CN109886084A - Face authentication method, electronic equipment and storage medium based on gyroscope - Google Patents
Face authentication method, electronic equipment and storage medium based on gyroscope Download PDFInfo
- Publication number
- CN109886084A CN109886084A CN201910004291.4A CN201910004291A CN109886084A CN 109886084 A CN109886084 A CN 109886084A CN 201910004291 A CN201910004291 A CN 201910004291A CN 109886084 A CN109886084 A CN 109886084A
- Authority
- CN
- China
- Prior art keywords
- image
- face
- movement
- face authentication
- gyroscope
- 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
Abstract
The invention discloses the face authentication methods based on gyroscope, comprising the following steps: identification model establishment step: user completes the identification model of each movement when establishing user's face authentication;Face authenticating step: video image when user completes each movement when obtaining user's face authentication, and it is compared with identification model and obtains the second comparing result;Equipment authenticating step: user completes the gyro data of the handheld device of each movement when obtaining user's face authentication, and the gyro data and system pre-stored data are compared and obtain the first comparing result;Authentication determination step: judge whether user's face authentication passes through according to the first comparing result and the second comparing result;Wherein, there is no sequencing when face authenticating step and equipment authenticating step execute.It can effectively prevent carrying out deception sexual assault using picture or video etc. through the invention to carry out face verification.The present invention also provides a kind of electronic equipment and storage mediums.
Description
Technical field
The present invention relates to field of face identification, more particularly to a kind of living body faces authentication method on intelligent devices, electricity
Sub- equipment and storage medium.
Background technique
Recognition of face is a kind of biological identification technology for carrying out identification based on facial feature information of people.By with taking the photograph
Camera or camera acquire image or video flowing containing face, and automatic detection and tracking face in the picture, and then to inspection
The face that measures carries out a series of the relevant technologies of face recognition, usually also referred to as Identification of Images, face recognition.And currently, people
Face identification has been widely used in finance, the administration of justice, army, public security, frontier inspection, government, space flight, electric power, factory, education, medical treatment
And the fields such as numerous enterprises and institutions.With further mature and Social Agree the raising of technology, face recognition technology will
It applies in more fields.
However, facial image and video information are all easier to be replicated to usurp, for example pass through face mask, screen face
The behavior that deception verifying is carried out etc. everybody face is pretended to be, so that there are larger security risks for recognition of face.Know especially as face
It is not increasingly being applied to the scene that security protection, financial field etc. need authentication, then comes with greater need for effective, reliable way
Take precautions against the security attack of face mask etc..
Summary of the invention
For overcome the deficiencies in the prior art, one of the objects of the present invention is to provide the face authentication sides based on gyroscope
Method, be able to solve in the prior art can not cog region get user's living body faces certification out with by face mask, screen
Facial image or video etc. are come the problem of verifying.
The second object of the present invention is to provide a kind of electronic equipment, and being able to solve can not identify in the prior art
Out user's face authentication with by face mask, screen facial image or video etc. come the problem of verifying.
The third object of the present invention is to provide a kind of computer readable storage medium, be able to solve in the prior art not
It can identify and obtain user's face authentication and by face mask, screen facial image or video etc. come the problem of verifying.
An object of the present invention adopts the following technical scheme that realization:
Face authentication method based on gyroscope, comprising the following steps:
Identification model establishment step: the identification model of each movement is completed when establishing each user's face authentication;
Face authenticating step: completing the video image of each movement when obtaining active user's face authentication, and by itself and knowledge
Other model, which compares, obtains the first comparing result;
Equipment authenticating step: the gyroscope number of the handheld device of each movement is completed when obtaining active user's face authentication
According to, and the gyro data and system pre-stored data are compared and obtain the second comparing result;
Authentication determination step: judge whether active user's face authentication leads to according to the first comparing result and the second comparing result
It crosses;
Wherein, there is no sequencing when face authenticating step and equipment authenticating step execute.
Further, face authenticating step further include:
Gray proces step: obtaining multiple corresponding images according to the video image that active user completes each movement, and
Gray proces are carried out to every image and obtain corresponding grayscale image;
Extraction step: the feature vector of every image is obtained to the extraction that the grayscale image of every image carries out feature vector;
Comparison step: the feature vector that active user completes every image of each movement is compared with identification model
Obtain the first comparing result.
Further, the active user completes the acquisition process of the video image of each movement further include: obtains first
Video image when everything is completed when active user's face authentication, and the time of each movement is then completed according to active user
Video Image Segmentation is completed to the video image of each movement at active user.
Further, the identification model establishment step specifically includes the following steps:
Step A1: the process that each user completes each movement is carried out to shoot multiple images, and according to movement to image
Carry out taxonomic revision;
Step A2: utilizing Weighted Average Algorithm, carries out gray proces to every image, obtains the grayscale image of every image;
Step A3: the grayscale image of every image is carried out to divide M*N grid spaces, according to the wheel at each position of face
The different face of the point in image when the wide, difference of color and each position of face are under different action states, different angle
Color density distribution situation, the points and correspondence image calculated in each region of every image the ratio between are always counted, and extract every
The feature vector of image;Wherein M > 0, N > 0, and M, N are natural number;
Step A4: it is utilized using the feature vector of every image as input by the corresponding movement of every image as output
Convolutional neural networks carry out repetition training, establish the identification model that each user completes each movement.
Further, the authentication determination step further include: when the first comparing result is to be verified, and second compares
As a result for when being verified, active user's face authentication passes through.
Further, the equipment authenticating step further include: compare the gyro data and systemic presupposition threshold value
Obtain the second comparing result;
Or each user pre-stored in the gyro data and system is completed into the handheld device of respective action
Gyro data compares, and obtains the second comparing result.
Further, the handheld device is mobile phone, plate and face authentication mobile terminal.
Further, the gyroscope is three-axis gyroscope.
The second object of the present invention adopts the following technical scheme that realization:
A kind of electronic equipment can be run on a memory and on a processor including memory, processor and storage
Computer program realizes that the face as described in one of the object of the invention based on gyroscope is recognized when the processor executes described program
The step of card method.
The third object of the present invention adopts the following technical scheme that realization:
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
The step of face authentication method as described in one of the object of the invention based on gyroscope is realized when row.
Compared with prior art, the beneficial effects of the present invention are:
The present invention is established according to image when user's face verification in the facial characteristics variation for completing deliberate action first to be known
Other model, and in the gyro data built in the handheld device for completing deliberate action when recording user's face verification;Then exist
When verifying, the facial characteristics of user's face changes and the gyroscope built in handheld device when by the way that user being carried out face verification
Data are combined, and can effectively prevent testing by the progress duplicity face such as Pre-built Videos images such as face mask, screen face
The problem of card.
Detailed description of the invention
Fig. 1 is the face authentication method flow chart provided by the invention based on gyroscope.
Specific embodiment
In the following, being described further in conjunction with attached drawing and specific embodiment to the present invention, it should be noted that not
Under the premise of conflicting, new implementation can be formed between various embodiments described below or between each technical characteristic in any combination
Example.
The present invention is used for user by the gyro data for carrying the smart machines such as smart phone, tablet computer and carries out people
Face identifies in authentication operation, for example the three-axis gyroscope by obtaining smart machine obtains user and recognizes in progress recognition of face face
The translational acceleration and angle change information of smart machine when card operation, instruction performance when being verified in conjunction with user into
Pedestrian's face authentication determination that is to say and be combined face authenticating and equipment certification, can effectively prevent by replicating, usurping view
Frequency image carries out the security attack behavior of deception certification.
The invention discloses embodiments one, as shown in Figure 1, the face authentication method based on gyroscope, including face authenticating
With equipment authenticate, wherein face authenticating the following steps are included:
Step S11: starting face authentication and it is complete to obtain the prompt that active user provides according to the default verifying of system instruction
At the video image of everything.Such as active user done according to the prompt that provides of the default verifying of system instruction it is a series of
The video image of everything.
When opening the certification of video living body faces, active user will use handheld device, such as smart phone etc. simultaneously first
Handheld device face face face is shot to the facial image of itself, and system can provide a system according to default verifying instruction
The prompt action of column come indicate active user complete.For example it opens one's mouth, shooting state is kept to translate mobile phone to the left side or the right;It stretches out
Tongue keeps shooting state to translate mobile phone to front;Tongue is rolled, shooting state is kept to translate mobile phone to the right side or the left side;It receives
Return tongue.Wherein, each prompt action stops that the several seconds need to be paused and combines the lasting shooting of angle holding for moving in parallel handheld device
State.User includes using in the video image for completing that default verifying instruction will be obtained when all movements, the video image
Complete the video of prompt action all in the default verifying instruction in family.The video of predetermined registration operation process is completed by obtaining user
Image such as includes the action video image of mouth, tongue etc. in the image.
Step S12: each of when instructing acquisition active user to complete the default verifying instruction according to the default verifying of system
Movement.For example, will include multiple verifying instructions may include multiple movements for each default verifying instruction.It is used when current
When the execution of family, system can call the realization of the equipment such as camera to record a video active user's execution, packet in the video recording
Include the image that active user completes everything.
Video image: being split by step S13 according to the deadline of each movement and it is every to show that active user completes
The video image of a movement.Due to active user's just pause several seconds confirmation when completing each movement, then execute again next
A movement, therefore above-mentioned Video Image Segmentation can be come according to the deadline of each movement, it is every to show that active user completes
The video image of a movement.
In addition, in the actual use process, the video image of each movement is completed for obtaining active user, it can also be with
It is directly to complete a movement every time in execution just to store the video image of the movement, so there is no need to right
Whole video image is split.
For example default verifying instruction needs three movements of user's completion: movement A, movement B and movement C are then regarded in generation
When frequency image:
First, by video image and stored when user is continuously finished three movements, in this way according to each movement complete when
Between section video image is split can obtain the video image for completing each movement;
Second, just video image is stored when user's one movement of every completion, and according to execution by video figure
As storing respectively.
Step S14: show that active user completes each movement according to the video image that active user completes each movement
Modified-image is acted, and it is compared with identification model, and obtain the second comparing result.
For different users when completing each movement, the changes in faces of face is different, and therefore, the present invention passes through preparatory
Classification annotation processing is carried out according to the video image that each user completes each movement of default verifying instruction, and is passed through volume
Product neural network obtains the identification model of each movement after being trained.In this way in certification, it is only necessary to by active user's face
The video image of each movement is completed when verifying and identification model is matched to obtain matching result, can finally be tied according to matching
Fruit is to determine whether certification passes through.
In addition, the present invention in order to verify each movement when user completes default verifying instruction movement modified-image whether
When meeting the requirements, it is also necessary to pre-establish identification model.The identification model is to utilize to go back video capture handheld device according to shooting
User's face feature different angle variation come obtain multiple angles stereo-picture establish.For example it is translated in handheld device
In the process, the image of plane can be because the bias of shooting angle changes so that obtained flat image inclination is thinning, and can not obtain
To the stereo-picture at the positions such as the corresponding mouth of other shooting angle, tongue;And if it is user shot then because
Shooting main body be it is three-dimensional, the stereo-picture of all angles at the positions such as mouth, the tongue of user's face can be taken, because
This, can use the identification model of foundation to exclude the certification of the deception sexual assault of flat image.For example it collects arrange packet in advance
It includes user's video image of the movement at each position of user's face when completing corresponding default verifying instruction and carries out classification annotation,
The corresponding key frame images input convolutional neural networks of video image for extracting each movement respectively are trained, by instructing repeatedly
Practice the identification model for establishing each movement.In this way when verifying judges, each movement of instruction is verified in the video figure that will acquire
Corresponding key frame images input convolutional neural networks make the template samples of itself and each movement in established identification model
Comparison judges the correctness that each movement of user is completed, and then knows whether the user is correctly completed default verifying instruction.
The present invention also illustrates and provides the establishment process of identification model, comprising the following steps:
Step A1: such as to the state of opening one's mouth, stretch out tongue state, each movement such as roll tongue or movement complete process are clapped
Take the photograph from front and move to left side, moved to from front all angles such as right side image (such as correspond to open one's mouth, stretch out tongue,
Shooting state is kept to move to the left side or the right using mobile phone when rolling the verifyings such as tongue movement), it is not sharing the same light to above-mentioned image
It carries out being stored after respective action progress taxonomic revision is collected in a large amount of shootings under line.
Step A2: utilizing Weighted Average Algorithm, carries out gray proces to every image, obtains the grayscale image of every image.
Step A3: dividing M*N grid spaces for image, according to mouth, the profile at tongue position, color and different movements
The different colours Density Distribution situation of point under state, when different angle in image, calculate the points each sung in region with
Image the ratio between is always counted, and the feature vector of every image is extracted.Wherein M, N are natural number.
Step A4: using the feature vector of every obtained image as input, by the corresponding movement of every image as defeated
Out, repetition training is carried out using convolutional neural networks, establishes the identification model of each movement.
The identification model that user completes each movement can be established by the above method, it thus can be by current authentication
User, which completes the video image of each movement and the identification model, to carry out face verification to current authentication user.
In addition, face mask or prerecording video, image in order to prevent etc. and carrying out deception sexual assault to carry out face
Certification, the data that the present invention also passes through the gyroscope built in handheld device of the addition user when completing each movement are carried out into one
Step card.
Further, equipment authenticates further include: step S21: obtaining active user and completes when each movement in handheld device
The three-axis gyroscope data set.Since real user is when carrying out face authentication, needs to carry out handheld device and verified, such as
Hand-held intelligent mobile phone, Intelligent flat, certification terminal device etc., and user is when completing each movement, built in handheld device
Gyroscope will generate corresponding data, such as translational acceleration, angle change data etc.;And if not real user, than
When as carried out face authentication by the video image prerecorded, mobile device itself be not will do it is mobile, in other words
Gyroscope built in it would not generate corresponding data.Therefore, when carrying out face authentication, by will be built in handheld device
The data of gyroscope are added in authentication determination, ensure that true user when user's face authentication is authenticated.
In general, in handheld device, such as smart phone, built in gyroscope be three-axis gyroscope, therefore with
Three-axis gyroscope data when each movement built in record handheld device are completed at family, then by the three-axis gyroscope data and system
In each user for prestoring completed each movement when three-axis gyroscope data it is whether consistent, if so, thinking that certification is logical
It crosses.It that is to say: step S22: three-axis gyroscope data and system when active user is completed each movement built in handheld device
Preset data compares, and obtains the second comparing result.
Three-axis gyroscope data include translational acceleration and angle change data.It can when judging the change in location of handheld device
By translational acceleration and angle whether with default verifying instructions match corresponding in the transformation period section.
In the actual use process, for example active user completes the video image of each movement there are two types of acquisition modes,
Then also there are two types of modes for the data of corresponding gyroscope: when such as user continuously finishes the everything of default verifying instruction,
The data of continuous record gyroscope;And when for another example storing the video image that user completes each movement respectively, also will
Gyro data when user completes each movement stores respectively.
In fact, if authenticating using the video image prerecorded, when completing default verifying instruction
Three-axis gyroscope data built in smart machine should be it is constant, and it is pre-stored consistent in system.In other words, because it is logical
The video of all angles such as the mouth recorded, tongue variation is crossed when carrying out deception sexual assault, is that the main body in video is changing
Angles and positions, for verify shooting mobile phone or shielding computer remain static, built in three-axis gyroscope will not produce
The delta data of the male character types in Chinese operas, usu. referring tov the bearded character degree or acceleration, and only when user is that hand-held mobile phone or tablet computer complete default verifying instruction in real time
When record video image when, the situation of change of mouth, tongue position is obtained by the position and angle change of handheld device,
Then accordingly the three-axis gyroscope built in handheld device will generate the delta data of angle or acceleration.
Step S3: judged according to the first comparing result and the second comparing result the certification whether be active user face
Certification, if so, illustrating that active user's certification passes through.
When judging, only when the first comparing result and the second comparing result meet preset condition simultaneously, just think to use
The face authentication at family passes through.It that is to say: being only verified when active user completes default verifying instruction, and handheld device
When built-in three-axis gyroscope data verification passes through, it is just considered the face authentication of active user, rather than it is other using pre-
Video first recorded etc. carries out the certification of deception sexual assault, otherwise, then it authenticates and does not pass through.
Such as first comparing result, it that is to say that face action is matched with identification model, matching result reaches 85%
More than, and angle judge to from left to right translate reach 15 degree or more, acceleration range be greater than setting threshold value, that is, think people
Face certification passes through.The threshold value of acceleration range can be according to practical any setting, because if to use recorded video duplicity
When certification, capture apparatus is not no displacement data, as long as that is to say that true verifying brief acceleration not can be realized mainly for 0.
Further, further include step S23 in the equipment authenticating step: being held when active user is completed each movement
The three-axis gyroscope number built in handheld device when respective action is completed in three-axis gyroscope data and system built in equipment
According to comparing, and obtain third comparing result.Further, the invention also includes step S4: according to the first comparing result and
Third comparing result judges whether the certification is the face authentication of active user, if so, illustrating that active user's certification passes through.
It in other words, is by pre- in the verifying of the gyro data for the handheld device for completing each movement to active user
First collect the gyro data built in handheld device when different user completes each movement, and by itself and corresponding user completion pair
The identification model that should be acted is bound.Namely: before face authentication, need the identification model by each movement to be stored in be
In system, while the three-axis gyroscope data of the handheld device also by user when completing each movement are also stored in system, and
The two is associated according to each movement that user completes.
In certification, active user is completed each in gyro data and system built in the handheld device of each movement
The gyro data built in handheld device when user's execution carries out matching comparison, obtains third comparing result.
In this way, then active user completes the gyro built in the handheld device of each movement only when face authenticating passes through
Instrument data are consistent with the corresponding gyro data that active user prestores in system, then it is assumed that certification passes through.
The present invention is combined by face authenticating and equipment certification, reaches the living body authentication to user's face, can be effective
Prevent the security attack behavior that deception certification is carried out by replicating, usurping video image.
The present invention also provides a kind of electronic equipment comprising memory, processor and storage are on a memory and can
The computer program run in processing, the processor are realized when executing described program as described herein based on the people of gyroscope
The step of face authentication method.
The present invention also provides a kind of computer readable storage mediums, are stored thereon with computer program, computer program
The step of face authentication method based on gyroscope as previously described is realized when being executed by processor.
The above embodiment is only the preferred embodiment of the present invention, and the scope of protection of the present invention is not limited thereto,
The variation and replacement for any unsubstantiality that those skilled in the art is done on the basis of the present invention belong to institute of the present invention
Claimed range.
Claims (10)
1. the face authentication method based on gyroscope, which comprises the following steps:
Identification model establishment step: the identification model of each movement is completed when establishing each user's face authentication;
Face authenticating step: the video image of each movement is completed when obtaining active user's face authentication, and by it and identifies mould
Type, which compares, obtains the first comparing result;
Equipment authenticating step: completing the gyro data of the handheld device of each movement when obtaining active user's face authentication, and
The gyro data and system pre-stored data are compared and obtain the second comparing result;
Authentication determination step: judge whether active user's face authentication passes through according to the first comparing result and the second comparing result;
Wherein, there is no sequencing when face authenticating step and equipment authenticating step execute.
2. according to claim 1 based on the face authentication method of gyroscope, which is characterized in that face authenticating step is also wrapped
It includes:
Gray proces step: multiple corresponding images are obtained according to the video image that active user completes each movement, and to every
It opens image progress gray proces and obtains corresponding grayscale image;
Extraction step: the feature vector of every image is obtained to the extraction that the grayscale image of every image carries out feature vector;
Comparison step: the feature vector that active user completes every image of each movement is compared with identification model and is obtained
First comparing result.
3. according to claim 1 based on the face authentication method of gyroscope, which is characterized in that the active user completes every
The acquisition process of the video image of a movement further include: view when everything is completed when obtaining active user's face authentication first
Video Image Segmentation is completed each movement at active user by frequency image, the time that each movement is then completed according to active user
Video image.
4. according to claim 1 based on the face authentication method of gyroscope, which is characterized in that the identification model establishes step
It is rapid specifically includes the following steps:
Step A1: the process that each user completes each movement is carried out to shoot multiple images, and image is carried out according to movement
Taxonomic revision;
Step A2: utilizing Weighted Average Algorithm, carries out gray proces to every image, obtains the grayscale image of every image;
Step A3: the grayscale image of every image is carried out to divide M*N grid spaces, according to the profile at each position of face, face
The different colours of the point in image when each position of difference and face of color is under different action states, different angle are close
The ratio between distribution situation is spent, the points and correspondence image in each region of every image of calculating are always counted, extract every image
Feature vector;Wherein M > 0, N > 0, and M, N are natural number;
Step A4: convolution is utilized by the corresponding movement of every image as output using the feature vector of every image as input
Neural network carries out repetition training, establishes the identification model that each user completes each movement.
5. according to claim 1 based on the face authentication method of gyroscope, which is characterized in that the authentication determination step is also
It include: when the first comparing result is to be verified, and the second comparing result is when being verified, active user's face authentication is logical
It crosses.
6. according to claim 1 based on the face authentication method of gyroscope, which is characterized in that the equipment authenticating step is also
It include: to compare the gyro data and systemic presupposition threshold value to obtain the second comparing result;
Or each user pre-stored in the gyro data and system is completed to the gyro of the handheld device of respective action
Instrument data compare, and obtain the second comparing result.
7. according to claim 1 based on the face authentication method of gyroscope, which is characterized in that the handheld device is hand
Machine, plate and face authentication mobile terminal.
8. according to claim 1 based on the face authentication method of gyroscope, which is characterized in that the gyroscope is three axis tops
Spiral shell instrument.
9. a kind of electronic equipment including memory, processor and stores the meter that can be run on a memory and on a processor
Calculation machine program, it is characterised in that: realize when the processor executes described program and be based on as described in any one of claim 1-8
The step of face authentication method of gyroscope.
10. a kind of computer readable storage medium, is stored thereon with computer program, it is characterised in that: the computer program
The step of face authentication method as described in any one of claim 1-8 based on gyroscope is realized when being executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910004291.4A CN109886084A (en) | 2019-01-03 | 2019-01-03 | Face authentication method, electronic equipment and storage medium based on gyroscope |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910004291.4A CN109886084A (en) | 2019-01-03 | 2019-01-03 | Face authentication method, electronic equipment and storage medium based on gyroscope |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109886084A true CN109886084A (en) | 2019-06-14 |
Family
ID=66925592
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910004291.4A Pending CN109886084A (en) | 2019-01-03 | 2019-01-03 | Face authentication method, electronic equipment and storage medium based on gyroscope |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109886084A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112200120A (en) * | 2020-10-23 | 2021-01-08 | 支付宝(杭州)信息技术有限公司 | Identity recognition method, living body recognition device and electronic equipment |
CN112380979A (en) * | 2020-11-12 | 2021-02-19 | 平安科技(深圳)有限公司 | Living body detection method, living body detection device, living body detection equipment and computer readable storage medium |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103973441A (en) * | 2013-01-29 | 2014-08-06 | 腾讯科技(深圳)有限公司 | User authentication method and device on basis of audios and videos |
CN105205455A (en) * | 2015-08-31 | 2015-12-30 | 李岩 | Liveness detection method and system for face recognition on mobile platform |
CN105260726A (en) * | 2015-11-11 | 2016-01-20 | 杭州海量信息技术有限公司 | Interactive video in vivo detection method based on face attitude control and system thereof |
US20170032114A1 (en) * | 2010-11-29 | 2017-02-02 | Biocatch Ltd. | System, method, and device of detecting identity of a user and authenticating a user |
CN106650555A (en) * | 2015-11-02 | 2017-05-10 | 苏宁云商集团股份有限公司 | Real person verifying method and system based on machine learning |
CN107220590A (en) * | 2017-04-24 | 2017-09-29 | 广东数相智能科技有限公司 | A kind of anti-cheating network research method based on In vivo detection, apparatus and system |
CN107943449A (en) * | 2017-12-23 | 2018-04-20 | 河南智盈电子技术有限公司 | A kind of intelligent sound system based on human facial expression recognition |
CN108710788A (en) * | 2018-05-22 | 2018-10-26 | 上海众人网络安全技术有限公司 | A kind of safety certifying method, device, terminal and storage medium |
-
2019
- 2019-01-03 CN CN201910004291.4A patent/CN109886084A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20170032114A1 (en) * | 2010-11-29 | 2017-02-02 | Biocatch Ltd. | System, method, and device of detecting identity of a user and authenticating a user |
CN103973441A (en) * | 2013-01-29 | 2014-08-06 | 腾讯科技(深圳)有限公司 | User authentication method and device on basis of audios and videos |
CN105205455A (en) * | 2015-08-31 | 2015-12-30 | 李岩 | Liveness detection method and system for face recognition on mobile platform |
CN106650555A (en) * | 2015-11-02 | 2017-05-10 | 苏宁云商集团股份有限公司 | Real person verifying method and system based on machine learning |
CN105260726A (en) * | 2015-11-11 | 2016-01-20 | 杭州海量信息技术有限公司 | Interactive video in vivo detection method based on face attitude control and system thereof |
CN107220590A (en) * | 2017-04-24 | 2017-09-29 | 广东数相智能科技有限公司 | A kind of anti-cheating network research method based on In vivo detection, apparatus and system |
CN107943449A (en) * | 2017-12-23 | 2018-04-20 | 河南智盈电子技术有限公司 | A kind of intelligent sound system based on human facial expression recognition |
CN108710788A (en) * | 2018-05-22 | 2018-10-26 | 上海众人网络安全技术有限公司 | A kind of safety certifying method, device, terminal and storage medium |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112200120A (en) * | 2020-10-23 | 2021-01-08 | 支付宝(杭州)信息技术有限公司 | Identity recognition method, living body recognition device and electronic equipment |
CN112380979A (en) * | 2020-11-12 | 2021-02-19 | 平安科技(深圳)有限公司 | Living body detection method, living body detection device, living body detection equipment and computer readable storage medium |
WO2021197369A1 (en) * | 2020-11-12 | 2021-10-07 | 平安科技(深圳)有限公司 | Liveness detection method and apparatus, electronic device, and computer readable storage medium |
CN112380979B (en) * | 2020-11-12 | 2024-05-07 | 平安科技(深圳)有限公司 | Living body detection method, living body detection device, living body detection equipment and computer readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109446981B (en) | Face living body detection and identity authentication method and device | |
CN107609383B (en) | 3D face identity authentication method and device | |
CN107748869B (en) | 3D face identity authentication method and device | |
US10275672B2 (en) | Method and apparatus for authenticating liveness face, and computer program product thereof | |
CN106599772B (en) | Living body verification method and device and identity authentication method and device | |
CN107633165B (en) | 3D face identity authentication method and device | |
US9652663B2 (en) | Using facial data for device authentication or subject identification | |
Galdi et al. | Multimodal authentication on smartphones: Combining iris and sensor recognition for a double check of user identity | |
TW201911130A (en) | Method and device for remake image recognition | |
CN106156578A (en) | Auth method and device | |
CN108197586A (en) | Recognition algorithms and device | |
CN105844206A (en) | Identity authentication method and identity authentication device | |
CN111738735B (en) | Image data processing method and device and related equipment | |
CN105868677A (en) | Live human face detection method and device | |
CN111414858B (en) | Face recognition method, target image determining device and electronic system | |
CN112733802B (en) | Image occlusion detection method and device, electronic equipment and storage medium | |
CN106709418B (en) | Face identification method and identification device based on scene photograph and certificate photo | |
Smith-Creasey et al. | Continuous face authentication scheme for mobile devices with tracking and liveness detection | |
CN112507889A (en) | Method and system for verifying certificate and certificate holder | |
CN110163094A (en) | Biopsy method, device, equipment and storage medium based on gesture motion | |
CN107622246A (en) | Face identification method and Related product | |
CN109886084A (en) | Face authentication method, electronic equipment and storage medium based on gyroscope | |
CN113642497A (en) | Method, server and equipment for preventing face cheating | |
CN106156739A (en) | A kind of certificate photo ear detection analyzed based on face mask and extracting method | |
CN106355066A (en) | Face authentication method and face authentication device |
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 |