to complete random action choosing
Select and prompt unit it is randomly selected it is described it is at least one movement and movement complete number, then be determined as living body；Otherwise, sentence
It is set to non-living body.
In conclusion implementing human face in-vivo detection method and device of the invention, have the advantages that：The present invention
It is detected by picture quality, image is screened for the first time, then when carrying out In vivo detection, system is from deliberate action concentration
Random action and the number of execution, it is desirable that user completes before the deadline, and therefore, user can not utilize photograph
Piece is cheated to by In vivo detection, on the other hand, due to detected movement be it is randomly selected, be detected action request
Number of repetition be also it is randomly selected, therefore, user can not by playing video mode come by In vivo detection, in short,
The present invention can preferably prevent the fraud of the photos and videos broadcast mode in In vivo detection so that In vivo detection can
It is higher by property and safety.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the program can be stored in a computer-readable storage medium
In, the program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, the storage medium can be magnetic
Dish, CD, read-only memory (Read Only Memory, ROM) or random access memory (Random
ABBessMemory, RAM) etc..
The embodiment of the present invention is described with above attached drawing, but the invention is not limited to above-mentioned specific
Embodiment, the above mentioned embodiment is only schematical, rather than restrictive, those skilled in the art
Under the inspiration of the present invention, without breaking away from the scope protected by the purposes and claims of the present invention, it can also make very much
Form, all of these belong to the protection of the present invention.
Claims (10)
1. a kind of human face in-vivo detection method, which is characterized in that including：
S100, the facial feature points for obtaining image；
Otherwise S200, the picture quality for obtaining image carry out next frame image if picture quality qualification performs the next step suddenly
Processing, re-execute the steps S100；
The number that at least one of S300, random selection deliberate action collection movement and movement are completed is prompted to user；
S400, detection user act, if user at the appointed time in complete step S300 in it is randomly selected described in extremely
The number that a kind of few movement and movement are completed, then be determined as living body；Otherwise, it is determined that being non-living body.
2. human face in-vivo detection method according to claim 1, which is characterized in that acquisition image described in step S200
Picture quality include：Judgment criteria of the Y-PSNR PSNR of image as picture quality is obtained based on following formula, such as
Fruit Y-PSNR PSNR is no more than threshold value, then judges that picture quality qualification is held, otherwise judge that picture quality is unqualified；
In formula, L takes the line number of the pixel array of 255, M expression image, and N indicates the columns of the pixel array of image, fijIt indicates
The grey scale pixel value of i-th row jth column, f 'ijFor the mean value of the entire pixel array of image, MSE indicates the entire pixel battle array of image
The gray scale mean square deviation of column.
3. human face in-vivo detection method according to claim 1, which is characterized in that detection user described in step S400
Done movement is specially：Detect the variation of facial feature points, if variation meet in step S300 it is randomly selected it is described at least
A kind of variation acting corresponding characteristic point then judges to complete corresponding one-off.
4. human face in-vivo detection method according to claim 1, which is characterized in that further include before the step S100：
Using the face picture shot in actual application environment, non-face picture as the training sample of Face datection, to each training
Sample extraction local binary feature, and be sent into random forest cascade classifier and carry out sample learning and training to obtain Face datection
Classifier；
Wherein, it is specifically included in the step S100：Face is carried out to any one picture using the Face datection classifier
Detection and alignment, to return to Face datection information, whether the Face datection information includes in picture containing face, face
Position, size and characteristic point location information.
5. human face in-vivo detection method according to claim 1, which is characterized in that further include before the step S100：
Deliberate action collection is pre-saved, deliberate action collection includes blinking, opening one's mouth, shaking the head, nodding.
6. a kind of face living body detection device, which is characterized in that including：
Characteristic point acquiring unit, for obtaining the facial feature points of image；
Picture quality authentication unit triggers if picture quality qualification for obtaining the picture quality of image, and otherwise notice is special
Sign point acquiring unit carries out the processing of next frame image；
Random action selection and prompt unit are completed for randomly choosing the movement of at least one of deliberate action collection and movement
Number be prompted to user；
Motion detection unit is acted for detecting user, if user at the appointed time in complete random action selection and
The number that the randomly selected at least one movement of prompt unit and movement are completed, then be determined as living body；Otherwise, it is determined that being
Non-living body.
7. face living body detection device according to claim 6, which is characterized in that described image quality verification unit packet
It includes：
Y-PSNR computation subunit, for obtaining the Y-PSNR PSNR of image based on following formula as picture quality
Judgment criteria；
Authentication unit, for sentencing Y-PSNR PSNR and threshold value comparison if Y-PSNR PSNR is no more than threshold value
Disconnected picture quality qualification is held, and otherwise judges that picture quality is unqualified；
In formula, L takes the line number of the pixel array of 255, M expression image, and N indicates the columns of the pixel array of image, fijIt indicates
The grey scale pixel value of i-th row jth column, f 'ijFor the mean value of the entire pixel array of image, MSE indicates the entire pixel battle array of image
The gray scale mean square deviation of column.
8. face living body detection device according to claim 6, which is characterized in that the detection user does movement tool
Body is：Detect the variation of facial feature points, if variation meet random action selection and prompt unit it is randomly selected it is described extremely
A kind of few variation for acting corresponding characteristic point then judges to complete corresponding one-off.
9. face living body detection device according to claim 6, which is characterized in that described device further includes：
Face datection classifier determination unit, for making the face picture shot in actual application environment, non-face picture
For the training sample of Face datection, local binary feature is extracted to each training sample, and is sent into random forest cascade classifier
Sample learning and training are carried out to obtain Face datection classifier；
Wherein, characteristic point acquiring unit is to carry out Face datection and right to any one picture using the Face datection classifier
Together, to return to Face datection information, the Face datection information include in picture whether the position, big containing face, face
Small and characteristic point location information.
10. face living body detection device according to claim 6, which is characterized in that described device further includes that behavior aggregate is pre-
If unit, for pre-saving deliberate action collection, deliberate action collection includes blinking, opening one's mouth, shaking the head, nodding.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710341619.2A CN108875461A (en) | 2017-05-16 | 2017-05-16 | A kind of human face in-vivo detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710341619.2A CN108875461A (en) | 2017-05-16 | 2017-05-16 | A kind of human face in-vivo detection method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108875461A true CN108875461A (en) | 2018-11-23 |
Family
ID=64320614
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710341619.2A Pending CN108875461A (en) | 2017-05-16 | 2017-05-16 | A kind of human face in-vivo detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108875461A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109558856A (en) * | 2018-12-08 | 2019-04-02 | 北京俩俩科技有限公司 | On a kind of certification line between user true friend relation system and method |
| CN109671318A (en) * | 2019-02-02 | 2019-04-23 | 姜召英 | Online teaching equipment, method and system |
| CN110247898A (en) * | 2019-05-23 | 2019-09-17 | 平安普惠企业管理有限公司 | Auth method, device, medium and electronic equipment |
| CN110276313A (en) * | 2019-06-25 | 2019-09-24 | 网易（杭州）网络有限公司 | Identity identifying method, identification authentication system, medium and calculating equipment |
| CN110309798A (en) * | 2019-07-05 | 2019-10-08 | 中新国际联合研究院 | A kind of face cheat detecting method extensive based on domain adaptive learning and domain |
| CN111222380A (en) * | 2018-11-27 | 2020-06-02 | 杭州海康威视数字技术股份有限公司 | Living body detection method and device and recognition model training method thereof |
| WO2021000415A1 (en) * | 2019-07-03 | 2021-01-07 | 平安科技（深圳）有限公司 | Method and device for live user detection, computer device, and storage medium |
-
2017
- 2017-05-16 CN CN201710341619.2A patent/CN108875461A/en active Pending
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111222380A (en) * | 2018-11-27 | 2020-06-02 | 杭州海康威视数字技术股份有限公司 | Living body detection method and device and recognition model training method thereof |
| CN111222380B (en) * | 2018-11-27 | 2023-11-03 | 杭州海康威视数字技术股份有限公司 | Living body detection method and device and recognition model training method thereof |
| CN109558856A (en) * | 2018-12-08 | 2019-04-02 | 北京俩俩科技有限公司 | On a kind of certification line between user true friend relation system and method |
| CN109671318A (en) * | 2019-02-02 | 2019-04-23 | 姜召英 | Online teaching equipment, method and system |
| CN109671318B (en) * | 2019-02-02 | 2020-09-08 | 广州宏途教育网络科技有限公司 | Online teaching equipment, method and system based on image processing |
| CN110247898A (en) * | 2019-05-23 | 2019-09-17 | 平安普惠企业管理有限公司 | Auth method, device, medium and electronic equipment |
| WO2020233009A1 (en) * | 2019-05-23 | 2020-11-26 | 平安普惠企业管理有限公司 | Identity authentication method and apparatus, computing device, and storage medium |
| CN110247898B (en) * | 2019-05-23 | 2021-11-19 | 平安普惠企业管理有限公司 | Identity verification method, identity verification device, identity verification medium and electronic equipment |
| CN110276313A (en) * | 2019-06-25 | 2019-09-24 | 网易（杭州）网络有限公司 | Identity identifying method, identification authentication system, medium and calculating equipment |
| CN110276313B (en) * | 2019-06-25 | 2022-04-22 | 杭州网易智企科技有限公司 | Identity authentication method, identity authentication device, medium and computing equipment |
| WO2021000415A1 (en) * | 2019-07-03 | 2021-01-07 | 平安科技（深圳）有限公司 | Method and device for live user detection, computer device, and storage medium |
| CN110309798A (en) * | 2019-07-05 | 2019-10-08 | 中新国际联合研究院 | A kind of face cheat detecting method extensive based on domain adaptive learning and domain |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108875461A (en) | A kind of human face in-vivo detection method and device | |
| US10650261B2 (en) | System and method for identifying re-photographed images | |
| Asep | A design of continuous user verification for online exam proctoring on M-learning | |
| Fathy et al. | Face-based active authentication on mobile devices | |
| CN103440479B (en) | A kind of method and system for detecting living body human face | |
| CN109461003A (en) | Plurality of human faces scene brush face payment risk preventing control method and equipment based on multi-angle of view | |
| CN109740501A (en) | A kind of Work attendance method and device of recognition of face | |
| CN105303089A (en) | Camera applications in a handheld device | |
| CN107480586B (en) | Face characteristic point displacement-based biometric photo counterfeit attack detection method | |
| Pravallika et al. | SVM classification for fake biometric detection using image quality assessment: Application to iris, face and palm print | |
| CN112507889A (en) | Method and system for verifying certificate and certificate holder | |
| CN111666835A (en) | Face living body detection method and device | |
| CN107992845A (en) | A kind of face recognition the method for distinguishing and device, computer equipment | |
| CN111178130A (en) | Face recognition method, system and readable storage medium based on deep learning | |
| CN109376704A (en) | A kind of human face in-vivo detection method | |
| Benlamoudi | Multi-modal and anti-spoofing person identification | |
| Garg et al. | Biometric authentication using soft biometric traits | |
| Iwasokun et al. | Design of e-invigilation framework using multi-modal biometrics | |
| CN108764033A (en) | Auth method and device, electronic equipment, computer program and storage medium | |
| CN114299569A (en) | Safe face authentication method based on eyeball motion | |
| Singh et al. | Attendance monitoring and management using QR code based sensing with cloud based Processing | |
| CN112069915B (en) | ATM with face recognition system | |
| Kawamata et al. | Face authentication for e-Learning using time series information | |
| Kainz et al. | Students’ Attendance Monitoring through the Face Recognition | |
| Kharabe et al. | An efficient study on various biometric methods |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20181123 |
|
| WD01 | Invention patent application deemed withdrawn after publication |