CN107679493A - Face identification method and device - Google Patents
Face identification method and device Download PDFInfo
- Publication number
- CN107679493A CN107679493A CN201710918492.6A CN201710918492A CN107679493A CN 107679493 A CN107679493 A CN 107679493A CN 201710918492 A CN201710918492 A CN 201710918492A CN 107679493 A CN107679493 A CN 107679493A
- Authority
- CN
- China
- Prior art keywords
- user
- registered images
- image
- authentication
- face
- 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
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Collating Specific Patterns (AREA)
Abstract
This application discloses face identification method and device.One embodiment of this method includes:The image of the user of pending authentication is gathered, and determines the maximum registered images of the similarity of the face object included in multiple registered images and the face object in the image of the user collected collected;Judge whether the registered images determined are initial registration image in registered images set belonging to the registered images determined, obtain judged result, and the verification mode according to corresponding to judged result determines whether user passes through authentication.Realize and consider the influence that the face feature of user changes to recognition result with the time, avoid the feature of the face for the user for not registering with the image of user in the face identification system such as face recent with the user for the image for having registered with user characteristic similarity is maximum and similarity is more than threshold value and by the situation of authentication, lift the accuracy rate of recognition of face.
Description
Technical field
The application is related to artificial intelligence field, and in particular to field of face identification, more particularly to face identification method and dress
Put.
Background technology
Face recognition technology is the artificial intelligence technology verified based on the face feature of user to the identity of user.Mesh
Before, the mode of generally use is:The image of the user of pending authentication is gathered, finds out what is included in face identification system
Face object similarity highest registered images in the image of the user of face object and the pending authentication collected,
When highest similarity is more than similarity threshold, then pass through the authentication of the user of pending authentication.
However, because aforesaid way does not consider the influence that the feature of the face of user changes with time to recognition result,
Image of the user for the image for causing to occur not registering with user in face identification system such as with having registered with user
The characteristic similarity of the recent face of user is maximum and similarity is more than threshold value by the situation of authentication, causes face
The accuracy rate of identification is relatively low.
Invention information
This application provides a kind of face identification method and device, for solving technology existing for above-mentioned background section
Problem.
In a first aspect, this application provides face identification method, this method includes:Gather the user of pending authentication
Image, and determine the face pair in the face object included in multiple registered images and the image of the user collected
The maximum registered images of the similarity of elephant;Judge whether the registered images determined are registered images belonging to the registered images
Initial registration image in set, obtains judged result, and whether verification mode determines user according to corresponding to judged result
Pass through authentication.
Second aspect, this application provides face identification device, the device includes:Processing unit, it is configured to collection and treats
The image of the user of authentication is carried out, and determines the face object included in multiple registered images and the user collected
The maximum registered images of the similarity of face object in image;Authentication unit, it is configured to judge the registered images determined
Whether it is initial registration image in registered images set belonging to registered images, obtains judged result, and according to judging to tie
Verification mode corresponding to fruit determines whether user passes through authentication.
The face identification method and device that the application provides, the image of the user by gathering pending authentication, with
And the face object included in the multiple registered images of determination is similar to the face object in the image of the user collected
Spend maximum registered images;Judge whether the registered images determined are in registered images set belonging to the registered images
Initial registration image, judged result is obtained, and the verification mode according to corresponding to judged result determines whether user passes through identity
Checking.Realize and consider the influence that the face feature of user changes to recognition result with the time, avoid and do not exist such as
The user of the feature that the face of the user of the image of user is registered with face identification system and the image for having registered with user
The characteristic similarity of recent face is maximum and similarity is more than threshold value by the situation of authentication, lifts recognition of face
Accuracy rate.
Brief description of the drawings
By reading the detailed description made to non-limiting example made with reference to the following drawings, the application's is other
Feature, objects and advantages will become more apparent upon:
Fig. 1 shows the exemplary system architecture that can apply the face identification method of the application;
Fig. 2 shows the flow chart of one embodiment of the face identification method according to the application;
Fig. 3 shows the structural representation of one embodiment of the face identification device according to the application;
Fig. 4 shows the hardware architecture diagram suitable for being used for the electronic equipment for realizing the embodiment of the present application.
Embodiment
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining related invention, rather than the restriction to the invention.It also should be noted that in order to
Be easy to describe, illustrate only in accompanying drawing to about the related part of invention.
It should be noted that in the case where not conflicting, the feature in embodiment and embodiment in the application can phase
Mutually combination.Describe the application in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1 is refer to, it illustrates the exemplary system architecture for the face identification method that can apply the application.
As shown in figure 1, system architecture can include gate 101, terminal 102, server 103.Gate 101 can have been run
Face identification system, user can using terminal 102 before authentication is carried out to user using gate 101 first by user
The certificate photo of image such as user upload onto the server 103, then the image of user is sent to gate 101 by server 103,
Registered in advance in face identification system on gate 101 is operated in.
Fig. 2 is refer to, it illustrates the flow of one embodiment of the face identification method according to the application.Need to illustrate
, face identification method that the embodiment of the present application is provided can run equipment (such as the lock in Fig. 1 of face identification system
Machine 101) perform, specifically, it can be performed by face identification system.This method comprises the following steps:
Step 201, the image of the user of pending authentication is gathered, and determines corresponding phase in multiple registered images
Like the registered images that degree is maximum.
In the present embodiment, it is any user can be referred to as by face identification system progress authentication per capita.
The face of user in the picture can be referred to as face object corresponding to the face of user.For the face object in image
Speech, when face object corresponding to the face in an image only comprising a user, then the image can be referred to as user's
Image.For example, the image of user can be the certificate photo for only including face object corresponding to the face of a user.
In the present embodiment, the identity of user can be verified by face identification system.For example, when user reaches
, it is necessary to which gate could be passed through by carrying out authentication to user by face identification system when running the gate of face identification system.
The user can be taken pictures first, collect the image of the user, the face pair of the user is included in the image of the user
The face object answered.
In the present embodiment, registered images can refer to before the image of user of pending authentication is gathered, in advance
The image of the user first registered in face identification system.The image of one user carries out registration in face identification system can
To be added to equivalent to by registered images in a registered images set.Note of the image of one user in face identification system
The volume time can be that the image of a user is added to the time in a registered images set.One user passes through body each time
During part checking, the image of the user collected during authentication can be added in a registered images set.
In the present embodiment, in face identification system, face identification system can establish a user and a registration
The corresponding relation of image collection.Each registered images in registered images set corresponding to one user belong to the user.
Each registered images set corresponds to the mark of a user respectively.
In the present embodiment, can be by hour of log-on in registered images set corresponding to a user corresponding to the user
Earliest registered images are referred to as initial registration image in the hour of log-on of all registered images in registered images set.
The registered images as initial registration image in registered images set corresponding to one user can be to this
User carries out the image for belonging to the user registered before authentication in face identification system first.
For example, before the gate of operation face identification system carries out authentication to user first, can be by the user
Terminal the certificate photo of the image of the user such as user is sent to server, then the image of the user is sent out by server
Deliver to gate.The face identification system operated on gate can receive the image of the user, create and noted corresponding to the user
Volume image collection, registered using the image of the user received as corresponding to initial registration image is added to the user of establishment
In image collection, so as to complete registration of the initial registration image in face identification system.
This in addition to initial registration image in registered images set corresponding to one user belongs to the note of the user
Volume image can be when passing through authentication each time in history verification process, to be added into registered images corresponding to the user
The image of the user collected in history verification process in set.
In the present embodiment, multiple registered images can include:Authentication is being carried out to a user, this is being collected and treats
Before the image for carrying out the user of authentication, the category in the image of all users registered in advance in face identification system
The image and initial registration image of the user of newest registration in a registered images set.
In other words, authentication is being carried out to user, collect the pending authentication user image it
The image of each user in the image of preceding all users registered in advance in face identification system is each affiliated
Registered images set in.It is maximum with the similarity of the face object in the image of the user of pending authentication searching
Registered images when, can be from the image and initial registration image of the user of the newest registration in each registered images set
Find out the maximum note of the similarity of the face object in the image of the user of the face object and pending authentication included
Volume image.
In the present embodiment, face object and registered images in the image of the user of the pending authentication collected
In face object similarity can refer to pending authentication user image in face object feature and note
The similarity of the feature of face object in volume image.The feature of face object can use facial feature points to represent.
In the face object and a registered images in calculating the image of user of the pending authentication collected
Face object similarity when, the face pair in the image for the user that the pending authentication collected can be generated respectively
Characteristic point corresponding to the facial feature points of face object in characteristic point vector sum registered images corresponding to the facial feature points of elephant
Vector, it is special corresponding to the facial feature points of the face object in the image for the user for calculating the pending authentication collected
The cosine similarity of characteristic point vector corresponding to the facial feature points of face object in sign point one registered images of vector sum, will
The cosine similarity is as the face in the face object in the image of the user of pending authentication and a registered images
The similarity of object.
Step 202, whether it is initial registration image in registered images set according to the registered images determined, using phase
The verification mode answered determines whether user passes through authentication.
In the present embodiment, in the face object that determines to include in multiple registered images by step 201 and collect
After the registered images of face object similarity maximum in the image of the user of pending authentication, it can be schemed according to registration
As the subordinate relation with registered images set, the registered images set belonging to the registered images that this is determined is found out.Then, may be used
To judge whether the registered images determined are initial registration in registered images set belonging to the registered images determined
Image.
In the present embodiment, verification mode different corresponding to different judged results.In other words, when the registration determined
When image is the initial registration image in the registered images set belonging to the registered images that this is determined or when the registration determined
When image is not the initial registration image in the registered images set belonging to the registered images that this is determined, using different checkings
Mode is verified to the identity of the user of pending authentication.
In the present embodiment, when carrying out authentication to user, the registration determined from multiple registered images
Image be comprising face object it is similar to the face object in the image of the user of the pending authentication collected
Spend maximum registered images.The registered images determined from multiple registered images and the pending authentication that collects
The similarity of face object in the image of user can be referred to as similarity maximum corresponding to the registered images that this is determined.
In the present embodiment, when the registered images determined from multiple registered images are not the registered images that this is determined
During initial registration image in affiliated registered images set, verification mode can be:It will be determined from multiple registered images
Registered images belonging to registered images set in initial registration image in face object and pending authentication use
Maximum phase corresponding to the similarity of face object in the image at family and the registered images determined from multiple registered images
Like degree compared with same similarity threshold, the initial registration in the registered images set belonging to the registered images determined
The similarity of face object in the image of the user of face object and pending authentication in image and the note determined
When maximum similarity is all higher than same similarity threshold corresponding to volume image, the use to pending authentication can be passed through
The authentication at family, you can so that the identification of the user of the pending authentication to be determined as from multiple registered images
Registered images belonging to user, otherwise not by treat carry out authentication user authentication.
Initial registration in the registered images set belonging to the registered images that the registered images determined are determined for this
During image, verification mode can be:Only by similarity maximum corresponding to the registered images determined and above-mentioned same similarity
Threshold value compares, then can be with when similarity maximum corresponding to the registered images determined is more than above-mentioned same similarity threshold
Pass through the authentication of the user to pending authentication.Otherwise do not tested by treating the identity for the user for carrying out authentication
Card.
In some optional implementations of the present embodiment, when the registered images determined are not the notes belonging to registered images
Volume image collection in initial registration image when, verification mode can be:The note belonging to the registered images determined can be calculated
The face object in initial registration image in volume image collection and the face pair in the image of the user of pending authentication
The similarity of elephant, the similarity can be referred to as initial registration image similarity.It is then possible to judge whether that satisfaction passes through bar
Part:Maximum similarity corresponding to the registered images that initial registration image similarity is more than the first similarity threshold and determined
More than the second similarity threshold, when meeting to pass through condition, determine that the user of pending authentication passes through authentication;When not
When satisfaction passes through condition, determine that the user of pending authentication does not pass through authentication.First similarity threshold can be less than
Second similarity threshold.
Initial registration figure in the registered images set that the registered images determined are belonging to the registered images determined
During picture, verification mode can be:Whether maximum similarity is more than the first similarity corresponding to the registered images for judging to determine
Threshold value.When similarity maximum corresponding to the registered images determined is more than the first similarity threshold, it may be determined that pending
The user of authentication passes through authentication.When similarity maximum corresponding to the registered images determined is less than the first similarity
During threshold value, determine that the user of pending authentication does not pass through authentication.
For example, the user of pending authentication is user A, it is assumed that comprising just in registered images set corresponding to user A
The user A of face object corresponding to beginning registered images and the face comprising user A subsequently registered in face identification system
Image.Initial registration image in registered images set corresponding to user A for user A utilize first face identification system to
Family A carries out the user A registered before authentication in face identification system image, i.e., utilizes face identification system pair first
Before user A carries out authentication, the image such as user A's for the user A being added in registered images set corresponding to user A
Certificate photo.The hour of log-on of initial registration image in registered images set corresponding to user A is in registered images corresponding to user A
In the hour of log-on of all registered images in set earliest.
Reach gate in user A, operate in after the image that face identification system on gate collects user A, from multiple
The registered images determined in registered images are the registered images in registered images set corresponding to user A.
When the image for the user A that the registered images determined are the newest registration in registered images set corresponding to user A
When, it is determined that the initial note in registered images set corresponding to the user A belonging to the image that the registered images gone out are not to determine out
Volume image, at this time, it may be necessary to meet the face of the user A in the initial registration image in registered images set corresponding to user A simultaneously
The similarity of the face object corresponding with the face of the user A in the user A collected image of face object corresponding to portion is big
User A in the user A of newest registration in registered images set corresponding to the first similarity threshold and user A image
Face corresponding to face object face object corresponding with the face of the user A in the user A collected image it is similar
When degree is more than the second similarity threshold, the authentication to user A could be passed through.
In other words, the time of the user A collected image is that can be used as current time, the user A used figure
As the user A image that uses of time in user A face corresponding to the feature of face object can represent current when
Between user A face feature.The newest user A registered in face identification system before user A image is collected
The feature of face object is newest in face identification system before can representing current time corresponding to the face of user A in image
The feature of the hour of log-on user A of the user A of middle registration image face.It is first in registered images set corresponding to user A
The feature of face object in beginning registered images can be expressed as the face of the time user A apart from current time certain time length
Feature.
Need to meet that the feature of current time user A face is used with the time apart from current time certain time length at the same time
The similarity of the feature of family A face be more than the feature of the first similarity threshold and current time user A face with it is newest
The similarity of the feature of the hour of log-on user A of the user A registered in face identification system image face is more than second
Similarity threshold, just pass through the authentication to user A.
When the registered images determined are the initial registration image in registered images set corresponding to user A, it is only necessary to
Meet face object corresponding to the face of the user A in initial registration image and the user A's in the user A collected image
The similarity of face object corresponding to face is more than the first similarity threshold, you can passes through the authentication to user A.
Assuming that user B reaches gate after the user A by authentication, it is not present in face identification system and belongs to use
Family B registered images.When carrying out authentication to user B, user B image is gathered first, it is assumed that the multiple notes determined
The phase of the face object face object corresponding with the face of the user B in the user B collected image included in volume image
Like the user A of the newest registration in the registered images set corresponding to user A of the maximum registered images of degree image, and determine
Maximum similarity corresponding to the registered images gone out is more than the second similarity threshold, i.e., in registered images set corresponding to user A
Newest registration user A image in user A face corresponding in face object and the user B image that collects
The similarity of face object corresponding to user B face is more than the second similarity threshold.
But because basis passes through condition, it is also necessary to by people corresponding to the face of the user B in the user B collected image
Face object corresponding to the face of the user A in initial registration image in the registered images set corresponding with user A of face object
Similarity and the first similarity threshold be compared.
Due to the registration corresponding with user A of face object corresponding to the face of the user B in the user B collected image
The similarity that the face of the user A in initial registration image in image collection corresponds to face object is less than the first similarity threshold
Value, therefore, user B can not pass through authentication.
In other words, the time of the user B collected image can be used as current time, the user B collected image
In user B face corresponding to face object feature can represent current time user B face feature.A couples of user
The feature of face object corresponding to the face of the user A in initial registration image in the registered images set answered can represent away from
The feature of face from the time user A of current time certain time length.
Feature and the face of the time user A apart from current time certain time length due to current time user B face
The similarity of feature be less than the first similarity threshold, can not meet by condition, then user B can not pass through authentication.
In some optional implementations of the present embodiment, pending authentication user by authentication it
Afterwards, the image of the user collected can be added to the registered images collection belonging to the registered images determined as registered images
In conjunction.So as to which the image of the user of the pending authentication collected be registered in face identification system.
For example, the user of pending authentication is user A, it is assumed that comprising just in registered images set corresponding to user A
The user A of face object corresponding to beginning registered images and the face comprising user A subsequently registered in face identification system
Image.Initial registration image is that user A knows before authentication is carried out to user A using face identification system first in face
The user A registered in other system image, i.e., before carrying out authentication to user A using face identification system first, add
To the image such as user A of the user A in registered images set corresponding to user A certificate photo.Registered images corresponding to user A
The registration of all registered images of the hour of log-on of initial registration image in set in registered images set corresponding to user A
In time earliest.
Reach gate in user A, operate in after the image that face identification system on gate collects user A, from multiple
The registered images determined in registered images are the registered images in registered images set corresponding to user A.
Assuming that the registered images determined are the image of the user A of newest registration in registered images set corresponding to user A
When, it is determined that the initial note in registered images set corresponding to the user A belonging to the image that the registered images gone out are not to determine out
Volume image, when the face of the user A in the initial registration image in registered images set corresponding to user A correspond to face object and
The similarity of face object corresponding to the face of user A in the user A collected image be more than the first similarity threshold with
And in face object corresponding to the face of the user A in the user A of newest registration image and the user A collected image
When the similarity of face object corresponding to user A face is more than the second similarity threshold, pass through the authentication to user A.
It is then possible to the user A collected image is added in registered images set corresponding to user A.
Fig. 3 is refer to, as the realization to method shown in above-mentioned each figure, this application provides a kind of face identification device
One embodiment, the device embodiment are corresponding with the embodiment of the method shown in Fig. 2.
As shown in figure 3, face identification device includes:Processing unit 301, authentication unit 302.Wherein, processing unit 301 is matched somebody with somebody
The image of the user for gathering pending authentication, and the face object for determining to include in multiple registered images are put with adopting
The maximum registered images of the similarity of face object in the image of the user of the pending authentication collected;Authentication unit
302 be configured to judge the registered images determined whether be in registered images set belonging to the registered images determined just
Beginning registered images, judged result is obtained, and the verification mode according to corresponding to judged result determines whether user is tested by identity
Card.
In some optional implementations of the present embodiment, authentication unit 302 includes:First authentication subelement,
It is configured to when judged result is in the registered images set belonging to the registered images that the registered images determined are not to determine out
Initial registration image when, calculate the people in the initial registration image in the registered images set belonging to the registered images determined
The initial registration image similarity of face object in the image of the user of face object and the pending authentication collected;Sentence
It is disconnected whether to meet to pass through condition:Initial registration image similarity is more than the first similarity threshold and the registered images pair determined
The maximum similarity answered is more than the second similarity threshold;When meeting to pass through condition, the user of pending authentication is determined
Pass through authentication;When being unsatisfactory for passing through condition, determine that the user of pending authentication does not pass through authentication.
In some optional implementations of the present embodiment, authentication unit 302 includes:Second authentication subelement,
It is configured to, when it is the initial registration image in the registered images set belonging to registered images that judged result, which is registered images, sentence
Whether maximum similarity is more than the first similarity threshold corresponding to the disconnected registered images determined;If so, determine pending body
The user of part checking passes through authentication;If it is not, determine that the user of pending authentication does not pass through authentication.
In some optional implementations of the present embodiment, the first similarity threshold is less than the second similarity threshold.
In some optional implementations of the present embodiment, face identification device also includes:Registering unit, it is configured to
It is determined that pending authentication user by authentication after, by the figure of the user of the pending authentication collected
In registered images set as belonging to the registered images determined are added to as registered images.
Fig. 4 shows the hardware architecture diagram suitable for being used for the electronic equipment for realizing the embodiment of the present application.
As shown in figure 4, electronic equipment include CPU401, memory 402, wired network adapter 403, wireless network card 404,
CPU401, memory 402, wired network adapter 403, wireless network card 404 are connected with each other by bus 405.According to the present processes
Computer program is may be implemented as, the instruction of the operation described in above-described embodiment is included in the computer program.Computer
Program can be stored in memory 402.The computer journey that the CPU 401 of electronic equipment is stored by calling in memory 402
Sequence, authentication is carried out to user.
Present invention also provides a kind of computer-readable medium, the computer-readable medium can be wrapped in electronic equipment
Include;Can also be individualism, without in supplying electronic equipment.Above computer computer-readable recording medium carries one or more
Program, when one or more program is performed by electronic equipment so that electronic equipment:Gather the user of pending authentication
Image, and determine the figure of the user of the face object included in multiple registered images and the pending authentication collected
The maximum registered images of the similarity of face object as in;Whether the registered images for judging to determine are the registration figure determined
As the initial registration image in affiliated registered images set, judged result, and the checking according to corresponding to judged result are obtained
Mode determines whether user passes through authentication.
It should be noted that computer-readable medium described herein can be computer-readable signal media or meter
Calculation machine readable storage medium storing program for executing either the two any combination.Computer-readable recording medium can for example include but unlimited
In the system of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, device or device, or any combination above.Computer can
Reading the more specifically example of storage medium can include but is not limited to:Electrically connecting with one or more wires, portable meter
Calculation machine disk, hard disk, random access storage device (RAM), read-only storage (ROM), erasable programmable read only memory
(EPROM or flash memory), optical fiber, portable compact disc read-only storage (CD-ROM), light storage device, magnetic memory device or
The above-mentioned any appropriate combination of person.In this application, computer-readable recording medium can be any includes or storage program
Tangible medium, the program can be commanded execution system, device either device use or it is in connection.And in this Shen
Please in, computer-readable signal media can include in a base band or as carrier wave a part propagation data-signal, its
In carry computer-readable program code.The data-signal of this propagation can take various forms, and include but is not limited to
Electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be computer-readable
Any computer-readable medium beyond storage medium, the computer-readable medium can send, propagate or transmit for by
Instruction execution system, device either device use or program in connection.The journey included on computer-readable medium
Sequence code can be transmitted with any appropriate medium, be included but is not limited to:Wirelessly, electric wire, optical cable, RF etc., or it is above-mentioned
Any appropriate combination.
Flow chart and block diagram in accompanying drawing, it is illustrated that according to the system of the various embodiments of the application, method and computer journey
Architectural framework in the cards, function and the operation of sequence product.At this point, each square frame in flow chart or block diagram can generation
The part of one module of table, program segment or code, the part of the module, program segment or code include one or more use
In the executable instruction of logic function as defined in realization.It should also be noted that marked at some as in the realization replaced in square frame
The function of note can also be with different from the order marked in accompanying drawing generation.For example, two square frames succeedingly represented are actually
It can perform substantially in parallel, they can also be performed in the opposite order sometimes, and this is depending on involved function.Also to note
Meaning, the combination of each square frame and block diagram in block diagram and/or flow chart and/or the square frame in flow chart can be with holding
Function as defined in row or the special hardware based system of operation are realized, or can use specialized hardware and computer instruction
Combination realize.
Being described in unit involved in the embodiment of the present application can be realized by way of software, can also be by hard
The mode of part is realized.Described unit can also be set within a processor, for example, can be described as:A kind of processor bag
Include processing unit, authentication unit.Wherein, the title of these units does not form the limit to the unit in itself under certain conditions
It is fixed, for example, processing unit is also described as " being used for the image for gathering the user of pending authentication, and determining more
The maximum registration of the similarity of the face object included in individual registered images and the face object in the image of the user collected
The unit of image ".
Above description is only the preferred embodiment of the application and the explanation to institute's application technology principle.People in the art
Member should be appreciated that invention scope involved in the application, however it is not limited to the technology that the particular combination of above-mentioned technical characteristic forms
Scheme, while should also cover in the case where not departing from the inventive concept, carried out by above-mentioned technical characteristic or its equivalent feature
Other technical schemes that any combination is closed and formed.Such as features described above have with (but not limited to) disclosed herein it is similar
The technical scheme that the technical characteristic of function is replaced mutually and formed.
Claims (12)
1. a kind of face identification method, it is characterised in that methods described includes:
The image of the user of pending authentication is gathered, and determines face object and the collection included in multiple registered images
To the user image in face object the maximum registered images of similarity;
Judge whether the registered images determined are initial registration in registered images set belonging to the registered images determined
Image, judged result is obtained, and the verification mode according to corresponding to judged result determines whether the user passes through authentication.
2. according to the method for claim 1, it is characterised in that the verification mode according to corresponding to judged result determines the use
Whether family is included by authentication:
When first in the registered images set that judged result is belonging to the registered images that the registered images determined are not to determine out
During beginning registered images, the face pair in the initial registration image in the registered images set belonging to the registered images determined is calculated
As the initial registration image similarity with the face object in the image of the user collected;
Judge whether that satisfaction passes through condition:Initial registration image similarity is more than the first similarity threshold and the registration determined
Maximum similarity corresponding to image is more than the second similarity threshold;
When meeting to pass through condition, determine that the user passes through authentication;
When being unsatisfactory for passing through condition, determine that the user does not pass through authentication.
3. according to the method for claim 2, it is characterised in that the verification mode according to corresponding to judged result determines the use
Whether family is included by authentication:
When judged result is that the registered images determined are initial in the registered images set belonging to the registered images determined
During registered images, whether maximum similarity is more than the first similarity threshold corresponding to the registered images that judge to determine;
If so, determine that the user passes through authentication;
If it is not, determine that the user does not pass through authentication.
4. according to the method for claim 3, it is characterised in that first similarity threshold is less than second similarity
Threshold value.
5. according to the method for claim 4, it is characterised in that it is determined that the user by authentication after, it is described
Method also includes:
The image of the user collected is added to the registered images belonging to the registered images determined as registered images
In set.
6. a kind of face identification device, it is characterised in that described device includes:
Processing unit, it is configured to gather the image of the user of pending authentication, and determines to wrap in multiple registered images
The maximum registered images of the similarity of the face object contained and the face object in the image of the user collected;
Authentication unit, it is configured to judge whether the registered images determined are registered images belonging to the registered images determined
Initial registration image in set, judged result is obtained, and the verification mode according to corresponding to judged result determines the user
Whether authentication is passed through.
7. device according to claim 6, it is characterised in that the authentication unit includes:
First authentication subelement, it is configured to when judged result is the registration figure that the registered images determined are not to determine out
During as initial registration image in affiliated registered images set, the registered images set belonging to the registered images determined is calculated
In initial registration image in face object and the face object in the image of the user that collects initial registration figure
As similarity;Judge whether that satisfaction passes through condition:Initial registration image similarity is more than the first similarity threshold and determined
Registered images corresponding to maximum similarity be more than the second similarity threshold;When meeting to pass through condition, the user is determined
Pass through authentication;When being unsatisfactory for passing through condition, determine that the user does not pass through authentication.
8. device according to claim 7, it is characterised in that described device also includes:
Second authentication subelement, it is configured to when judged result is that the registered images determined are the registered images determined
During initial registration image in affiliated registered images set, maximum similarity is corresponding to the registered images that judge to determine
It is no to be more than the first similarity threshold;If so, determine that the user passes through authentication;If it is not, determine that the user does not pass through body
Part checking.
9. device according to claim 8, it is characterised in that first similarity threshold is less than second similarity
Threshold value.
10. device according to claim 9, it is characterised in that described device also includes:
Registering unit, be configured to it is determined that the user by authentication after, by the image of the user collected
It is added to as registered images in the registered images set belonging to the registered images determined.
11. a kind of electronic equipment, it is characterised in that including:
One or more processors;
Memory, for storing one or more programs,
When one or more of programs are by one or more of computing devices so that one or more of processors
Realize the method as described in any in claim 1-5.
12. a kind of computer-readable recording medium, is stored thereon with computer program, it is characterised in that the program is by processor
The method as described in any in claim 1-5 is realized during execution.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710918492.6A CN107679493A (en) | 2017-09-30 | 2017-09-30 | Face identification method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710918492.6A CN107679493A (en) | 2017-09-30 | 2017-09-30 | Face identification method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107679493A true CN107679493A (en) | 2018-02-09 |
Family
ID=61137857
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710918492.6A Pending CN107679493A (en) | 2017-09-30 | 2017-09-30 | Face identification method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107679493A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108804893A (en) * | 2018-03-30 | 2018-11-13 | 百度在线网络技术(北京)有限公司 | A kind of control method, device and server based on recognition of face |
CN110837749A (en) * | 2018-08-15 | 2020-02-25 | 北京京东金融科技控股有限公司 | Identity recognition method, device, electronic equipment and 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 |
CN113158786A (en) * | 2021-03-11 | 2021-07-23 | 光控特斯联(上海)信息科技有限公司 | Face recognition data processing method and device, computer equipment and storage medium |
CN113469012A (en) * | 2021-06-28 | 2021-10-01 | 广州云从鼎望科技有限公司 | Method, system, medium, and apparatus for user face-brushing verification |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102004908A (en) * | 2010-11-30 | 2011-04-06 | 汉王科技股份有限公司 | Self-adapting face identification method and device |
US20140325641A1 (en) * | 2013-04-25 | 2014-10-30 | Suprema Inc. | Method and apparatus for face recognition |
CN105868695A (en) * | 2016-03-24 | 2016-08-17 | 北京握奇数据***有限公司 | Human face recognition method and system |
-
2017
- 2017-09-30 CN CN201710918492.6A patent/CN107679493A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102004908A (en) * | 2010-11-30 | 2011-04-06 | 汉王科技股份有限公司 | Self-adapting face identification method and device |
US20140325641A1 (en) * | 2013-04-25 | 2014-10-30 | Suprema Inc. | Method and apparatus for face recognition |
CN105868695A (en) * | 2016-03-24 | 2016-08-17 | 北京握奇数据***有限公司 | Human face recognition method and system |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108804893A (en) * | 2018-03-30 | 2018-11-13 | 百度在线网络技术(北京)有限公司 | A kind of control method, device and server based on recognition of face |
CN110837749A (en) * | 2018-08-15 | 2020-02-25 | 北京京东金融科技控股有限公司 | Identity recognition method, device, electronic equipment and 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 |
CN113158786A (en) * | 2021-03-11 | 2021-07-23 | 光控特斯联(上海)信息科技有限公司 | Face recognition data processing method and device, computer equipment and storage medium |
CN113469012A (en) * | 2021-06-28 | 2021-10-01 | 广州云从鼎望科技有限公司 | Method, system, medium, and apparatus for user face-brushing verification |
CN113469012B (en) * | 2021-06-28 | 2024-05-03 | 广州云从鼎望科技有限公司 | User face brushing verification method, system, medium and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107679493A (en) | Face identification method and device | |
TWI752418B (en) | Server, client, user authentication method and system | |
CN109993150B (en) | Method and device for identifying age | |
EP3893125A1 (en) | Method and apparatus for searching video segment, device, medium and computer program product | |
CN107729928A (en) | Information acquisition method and device | |
CN108830235A (en) | Method and apparatus for generating information | |
CN106778453B (en) | Method and device for detecting glasses wearing in face image | |
CN107393541A (en) | Information Authentication method and apparatus | |
CN107563360A (en) | Information acquisition method and device | |
CN108805071A (en) | Identity verification method and device, electronic equipment, storage medium | |
CN107578034A (en) | information generating method and device | |
CN108416326A (en) | Face identification method and device | |
CN109871834A (en) | Information processing method and device | |
CN108171204A (en) | Detection method and device | |
CN111095246B (en) | Method and electronic device for authenticating user | |
CN108280422A (en) | The method and apparatus of face for identification | |
EP3038317B1 (en) | User authentication for resource transfer based on mapping of physiological characteristics | |
CN107491674A (en) | Feature based information carries out the method and device of user's checking | |
CN107220652A (en) | Method and apparatus for handling picture | |
CN109871791A (en) | Image processing method and device | |
CN110059624A (en) | Method and apparatus for detecting living body | |
CN107886559A (en) | Method and apparatus for generating picture | |
CN108241855A (en) | image generating method and device | |
CN110110666A (en) | Object detection method and device | |
CN111539903A (en) | Method and device for training face image synthesis model |
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 |