CN106951866A - A kind of face authentication method and device - Google Patents
A kind of face authentication method and device Download PDFInfo
- Publication number
- CN106951866A CN106951866A CN201710170592.5A CN201710170592A CN106951866A CN 106951866 A CN106951866 A CN 106951866A CN 201710170592 A CN201710170592 A CN 201710170592A CN 106951866 A CN106951866 A CN 106951866A
- Authority
- CN
- China
- Prior art keywords
- user
- video data
- face
- certified
- facial image
- 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
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/30—Individual registration on entry or exit not involving the use of a pass
- G07C9/32—Individual registration on entry or exit not involving the use of a pass in combination with an identity check
- G07C9/37—Individual registration on entry or exit not involving the use of a pass in combination with an identity check using biometric data, e.g. fingerprints, iris scans or voice recognition
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention provides a kind of face authentication method and device, wherein, this method includes：The video data for the user to be certified that receiving terminal is sent；Whether the facial image of same people is only included in detection video data；When detecting only to include the facial image of same people in video data, according to video data, user to be certified is authenticated.The present invention carries out face authentication by video data to user to be certified, due to video data present be user face to be certified dynamic menu, therefore the face feature of the user to be certified included in video data is more detailed, and video data includes multiple image, situation about being influenceed when being authenticated by single image by factors such as light, shooting angle can be prevented effectively from, and can effectively solve traditional in vivo identification easily by technology it is counterfeit the problem of, substantially increase certification accuracy rate and success rate.
Description
Technical field
The present invention relates to internet communication and identity identification technical field, in particular to a kind of face authentication method
And device.
Background technology
In the system such as gate inhibition or welcome, it is necessary to user carry out identification, with user by authentication after be
User, which provides, releases the service such as gate inhibition.At present, face authentication is exactly a kind of common method of identifying user identity.
Currently, in the system such as gate inhibition or welcome, server storage have the human face photo that is uploaded during a large number of users registration and
Identity information.When a user uses gate inhibition or welcome's system, the human face photo of the user is shot by capture apparatus, by face
Photo upload is to server.Server is received after the human face photo, and the human face photo is calculated respectively and is stored with server local
Each human face photo between similarity, if there is similarity between the human face photo on server is more than predetermined threshold value
Human face photo, then the user authentication pass through, server send release gate inhibition instruct to door control terminal.If being not present on server
Similarity is more than the human face photo of predetermined threshold value, then the user authentication failure.
Existing face authentication method is authenticated by shooting the human face photo of user, but by light, shooting angle
Exist very very much not between the influence of the factors such as degree, the human face photo uploaded when the human face photo shot during certification and user's registration
Together, so as to cause the accuracy rate of face authentication very low.
The content of the invention
In view of this, the purpose of the embodiment of the present invention is to provide a kind of face authentication method and device, passes through video counts
Face feature according to the user to be certified for user to be certified include in face authentication, video data is more detailed, and regards
Frequency can be prevented effectively from when being authenticated by single image by the factor shadow such as light, shooting angle according to multiple image is included
Loud situation, and can effectively solve traditional in vivo identification easily by technology it is counterfeit the problem of, substantially increase certification accuracy rate
And success rate.
In a first aspect, the embodiments of the invention provide a kind of face authentication method, methods described includes：
The video data for the user to be certified that receiving terminal is sent；
Detect the facial image that same people whether is only included in the video data；
When detecting only to include the facial image of same people in the video data, according to the video data, to institute
User to be certified is stated to be authenticated.
With reference in a first aspect, the embodiments of the invention provide the possible implementation of the first of above-mentioned first aspect, its
In, it is described that the user to be certified is authenticated according to the video data, including：
According to the video data, the face feature file of the user to be certified is obtained；
The user to be certified is authenticated according to the face feature file.
With reference to the first possible implementation of first aspect, the embodiments of the invention provide the of above-mentioned first aspect
Two kinds of possible implementations, wherein, it is described according to the video data, obtain the face feature text of the user to be certified
Part, including：
Face sequence is intercepted from the video data；
The face characteristic of the user to be certified is extracted from the face sequence；
Dimension-reduction treatment is carried out to the face characteristic, the face feature file of the user to be certified is obtained.
With reference to the first possible implementation of first aspect, the embodiments of the invention provide the of above-mentioned first aspect
Three kinds of possible implementations, wherein, described to be authenticated according to the face feature file to the user to be certified, bag
Include：
The similarity between the face feature file and the face information of each registered users is calculated respectively；
Judge whether that similarity is more than the face information of the registered users of predetermined threshold value；
If it is, user to be certified described in certification is registered users, certification is sent by configured information to the end
End；If it is not, then user to be certified described in certification is non-registered users, authentification failure configured information is sent to the terminal.
With reference in a first aspect, the embodiments of the invention provide the possible implementation of the 4th of above-mentioned first aspect kind, its
In, the facial image of same people whether is only included in the detection video data, including：
Detected by the human face recognition model of training in advance and whether there is the figure comprising facial image in the video data
As frame；
If detecting there is the described image frame comprising facial image in the video data, described image frame bag is judged
The facial image contained whether be same people facial image.
Any of first to fourth kind of possible implementation with reference to first aspect or first aspect implementation,
The embodiments of the invention provide the possible implementation of the 5th of above-mentioned first aspect kind, wherein, what the receiving terminal was sent
Before the video data of user to be certified, also include：
The registration request that the terminal of user is sent is received, the registration request carries video data and subscriber identity information；
The video data and the subscriber identity information carried according to the registration request, is noted to the user
Volume.
With reference to the 5th kind of possible implementation of first aspect, the embodiments of the invention provide the of above-mentioned first aspect
Six kinds of possible implementations, wherein, the video data and the user identity carried according to the registration request
Information, is registered to the user, including：
The video data carried according to the registration request, obtains the face feature file of the user；
The face feature file of the user is defined as the face information of the user, the face information and institute is stored
State the corresponding relation of subscriber identity information.
Second aspect, the embodiments of the invention provide a kind of face authentication device, described device includes：
Receiver module, the video data of the user to be certified sent for receiving terminal；
Whether detection module, the facial image of same people is only included for detecting in the video data；
Authentication module, for detecting only to include the facial image of same people in the video data when the detection module
When, according to the video data, the user to be certified is authenticated.
With reference to second aspect, the embodiments of the invention provide the possible implementation of the first of above-mentioned second aspect, its
In, the authentication module includes：
Acquiring unit, for according to the video data, obtaining the face feature file of the user to be certified；
Authentication unit, for being authenticated according to the face feature file to the user to be certified.
With reference to the first possible implementation of second aspect, the embodiments of the invention provide the of above-mentioned second aspect
Two kinds of possible implementations, wherein, the acquiring unit includes：
Subelement is intercepted, for intercepting face sequence from the video data；
Extract subelement, the face characteristic for extracting the user to be certified from the face sequence；
Dimensionality reduction subelement, for carrying out dimension-reduction treatment to the face characteristic, the face for obtaining the user to be certified is special
Solicit articles part.
In method and device provided in an embodiment of the present invention, the video data for the user to be certified that receiving terminal is sent；
Whether the facial image of same people is only included in detection video data；When the face for detecting only to include same people in video data
During image, according to video data, user to be certified is authenticated.The present invention enters pedestrian by video data to user to be certified
Face certification, is the dynamic menu of user face to be certified due to what video data was presented, therefore waiting of being included in video data is recognized
The face feature for demonstrate,proving user is more detailed, and video data includes multiple image, can be prevented effectively from and be carried out by single image
Situation about being influenceed during certification by factors such as light, shooting angle, and can effectively solve traditional in vivo identification easily imitated by technology
The problem of emitting, substantially increases certification accuracy rate and success rate.
To enable the above objects, features and advantages of the present invention to become apparent, preferred embodiment cited below particularly, and coordinate
Appended accompanying drawing, is described in detail below.
Brief description of the drawings
Technical scheme in order to illustrate more clearly the embodiments of the present invention, below will be attached to what is used needed for embodiment
Figure is briefly described, it will be appreciated that the following drawings illustrate only certain embodiments of the present invention, therefore is not construed as pair
The restriction of scope, for those of ordinary skill in the art, on the premise of not paying creative work, can also be according to this
A little accompanying drawings obtain other related accompanying drawings.
Fig. 1 shows a kind of flow chart for face registration based on video data that the embodiment of the present invention 1 is provided；
Fig. 2 shows a kind of flow chart for face authentication method that the embodiment of the present invention 1 is provided；
Fig. 3 shows a kind of system architecture diagram for face authentication that the embodiment of the present invention 1 is provided；
Fig. 4 shows the system architecture diagram for another face authentication that the embodiment of the present invention 1 is provided；
Fig. 5 shows a kind of structural representation for face authentication device that the embodiment of the present invention 2 is provided；
Fig. 6 shows the structural representation for another face authentication device that the embodiment of the present invention 2 is provided.
Embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention
Middle accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is only
It is a part of embodiment of the invention, rather than whole embodiments.The present invention generally here described and illustrated in accompanying drawing is real
Applying the component of example can be arranged and be designed with a variety of configurations.Therefore, it is of the invention to what is provided in the accompanying drawings below
The detailed description of embodiment is not intended to limit the scope of claimed invention, but is merely representative of the selected reality of the present invention
Apply example.Based on embodiments of the invention, the institute that those skilled in the art are obtained on the premise of creative work is not made
There is other embodiment, belong to the scope of protection of the invention.
In view of existing face authentication method be authenticated by shooting the human face photo of user, but by light,
Exist very between the influence of the factors such as shooting angle, the human face photo uploaded when the human face photo shot during certification and user's registration
It is different, so as to cause the accuracy rate of face authentication very low.Based on this, the embodiments of the invention provide a kind of face authentication method
And device, it is described below by embodiment.
Embodiment 1
The embodiments of the invention provide a kind of face authentication method, treated and recognized by the corresponding video data of user to be certified
Card user is authenticated, due to including face figure in the facial image of multiframe user to be certified, and every two field picture in video data
The angle of picture may be different from, therefore video data can be comprehensively one in the positive face of user to be certified, left side of the face and right side face
Plant or multiple angles, thus it is very high by video data progress face authentication accuracy, it can be prevented effectively from by single image
Situation about being influenceed when being authenticated by factors such as light, shooting angle, and traditional in vivo identification can be effectively solved easily by skill
The problem of art is counterfeit.
In embodiments of the present invention, before the system such as gate inhibition or welcome is by video data progress face authentication, Yong Huxu
First register on the server.One section of video of the terminal takings oneself such as the mobile phone or panel computer that user passes through oneself in registration
Data, when shooting video data, user can rotate the head of oneself, so that in the video data shot comprising oneself just
Face, left side of the face and right side face, so that the video data can include the face feature of user in detail as far as possible.Afterwards user to
The terminal of oneself inputs the subscriber identity informations such as oneself name, sex, age, and clicks on the registration button shown in terminal.
When the terminal of user detects the register instruction of registration button triggering, registration request is sent to server, the registration
Request carries above-mentioned video data and subscriber identity information.In order to save the data traffic of user and ensure faster transmission speed
Degree, the video data of shooting can be the short-sighted frequency in several seconds, the small video of such as 3 seconds.
Server receives the registration request that the terminal of user is sent, the video data carried according to the registration request and user
Identity information, is registered to user.Specific registration process includes：The video data that server is carried according to registration request, is obtained
Take the face feature file at family；The face feature file of user is defined as the face information of user, storage face information with
The corresponding relation of subscriber identity information.
Server intercepts face sequence when obtaining the face feature file of user from video data；From the face sequence
The face characteristic of user is extracted in row；Dimension-reduction treatment is carried out to the face characteristic of extraction, the face feature file of user is obtained.
Wherein, face sequence is the multi-frame video image of the facial image comprising user in video data.Face characteristic is
The facial characteristics of user, such as shape of face, eyes, nose, face facial characteristics.Because in user's registration, server needs storage
The log-on message of user, and the face characteristic extracted is the characteristics of image of two dimension, data volume is big, and storage is needed in order to further reduce
Log-on message data volume, the embodiment of the present invention carries out dimension-reduction treatment to the two-dimentional face characteristic of extraction, by the people of two dimension
Face Feature Conversion is one-dimensional floating number string, and the face characteristic of two dimension is such as converted to the floating number of 256.The one-dimensional floating-point
Number string is the face feature file of user.
The face feature file of the user as the face information of the user, is stored the face information of the user by server
With the corresponding relation of subscriber identity information, that is, the registration operation to the user is completed, return succeeds in registration configured information to use
The terminal at family.For other each users, all registered in the manner described above, the face information of each user of server storage
With the corresponding relation of subscriber identity information.
Further, since some special circumstances are there may be when shooting video data, except bag in the video data such as shot
Also included outside facial image containing user and do not include facial image in other people facial image, or the video data shot.
So register flow path as shown in Figure 1, passes through the video data of the camera shooting 3 to 5 seconds of the terminal of user, the terminal of user
By the video data upload server of shooting, server detects in the video data whether include facial image, if do not included,
Then return and re-shoot terminal of the configured information to user.If detecting that video data includes facial image, further sentence
Whether disconnected video data only includes the facial image of same person, and configured information is re-shoot to user's if it is not, then returning
Terminal.If it is, server intercepts face sequence from video data, then completed according to above-mentioned registration process to user's
Face registration is operated.
In embodiments of the present invention, human face recognition model is trained beforehand through substantial amounts of machine learning, server passes through
The human face recognition model of training in advance judges in video data whether to include facial image, and by human face recognition model come
Judge whether the facial image for only including same person.
Identifying procedure as shown in Figure 2, user after server completes face registration, reuses door through the above way
During the system such as taboo or welcome, server carries out face authentication by following steps：
Step 101：The video data for the user to be certified that receiving terminal is sent.
In gate inhibition or welcome's system, it is equipped with imaging first-class shooting in the terminal such as door control terminal or welcome's terminal and sets
Standby, the picture in the region that terminal-pair capture apparatus is monitored is monitored in real time.When monitor a people enter terminal shooting
In the range of when, the shooting of several seconds is carried out to this people by capture apparatus, the video data of this people is obtained, such as this people is entered
The second beats of row 3 is taken the photograph, and obtains the video data of 3 seconds.This people into coverage is current user to be certified.Terminal taking
To after the video data of user to be certified, the video data is uploaded onto the server.It is to be certified that server receiving terminal is sent
The video data of user.
Step 102：Whether the facial image of same people is only included in detection video data.
Server detects to whether there is in video data by the human face recognition model of training in advance includes facial image
Picture frame；If detecting there is the picture frame comprising facial image in video data, the face that these picture frames are included is judged
Image whether be same people facial image.
When whether the facial image for judging that these picture frames are included is the facial image of same people, server is first determined whether
With the presence or absence of the picture frame of two or more facial images is included simultaneously in these picture frames, if it is, determining that this is regarded
Frequency includes many personal facial images in.If it is not, then determining whether the face that each frame is included in these picture frames
Image whether be same people facial image.Above-mentioned deterministic process is identified by the human face recognition model of training in advance
Judge.
In embodiments of the present invention, if judging, video data does not include facial image, or judges video data bag
Containing facial images more than two people or two people, although or judging in a two field picture of video data only comprising a people
Facial image, but the facial image included in multiple image is not the facial image of same person, judge the above this
During several situations, server, which is all returned, re-shoots configured information to terminal.
Only when server judges only to include the facial image of same people in video data, just as follows
103 operation to carry out face authentication to user to be certified.
Step 103：When detecting only to include the facial image of same people in video data, according to video data, treat
Certification user be authenticated.
When it is determined that only include the facial image of same people in the video data that terminal is uploaded, i.e., only including user's to be certified
During facial image, server obtains the face feature file of user to be certified according to the video data；According to face feature file
User to be certified is authenticated.
When obtaining the face feature file of user to be certified, server intercepts people from the video data of user to be certified
Face sequence；The face characteristic of user to be certified is extracted from the face sequence of interception；The face characteristic of extraction is carried out at dimensionality reduction
Reason, obtains the face feature file of user to be certified.The face feature file is one-dimensional floating number string.
After the face feature file for obtaining user to be certified, server obtains the face letter of the registered users stored
Breath, calculates the similarity between face feature file and the face information of each registered users respectively；Judge whether phase
Face information like degree more than the registered users of predetermined threshold value；If it is, certification user to be certified is registered users, hair
Send certification by configured information to terminal, after terminal receives certification by configured information, confirm the user to be certified to have noted
Volume user, gate inhibition is released for the user to be certified.If it is not, then certification user to be certified is non-registered users, sends certification and lose
Configured information is lost to terminal, terminal is received after authentification failure configured information, it is non-registered users to confirm the user to be certified, no
Gate inhibition is released for the user to be certified.
Can be system architecture as shown in Figure 3 using the system of face authentication method provided in an embodiment of the present invention, should
System includes terminal, server and the face authentication terminal of user, and face authentication terminal can be door control terminal or welcome's terminal
Deng.The terminal of user submits video data to be registered to server.Face authentication terminal is regarded the user's to be certified of shooting
Frequency is authenticated according to upload server.In the embodiment of the present invention, as shown in figure 4, server can also be divided into face knowledge
Other server and application server, recognition of face server are responsible for registering user, store the log-on message of user.When should
With server it needs to be determined that when whether user to be certified is registered users, application server calls recognition of face server to treat
Certification user carries out face authentication.
Environment is detected in real time by the capture apparatus of terminal, once find that face can shoot video data immediately
And upload, substantially increase the efficiency of face authentication.And do not need the user to be certified must just face due to shooting video data
The camera lens of capture apparatus is directed at, if user to be certified is to carry out the shooting of video data into coverage, therefore can be from
Larger distance is shot, so that the detecting distance of face authentication extends to 3-5 meters or even farther distance.Separately
In the systems such as outer gate inhibition or welcome in addition to it can carry out face authentication, also compatible RFID (Radio Frequency
Identification, REID) certification, identity card swipe the card a variety of authentication modes such as certification.And application is by regarding
Frequency can compatible private clound and public cloud according to the system for carrying out face authentication, that is to say, that can both dock privately owned data
Storehouse, can also dock the public database of big data quantity.
Face registration and face authentication are carried out using video data is shot, system can be believed the face included in video data
Breath carries out automatic detection, and completes registration and certification.Because video data includes the multiple image of face, presentation is face
The dynamic menu in portion, carrying out face authentication by video data has very high accuracy.
In embodiments of the present invention, the video data for the user to be certified that receiving terminal is sent；It is in detection video data
The no facial image for only including same people；When detecting only to include the facial image of same people in video data, according to video
Data, are authenticated to user to be certified.The present invention carries out face authentication by video data to user to be certified, due to video
What data were presented is the dynamic menu of user face to be certified, therefore the face feature of the user to be certified included in video data
It is more detailed, and video data includes multiple image, can be prevented effectively from when being authenticated by single image by light, shooting
The factors such as angle influence situation, and can effectively solve traditional in vivo identification easily by technology it is counterfeit the problem of, greatly improve
Certification accuracy rate and success rate.
Embodiment 2
Referring to Fig. 5, the embodiments of the invention provide a kind of face authentication device, the device is used to perform above-described embodiment 1
The face authentication method provided.The device is specifically included：
Receiver module 201, the video data of the user to be certified sent for receiving terminal；
Whether detection module 202, the facial image of same people is only included for detecting in video data；
Authentication module 203, for detecting only to include the facial image of same people in video data when detection module 202
When, according to video data, user to be certified is authenticated.
As shown in fig. 6, above-mentioned authentication module 203 includes：
Acquiring unit 2031, for according to video data, obtaining the face feature file of user to be certified；
Authentication unit 2032, for being authenticated according to face feature file to user to be certified.
Above-mentioned acquiring unit 2031 includes：Subelement is intercepted, for intercepting face sequence from video data；Extract son single
Member, the face characteristic for extracting user to be certified from face sequence；Dimensionality reduction subelement, for carrying out dimensionality reduction to face characteristic
Processing, obtains the face feature file of user to be certified.
Above-mentioned authentication unit 2032 includes：Computation subunit, for calculate respectively face feature file with it is each registered
Similarity between the face information of user；Judgment sub-unit, for judging whether that similarity has been more than predetermined threshold value
The face information of registered user；If it is, certification user to be certified be registered users, send certification by configured information to
Terminal；If it is not, then certification user to be certified is non-registered users, authentification failure configured information is sent to terminal.
In embodiments of the present invention, detection module 202 includes：
Detection unit, face is included for whether there is in the human face recognition model detection video data by training in advance
The picture frame of image；
Judging unit, if detecting there is the picture frame comprising facial image in video data for above-mentioned detection unit,
Then judge facial image that picture frame includes whether be same people facial image.
As shown in fig. 6, the device also includes：
Registering modules 204, for receiving the registration request that the terminal of user is sent, registration request carries video data and use
Family identity information；The video data and subscriber identity information carried according to registration request, is registered to user.
Above-mentioned Registering modules 204, for the video data carried according to registration request, obtain the face feature text of user
Part；The face feature file of user is defined as the face information of user, storage face information is corresponding with subscriber identity information
Relation.
In embodiments of the present invention, the video data for the user to be certified that receiving terminal is sent；It is in detection video data
The no facial image for only including same people；When detecting only to include the facial image of same people in video data, according to video
Data, are authenticated to user to be certified.The present invention carries out face authentication by video data to user to be certified, due to video
What data were presented is the dynamic menu of user face to be certified, therefore the face feature of the user to be certified included in video data
It is more detailed, and video data includes multiple image, can be prevented effectively from when being authenticated by single image by light, shooting
The factors such as angle influence situation, and can effectively solve traditional in vivo identification easily by technology it is counterfeit the problem of, greatly improve
Certification accuracy rate and success rate.
The face authentication device that the embodiment of the present invention is provided for the specific hardware in equipment or can be installed on equipment
On software or firmware etc..The technique effect of the device that the embodiment of the present invention is provided, its realization principle and generation and foregoing side
Method embodiment is identical, to briefly describe, and device embodiment part does not refer to part, refers in corresponding in preceding method embodiment
Hold.It is apparent to those skilled in the art that, for convenience and simplicity of description, device and unit described above
Specific work process, may be referred to the corresponding process in above method embodiment, will not be repeated here.
, can be by others side in embodiment provided by the present invention, it should be understood that disclosed apparatus and method
Formula is realized.Device embodiment described above is only schematical, for example, the division of the unit, only one kind are patrolled
Collect function to divide, there can be other dividing mode when actually realizing, but for example, multiple units or component can combine or can
To be integrated into another system, or some features can be ignored, or not perform.It is another, it is shown or discussed each other
Coupling or direct-coupling or communication connection can be the INDIRECT COUPLING or communication link of device or unit by some communication interfaces
Connect, can be electrical, machinery or other forms.
The unit illustrated as separating component can be or may not be it is physically separate, it is aobvious as unit
The part shown can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On NE.Some or all of unit therein can be selected to realize the mesh of this embodiment scheme according to the actual needs
's.
In addition, each functional unit in the embodiment that the present invention is provided can be integrated in a processing unit, also may be used
To be that unit is individually physically present, can also two or more units it is integrated in a unit.
If the function is realized using in the form of SFU software functional unit and is used as independent production marketing or in use, can be with
It is stored in a computer read/write memory medium.Understood based on such, technical scheme is substantially in other words
The part contributed to prior art or the part of the technical scheme can be embodied in the form of software product, the meter
Calculation machine software product is stored in a storage medium, including some instructions are make it that a computer equipment (can be individual
People's computer, server, or network equipment etc.) perform all or part of step of each of the invention embodiment methods described.
And foregoing storage medium includes：USB flash disk, mobile hard disk, read-only storage (ROM, Read-Only Memory), arbitrary access are deposited
Reservoir (RAM, Random Access Memory), magnetic disc or CD etc. are various can be with the medium of store program codes.
It should be noted that：Similar label and letter represents similar terms in following accompanying drawing, therefore, once a certain Xiang Yi
It is defined in individual accompanying drawing, then it further need not be defined and explained in subsequent accompanying drawing, in addition, term " the
One ", " second ", " the 3rd " etc. are only used for distinguishing description, and it is not intended that indicating or implying relative importance.
Finally it should be noted that：Embodiment described above, is only the embodiment of the present invention, to illustrate the present invention
Technical scheme, rather than its limitations, protection scope of the present invention is not limited thereto, although with reference to the foregoing embodiments to this hair
It is bright to be described in detail, it will be understood by those within the art that：Any one skilled in the art
The invention discloses technical scope in, it can still modify to the technical scheme described in previous embodiment or can be light
Change is readily conceivable that, or equivalent is carried out to which part technical characteristic；And these modifications, change or replacement, do not make
The essence of appropriate technical solution departs from the spirit and scope of embodiment of the present invention technical scheme.The protection in the present invention should all be covered
Within the scope of.Therefore, protection scope of the present invention should be based on the protection scope of the described claims.
Claims (10)
1. a kind of face authentication method, it is characterised in that methods described includes：
The video data for the user to be certified that receiving terminal is sent；
Detect the facial image that same people whether is only included in the video data；
When detecting only to include the facial image of same people in the video data, according to the video data, treated to described
Certification user be authenticated.
2. according to the method described in claim 1, it is characterised in that described according to the video data, to the use to be certified
Family is authenticated, including：
According to the video data, the face feature file of the user to be certified is obtained；
The user to be certified is authenticated according to the face feature file.
3. method according to claim 2, it is characterised in that described according to the video data, is obtained described to be certified
The face feature file of user, including：
Face sequence is intercepted from the video data；
The face characteristic of the user to be certified is extracted from the face sequence；
Dimension-reduction treatment is carried out to the face characteristic, the face feature file of the user to be certified is obtained.
4. method according to claim 2, it is characterised in that it is described according to the face feature file to described to be certified
User is authenticated, including：
The similarity between the face feature file and the face information of each registered users is calculated respectively；
Judge whether that similarity is more than the face information of the registered users of predetermined threshold value；
If it is, user to be certified described in certification is registered users, certification is sent by configured information to the terminal；Such as
Really no, then user to be certified described in certification is non-registered users, sends authentification failure configured information to the terminal.
5. according to the method described in claim 1, it is characterised in that whether only comprising same in the detection video data
The facial image of people, including：
Detected by the human face recognition model of training in advance and whether there is the picture frame comprising facial image in the video data；
If detecting there is the described image frame comprising facial image in the video data, judge what described image frame was included
Facial image whether be same people facial image.
6. the method according to claim any one of 1-5, it is characterised in that the user to be certified that the receiving terminal is sent
Video data before, also include：
The registration request that the terminal of user is sent is received, the registration request carries video data and subscriber identity information；
The video data and the subscriber identity information carried according to the registration request, is registered to the user.
7. method according to claim 6, it is characterised in that the video counts carried according to the registration request
According to the subscriber identity information, the user is registered, including：
The video data carried according to the registration request, obtains the face feature file of the user；
The face feature file of the user is defined as the face information of the user, the face information is stored and is used with described
The corresponding relation of family identity information.
8. a kind of face authentication device, it is characterised in that described device includes：
Receiver module, the video data of the user to be certified sent for receiving terminal；
Whether detection module, the facial image of same people is only included for detecting in the video data；
Authentication module, for when the detection module detects in the video data only to include the facial image of same people,
According to the video data, the user to be certified is authenticated.
9. device according to claim 8, it is characterised in that the authentication module includes：
Acquiring unit, for according to the video data, obtaining the face feature file of the user to be certified；
Authentication unit, for being authenticated according to the face feature file to the user to be certified.
10. device according to claim 9, it is characterised in that the acquiring unit includes：
Subelement is intercepted, for intercepting face sequence from the video data；
Extract subelement, the face characteristic for extracting the user to be certified from the face sequence；
Dimensionality reduction subelement, for carrying out dimension-reduction treatment to the face characteristic, obtains the face feature text of the user to be certified
Part.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710170592.5A CN106951866A (en) | 2017-03-21 | 2017-03-21 | A kind of face authentication method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710170592.5A CN106951866A (en) | 2017-03-21 | 2017-03-21 | A kind of face authentication method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106951866A true CN106951866A (en) | 2017-07-14 |
Family
ID=59472244
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710170592.5A Pending CN106951866A (en) | 2017-03-21 | 2017-03-21 | A kind of face authentication method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106951866A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107563360A (en) * | 2017-09-30 | 2018-01-09 | 百度在线网络技术（北京）有限公司 | Information acquisition method and device |
| CN108446688A (en) * | 2018-05-28 | 2018-08-24 | 北京达佳互联信息技术有限公司 | Facial image Sexual discriminating method, apparatus, computer equipment and storage medium |
| CN108960841A (en) * | 2018-07-16 | 2018-12-07 | 阿里巴巴集团控股有限公司 | Method of payment, apparatus and system |
| CN109635021A (en) * | 2018-10-30 | 2019-04-16 | 平安科技（深圳）有限公司 | A kind of data information input method, device and equipment based on human testing |
| CN109887186A (en) * | 2019-02-28 | 2019-06-14 | 深圳市沐腾科技有限公司 | A kind of locker opens cabinet method, locker and storage cabinet system |
| WO2019127365A1 (en) * | 2017-12-29 | 2019-07-04 | 深圳前海达闼云端智能科技有限公司 | Face living body detection method, electronic device and computer program product |
| CN110008673A (en) * | 2019-03-06 | 2019-07-12 | 阿里巴巴集团控股有限公司 | A kind of identification authentication method and apparatus based on recognition of face |
| CN110249339A (en) * | 2019-04-24 | 2019-09-17 | 深圳市汇顶科技股份有限公司 | A kind of face registration method, face registration device, server and can storage medium |
| CN110929555A (en) * | 2018-09-19 | 2020-03-27 | 和硕联合科技股份有限公司 | Face recognition method and electronic device using same |
| CN111027450A (en) * | 2019-12-04 | 2020-04-17 | 深圳市新国都金服技术有限公司 | Bank card information identification method and device, computer equipment and storage medium |
| CN113627387A (en) * | 2021-08-30 | 2021-11-09 | 平安国际融资租赁有限公司 | Parallel identity authentication method, device, equipment and medium based on face recognition |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102360421A (en) * | 2011-10-19 | 2012-02-22 | 苏州大学 | Face identification method and system based on video streaming |
| CN105095868A (en) * | 2015-07-23 | 2015-11-25 | 小米科技有限责任公司 | Picture matching method and apparatus |
| CN105787440A (en) * | 2015-11-10 | 2016-07-20 | 深圳市商汤科技有限公司 | Security protection management method and system based on face features and gait features |
| CN106228628A (en) * | 2016-07-15 | 2016-12-14 | 腾讯科技（深圳）有限公司 | System, the method and apparatus of registering based on recognition of face |
| CN106303447A (en) * | 2016-08-29 | 2017-01-04 | 深圳泰首智能技术有限公司 | A kind of monitoring method and device |
-
2017
- 2017-03-21 CN CN201710170592.5A patent/CN106951866A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102360421A (en) * | 2011-10-19 | 2012-02-22 | 苏州大学 | Face identification method and system based on video streaming |
| CN105095868A (en) * | 2015-07-23 | 2015-11-25 | 小米科技有限责任公司 | Picture matching method and apparatus |
| CN105787440A (en) * | 2015-11-10 | 2016-07-20 | 深圳市商汤科技有限公司 | Security protection management method and system based on face features and gait features |
| CN106228628A (en) * | 2016-07-15 | 2016-12-14 | 腾讯科技（深圳）有限公司 | System, the method and apparatus of registering based on recognition of face |
| CN106303447A (en) * | 2016-08-29 | 2017-01-04 | 深圳泰首智能技术有限公司 | A kind of monitoring method and device |
Non-Patent Citations (1)
| Title |
|---|
| 章毓晋: "《图像工程技术选编》", 31 July 2016 * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107563360B (en) * | 2017-09-30 | 2021-05-07 | 百度在线网络技术（北京）有限公司 | Information acquisition method and device |
| CN107563360A (en) * | 2017-09-30 | 2018-01-09 | 百度在线网络技术（北京）有限公司 | Information acquisition method and device |
| WO2019127365A1 (en) * | 2017-12-29 | 2019-07-04 | 深圳前海达闼云端智能科技有限公司 | Face living body detection method, electronic device and computer program product |
| CN108446688A (en) * | 2018-05-28 | 2018-08-24 | 北京达佳互联信息技术有限公司 | Facial image Sexual discriminating method, apparatus, computer equipment and storage medium |
| CN108446688B (en) * | 2018-05-28 | 2020-01-07 | 北京达佳互联信息技术有限公司 | Face image gender judgment method and device, computer equipment and storage medium |
| US10769417B2 (en) | 2018-07-16 | 2020-09-08 | Alibaba Group Holding Limited | Payment method, apparatus, and system |
| US10747990B2 (en) | 2018-07-16 | 2020-08-18 | Alibaba Group Holding Limited | Payment method, apparatus, and system |
| CN108960841A (en) * | 2018-07-16 | 2018-12-07 | 阿里巴巴集团控股有限公司 | Method of payment, apparatus and system |
| CN110929555A (en) * | 2018-09-19 | 2020-03-27 | 和硕联合科技股份有限公司 | Face recognition method and electronic device using same |
| CN109635021A (en) * | 2018-10-30 | 2019-04-16 | 平安科技（深圳）有限公司 | A kind of data information input method, device and equipment based on human testing |
| CN109887186A (en) * | 2019-02-28 | 2019-06-14 | 深圳市沐腾科技有限公司 | A kind of locker opens cabinet method, locker and storage cabinet system |
| CN110008673A (en) * | 2019-03-06 | 2019-07-12 | 阿里巴巴集团控股有限公司 | A kind of identification authentication method and apparatus based on recognition of face |
| CN110008673B (en) * | 2019-03-06 | 2022-02-18 | 创新先进技术有限公司 | Identity authentication method and device based on face recognition |
| CN110249339A (en) * | 2019-04-24 | 2019-09-17 | 深圳市汇顶科技股份有限公司 | A kind of face registration method, face registration device, server and can storage medium |
| WO2020215229A1 (en) * | 2019-04-24 | 2020-10-29 | 深圳市汇顶科技股份有限公司 | Face registration method, face registration device, server and storage medium |
| CN111027450A (en) * | 2019-12-04 | 2020-04-17 | 深圳市新国都金服技术有限公司 | Bank card information identification method and device, computer equipment and storage medium |
| CN113627387A (en) * | 2021-08-30 | 2021-11-09 | 平安国际融资租赁有限公司 | Parallel identity authentication method, device, equipment and medium based on face recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106951866A (en) | A kind of face authentication method and device | |
| US11354901B2 (en) | Activity recognition method and system | |
| US11074436B1 (en) | Method and apparatus for face recognition | |
| CN107590439A (en) | Target person identification method for tracing and device based on monitor video | |
| CN108229335A (en) | It is associated with face identification method and device, electronic equipment, storage medium, program | |
| CN106803289A (en) | A kind of false proof method and system of registering of intelligent mobile | |
| CN107066983A (en) | A kind of auth method and device | |
| CN108269333A (en) | Face identification method, application server and computer readable storage medium | |
| CN106228628A (en) | System, the method and apparatus of registering based on recognition of face | |
| CN107093066A (en) | Service implementation method and device | |
| CN106372606A (en) | Target object information generation method and unit identification method and unit and system | |
| CN105160318A (en) | Facial expression based lie detection method and system | |
| US20210158036A1 (en) | Databases, data structures, and data processing systems for counterfeit physical document detection | |
| CN108108711B (en) | Face control method, electronic device and storage medium | |
| CN109858337A (en) | A kind of face identification method based on pupil information, system and equipment | |
| CN108921874A (en) | Human body tracking processing method, apparatus and system | |
| WO2022062379A1 (en) | Image detection method and related apparatus, device, storage medium, and computer program | |
| CN106952371A (en) | A kind of face roaming authentication method and system | |
| CN106295672A (en) | A kind of face identification method and device | |
| CN109325413A (en) | A kind of face identification method, device and terminal | |
| CN110135262A (en) | The anti-peeping processing method of sensitive data, device, equipment and storage medium | |
| CN108734067A (en) | A kind of authentication method, system and camera that the testimony of a witness compares | |
| CN109766785A (en) | A kind of biopsy method and device of face | |
| US11503110B2 (en) | Method for presenting schedule reminder information, terminal device, and cloud server | |
| CN108734106A (en) | Quick sudden and violent probably video frequency identifying method based on comparison |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170714 |
|
| RJ01 | Rejection of invention patent application after publication |