CN106203333A - Face identification method and system - Google Patents
Face identification method and system Download PDFInfo
- Publication number
- CN106203333A CN106203333A CN201610538736.3A CN201610538736A CN106203333A CN 106203333 A CN106203333 A CN 106203333A CN 201610538736 A CN201610538736 A CN 201610538736A CN 106203333 A CN106203333 A CN 106203333A
- Authority
- CN
- China
- Prior art keywords
- facial image
- identified
- face
- degree
- information
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/754—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries involving a deformation of the sample pattern or of the reference pattern; Elastic matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Human Computer Interaction (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The open a kind of face identification method of the embodiment of the present invention and system, belong to image identification technical field, wherein method includes: input the facial image to be identified obtained to the first degree of depth convolutional neural networks to determine the probability that facial image to be identified is for someone, and the first degree of depth convolutional neural networks carries out degree of depth study based on sample facial image and determines；When probability is more than predetermined threshold value, determine facial image to be identified derive from described someone；When described probability is less than predetermined threshold value, by facial image to be identified input to the second degree of depth convolutional neural networks to extract the characteristic information of facial image to be identified；Compare to identify described facial image to be identified with the fixed reference feature information of storage in face characteristic storehouse by the characteristic information of described facial image to be identified；Face is identified by one aspect of the present invention by the first degree of depth convolutional neural networks, on the other hand carries out recognition of face by the way of aspect ratio pair, thus ensure that the effective identification to face.
Description
Technical field
The present invention relates to image identification technical field, particularly to a kind of face identification method and system.
Background technology
Recognition of face is a kind of biological identification technology that facial feature information based on people carries out identification.Use video camera
Or camera collection contains image or the video flowing of face, and detect and track face the most in the picture, and then to detecting
Face carry out a series of correlation techniques of face, be generally also called Identification of Images, facial recognition.
Recognition of face based on image is due to the characteristic such as directly perceived, efficient, in U.S.'s figure, payment, user right checking, search etc.
Important application is had under many scenes.
Using most commonly used face identification method at present is key point matching process, but inventor sends out in practice
Existing, using key point matching process to carry out recognition of face needs to demarcate face and the location of key point and extraction, and one
Aspect requires higher for the disposal ability of hardware, on the other hand for exaggerating expression or wearing the knowledge of the special circumstances such as sunglasses
Other scarce capacity, thus the reliability to face and accuracy can not be realized.
Summary of the invention
The embodiment of the present invention provides a kind of face identification method and system, at least solve above-mentioned technical problem it
One.
On the one hand, the embodiment of the present invention provides a kind of face identification method, including:
The facial image to be identified obtained is inputted to the first degree of depth convolutional neural networks to determine described face to be identified
Image is someone probability, and described first degree of depth convolutional neural networks carries out degree of depth study based on sample facial image and determines；
When described probability is more than predetermined threshold value, determine described facial image to be identified derive from described someone；
When described probability is less than predetermined threshold value, described facial image to be identified is inputted to the second degree of depth convolutional Neural net
Network is to extract the characteristic information of described facial image to be identified；
Described characteristic information is compared with the fixed reference feature information of storage in face characteristic storehouse and waits to know described in identifying
Other facial image, described fixed reference feature information is at least based on described sample Face image synthesis.
On the other hand, also provide for a kind of face identification system, including:
First identification module, inputs to the first degree of depth convolutional neural networks for the facial image to be identified that will obtain with really
Fixed described facial image to be identified is someone probability, and described first degree of depth convolutional neural networks is carried out based on sample facial image
Degree of depth study determines；
Threshold value judgment module, is used for judging that whether described probability is more than described predetermined threshold value；
First performs module, for when described probability is more than predetermined threshold value, determining that described facial image to be identified is originated
In described someone；
Second performs module, for when described probability is less than predetermined threshold value, being inputted extremely by described facial image to be identified
Second degree of depth convolutional neural networks is to extract the characteristic information of described facial image to be identified；
Second identification module, for comparing described characteristic information with the fixed reference feature information of storage in face characteristic storehouse
Relatively to identify described facial image to be identified, described fixed reference feature information is at least based on described sample Face image synthesis.
In the face identification method of the embodiment of the present invention and system, at two aspects, face is identified, thus protected
Demonstrate,prove the effective identification to face.On the one hand, by training the first degree of depth convolutional Neural net obtained based on sample facial image
Face is identified by network, and determines the probability that recognition result is correct accordingly；On the other hand, when judging that this probit is less than
During predetermined threshold value, just further by extract facial image to be identified characteristic information and with the ginseng of storage in face characteristic storehouse
Examine mode that characteristic information compares to carry out recognition of face.The identification to face is realized by above-mentioned two aspects, it is to avoid
It is based solely on when the first degree of depth convolutional neural networks is identified due to the first quality problems of degree of depth convolutional neural networks own
The recognition failures that cannot correctly identify facial image and cause or the situation of wrong identification, but further pass through the opposing party
Face is extracted the characteristic information of facial image to be identified and compares with the fixed reference feature information of storage in the face characteristic storehouse that prestores
To identify described facial image to be identified, it is achieved thereby that the dual guarantee to recognition of face, it is ensured that the effective knowledge to face
Not.
Accompanying drawing explanation
In order to be illustrated more clearly that the technical scheme of the embodiment of the present invention, required use in embodiment being described below
Accompanying drawing be briefly described, it should be apparent that, below describe in accompanying drawing be some embodiments of the present invention, for ability
From the point of view of the those of ordinary skill of territory, on the premise of not paying creative work, it is also possible to obtain the attached of other according to these accompanying drawings
Figure.
Fig. 1 is the flow chart of face identification method one embodiment of the present invention；
Fig. 2 is the flow chart of another embodiment of face identification method of the present invention；
Fig. 3 is the flow chart of the another embodiment of face identification method of the present invention；
Fig. 4 is the theory diagram of face identification system one embodiment of the present invention；
Fig. 5 is the theory diagram of the second execution module one embodiment in the face identification system of the present invention；
Fig. 6 is the theory diagram of the second identification module one embodiment in the face identification system of the present invention；
Fig. 7 is the theory diagram of another embodiment of the face identification system of the present invention；
Fig. 8 is the structural representation of an embodiment of the subscriber equipment of the present invention.
Specific embodiment
For making the purpose of the embodiment of the present invention, technical scheme and advantage clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
The a part of embodiment of the present invention rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art
The every other embodiment obtained under not making creative work premise, broadly falls into the scope of protection of the invention.
It should be noted that in the case of not conflicting, the embodiment in the application and the feature in embodiment can phases
Combination mutually.
The present invention can be used in numerous general or special purpose computing system environment or configuration.Such as: personal computer, service
Device computer, handheld device or portable set, laptop device, multicomputer system, system based on microprocessor, top set
Box, programmable consumer-elcetronics devices, network PC, minicomputer, mainframe computer, include any of the above system or equipment
Distributed computing environment etc..
The present invention can be described in the general context of computer executable instructions, such as program
Module.Usually, program module includes performing particular task or realizing the routine of particular abstract data type, program, object, group
Part, data structure etc..The present invention can also be put into practice in a distributed computing environment, in these distributed computing environment, by
The remote processing devices connected by communication network performs task.In a distributed computing environment, program module is permissible
It is positioned in the local and remote computer-readable storage medium of storage device.
In the present invention, " assembly ", " device ", " system " etc. refer to be applied to the related entities of computer, such as hardware, hard
Part and the combination of software, software or executory software etc..In detail, such as, assembly can but be not limited to run on place
The reason process of device, processor, object, can executive module, perform thread, program and/or computer.Further, server is run on
On application program or shell script, server can be assembly.One or more assemblies can be at the process performed and/or line
Cheng Zhong, and assembly can localize and/or be distributed between two or multiple stage computer on one computer, it is possible to by
Various computer-readable mediums run.Assembly can also be according to having the signal of one or more packet, such as, from one
With another component interaction in local system, distributed system, and/or the network in the Internet handed over by signal and other system
The signal of mutual data is communicated by locally and/or remotely process.
Finally, in addition it is also necessary to explanation, in this article, the relational terms of such as first and second or the like be used merely to by
One entity or operation separate with another entity or operating space, and not necessarily require or imply these entities or operation
Between exist any this reality relation or order.And, term " includes ", " comprising ", not only includes those key elements, and
And also include other key elements being not expressly set out, or also include intrinsic for this process, method, article or equipment
Key element.In the case of there is no more restriction, statement " including ... " key element limited, it is not excluded that including described wanting
Process, method, article or the equipment of element there is also other identical element.
As it is shown in figure 1, the face identification method of one embodiment of the invention, including:
S11, by obtain facial image to be identified input described to be identified to determine to the first degree of depth convolutional neural networks
Facial image is someone probability, and described first degree of depth convolutional neural networks carries out degree of depth study really based on sample facial image
Fixed；
S12, when described probability is more than predetermined threshold value, determine described facial image to be identified derive from described someone；
S13, when described probability is less than predetermined threshold value, by refreshing to the second degree of depth convolution for the input of described facial image to be identified
Through network to extract the characteristic information of described facial image to be identified；
S14, the fixed reference feature information of storage in the characteristic information of described facial image to be identified and face characteristic storehouse is entered
Row compares to identify described facial image to be identified, and described fixed reference feature information is at least based on described sample Face image synthesis.
In the present embodiment, at two aspects, face is identified, thus be ensure that the effective identification to face.One
Aspect, is identified face by the first degree of depth convolutional neural networks obtained based on the training of sample facial image, and phase
The probability that the determination recognition result answered is correct；On the other hand, (the default threshold here when judging this probit less than predetermined threshold value
Value can take 0.9, or the value asking for bigger value or less according to accuracy of identification), the most further by extracting
The characteristic information of facial image to be identified the mode compared with the fixed reference feature information of storage in face characteristic storehouse are entered
Row recognition of face.The identification to face is realized, it is to avoid be based solely on the first degree of depth convolutional Neural net by above-mentioned two aspects
Cannot correctly identify that facial image causes due to the first quality problems of degree of depth convolutional neural networks own when network is identified
Recognition failures or the situation of wrong identification, but further by the other hand extracting the feature letter of facial image to be identified
Breath also compares to identify described facial image to be identified with the fixed reference feature information of storage in the face characteristic storehouse that prestores, thus
Achieve the dual guarantee to recognition of face, it is ensured that the effective identification to face.
Facial image to be identified in step S11 of the present embodiment is from the image that video or hardware device gather
Obtain, and image has been carried out pretreatment, such as, image is carried out filtration more clear to obtain edge with image sharpening
Clear, use DPM (Deformable Part Model) algorithm detect from image and obtain facial image to be identified afterwards.
In step S11 in the present embodiment, the first degree of depth convolutional neural networks wraps to outfan the most successively from input
Input layer, five convolutional layers, full articulamentum and output layer are included, using sample facial image as input, with corresponding to each
The setting value of individual sample facial image be output be trained the degree of depth study obtain；Sample facial image in the present embodiment is permissible
10000 pictures selecting 1000 people are sample facial image, with this 10000 pictures for input, constantly adjust first deep
Degree convolutional neural networks, until the rate of accuracy reached of the output result of this first degree of depth convolutional neural networks is to certain threshold value, this threshold
Value can be 0.9, or according to the difference of the requirement to facial image accuracy of identification, this threshold value is heightened or turned down.
In step S13 in the present embodiment, the second degree of depth convolutional neural networks wraps to outfan the most successively from input
Input layer, five convolutional layers, pond layer, three normalization layers, full articulamentum and output layer, the second degree of depth convolution are included
Neutral net obtains again by above-mentioned training method, and in the training process by sample facial image at full articulamentum
Exporting as the description to sample facial image, i.e. as the fixed reference feature information of sample facial image, (fixed reference feature information is extremely
Include marginal information based on sample facial image, texture information and shape information less to generate, and fixed reference feature information
It is a Serial No. quantified), and fixed reference feature information is stored to face feature database.
As in figure 2 it is shown, in certain embodiments, the input of described facial image to be identified is rolled up by step S13 to second degree of depth
Long-pending neutral net includes with the characteristic information extracting described facial image to be identified:
S21, by the input of described facial image to be identified to described second degree of depth convolutional neural networks；
S22, obtain the feature of described facial image to be identified from the full articulamentum of described second degree of depth convolutional neural networks
Information.
By when described probability is less than predetermined threshold value in the present embodiment, i.e. by the first degree of depth convolutional neural networks not
When energy identifies the identity information of facial image to be identified, (picture quality of the facial image to be identified being likely due to acquisition is inadequate
Height, the clearest, thus can not completely identify；Or due to the sample used in the process of the first degree of depth convolutional neural networks training
This limited space, is not sufficient to be met the neutral net of accuracy of identification requirement；Or because of facial image to be identified also
It is not belonging to train any one in the sample facial image of the first degree of depth convolutional neural networks, i.e. facial image to be identified is
New facial image), then the characteristic information obtaining facial image to be identified stores in face characteristic storehouse for follow-up
The mode compared of fixed reference feature information to identify facial image to be identified.
In certain embodiments, when the picture quality of the facial image to be identified owing to obtaining is not high enough, the clearest, from
And can not completely identify；Or owing to the sample space used in the process of the first degree of depth convolutional neural networks training is limited, and
It is not enough to be met the neutral net of accuracy of identification requirement and cause to be treated by the first degree of depth convolutional neural networks identification
When identifying the identity information of facial image, facial image to be identified is identified by the mode carrying out aspect ratio pair further,
Ensure that the success rate of recognition of face；If additionally, in this case by aspect ratio to after still None-identified people to be identified
Face image (is below threshold value with the similarity of the fixed reference feature information in face characteristic storehouse), then be judged to this face figure to be identified
The characteristic information of picture is not stored in face characteristic storehouse as fixed reference feature information, the most then will correspond to this people to be identified
The characteristic information of face image actively writes in face characteristic storehouse, for when this facial image to be identified is again as input picture
Time smoothly complete recognition of face.
When in the sample facial image training the first degree of depth convolutional neural networks due to facial image to be identified being not belonging to
Any one, i.e. facial image to be identified is new facial image, the most directly will correspond to the spy of this facial image to be identified
Reference breath actively writes in face characteristic storehouse, smoothly completes for when this facial image to be identified is again as input picture
Recognition of face；The present embodiment is by will not belong to train the people to be identified of the sample facial image of the first degree of depth convolutional neural networks
The characteristic information of face image writes direct the mode in face characteristic storehouse, gradually improves the identification of the face to separate sources, with
As long as time also without have new face just to carry out the first degree of depth convolutional neural networks training and expense on the cost that brings (time
Between cost and Financial cost).
In certain embodiments, face characteristic storehouse includes the first face feature database and the second face characteristic storehouse, the first face
Feature database is for storing the fixed reference feature information corresponding to described sample facial image, and the second face characteristic storehouse is used for storing accordingly
New fixed reference feature information in new identity information.
The second face characteristic storehouse in the present embodiment is exactly the feature letter of the facial image of None-identified in above-described embodiment
The place that breath is write.
The first face feature database and the second face characteristic storehouse in the present embodiment can be physically separate two storages
Space, it is also possible to be the different memory area in same memory space.The present embodiment stores in the second face characteristic storehouse
Fixed reference feature information can be the feature of facial image of the None-identified constantly write one by one in face recognition process
Information, it is also possible to be that the characteristic information of the facial image directly obtained in batch from other face identification system (such as, has A and B
Two face identification systems, correspond respectively to two face feature databases of a and b, at this moment can directly obtain face identification system B's
Face characteristic storehouse is directly as the part in the second face characteristic storehouse of face identification system), thus avoid when needing expansion
When filling a face identification system, it is necessary to the first degree of depth convolutional neural networks is carried out re-training and the cost overhead that brings,
Cost overhead is typically embodied as time cost, and the training need substantial amounts of time of the first degree of depth convolutional neural networks is carried out repeatedly
Training, and during the training of this rapid lapse of time, whole original face identification system can only quit work, thus also make
Become the waste in resource.
As it is shown on figure 3, in certain embodiments, by the characteristic information of described facial image to be identified and face characteristic storehouse
The fixed reference feature information of storage compares to identify that described facial image to be identified includes:
In S31, the characteristic information calculating described facial image to be identified respectively and described face characteristic storehouse, storage is all
Similarity value between fixed reference feature information；
S32, to calculated all Similarity value according to being ranked up from big to small, and take the preceding phase of multiple ranking
Like angle value；
S33, determine that in the identity information corresponding to the preceding Similarity value of the plurality of ranking is respectively, number of repetition is most
The identity information for described facial image to be identified, or determine maximum the identity information corresponding to Similarity value be described
The identity information of facial image to be identified.
In the present embodiment, more than characteristic information and fixed reference feature information are calculated between two vectors in vector form
String Similarity value, is ranked up according to order from big to small calculated all of cosine similarity value afterwards, and from
Multiple cosine similarity value is taken greatly to little.
Inquire about the identity that whether there is repetition in the multiple identity informations corresponding to multiple cosine similarity values selected again
Information；
If it is, determining is wherein the identity corresponding to facial image to be identified by the identity information that number of repetition is most
Information, such as, has taken out 20 cosine similarity values, wherein has 5 cosine similarity values to both correspond to Zhang San, 2 cosine phases
Both corresponding to Li Si like angle value, remaining 13 cosine similarity values correspond respectively to different identity informations, it is determined that weighed
Again most identity informations that Zhang San is facial image to be identified is counted；
If it is not, then determine the identity that the identity information corresponding to cosine similarity value is facial image to be identified of maximum
Information.
In certain embodiments, after calculating all of cosine similarity value, first determine whether the cosine similarity of maximum
Whether value is less than predetermined threshold value, such as, if less than 0.9, if less than then judging that in face characteristic storehouse, storage does not has phase
In the fixed reference feature information of this facial image to be identified, and the characteristic information of this facial image to be identified should be write face characteristic
In storehouse.
The embodiment of the present invention can be passed through hardware processor (hardware processor) and realize correlation function mould
Block.
It should be noted that for aforesaid each method embodiment, in order to be briefly described, therefore it is all expressed as a series of
Action merge, but those skilled in the art should know, the present invention is not limited by described sequence of movement because
According to the present invention, some step can use other orders or carry out simultaneously.Secondly, those skilled in the art also should know
Knowing, embodiment described in this description belongs to preferred embodiment, involved action and the module not necessarily present invention
Necessary.
In the above-described embodiments, the description to each embodiment all emphasizes particularly on different fields, and does not has the portion described in detail in certain embodiment
Point, may refer to the associated description of other embodiments.
As shown in Figure 4, the embodiment of the present invention also provides for a kind of face identification system, comprising:
First identification module, inputs to the first degree of depth convolutional neural networks for the facial image to be identified that will obtain with really
Fixed described facial image to be identified is someone probability, and described first degree of depth convolutional neural networks is carried out based on sample facial image
Degree of depth study determines；
Threshold value judgment module, is used for judging that whether described probability is more than described predetermined threshold value；
First performs module, for when described probability is more than predetermined threshold value, determining that described facial image to be identified is originated
In described someone；
Second performs module, for when described probability is less than predetermined threshold value, being inputted extremely by described facial image to be identified
Second degree of depth convolutional neural networks is to extract the characteristic information of described facial image to be identified；
Second identification module, for comparing described characteristic information with the fixed reference feature information of storage in face characteristic storehouse
Relatively to identify described facial image to be identified, described fixed reference feature information is at least based on described sample Face image synthesis.
In the present embodiment, at two aspects, face is identified, thus be ensure that the effective identification to face.One
Aspect, is identified face by the first degree of depth convolutional neural networks obtained based on the training of sample facial image, and phase
The probability that the determination recognition result answered is correct；On the other hand, (the default threshold here when judging this probit less than predetermined threshold value
Value can take 0.9, or the value asking for bigger value or less according to accuracy of identification), the most further by extracting
The characteristic information of facial image to be identified the mode compared with the fixed reference feature information of storage in face characteristic storehouse are entered
Row recognition of face.The identification to face is realized, it is to avoid be based solely on the first degree of depth convolutional Neural net by above-mentioned two aspects
Cannot correctly identify that facial image causes due to the first quality problems of degree of depth convolutional neural networks own when network is identified
Recognition failures or the situation of wrong identification, but further by the other hand extracting the feature letter of facial image to be identified
Breath also compares to identify described facial image to be identified with the fixed reference feature information of storage in the face characteristic storehouse that prestores, thus
Achieve the dual guarantee to recognition of face, it is ensured that the effective identification to face.
As it is shown in figure 5, in certain embodiments, second performs module includes:
Image transmitting unit, for by described facial image to be identified input extremely described second degree of depth convolutional neural networks；
Characteristic acquisition unit, waits to know described in obtaining from the full articulamentum of described second degree of depth convolutional neural networks
The characteristic information of other facial image.
As shown in Figure 6, in certain embodiments, the second identification module includes:
Similarity calculated, for calculating all ginsengs of storage in described characteristic information and described face characteristic storehouse respectively
Examine the Similarity value between characteristic information；
Similarity value acquiring unit, is used for calculated all Similarity value according to being ranked up from big to small, and
Take the preceding Similarity value of multiple ranking；
Identity information determines unit, for determining the identity letter corresponding to the plurality of ranking preceding Similarity value difference
The identity information for described facial image to be identified that in breath, number of repetition is most, or determine corresponding to maximum Similarity value
The identity information that identity information is described facial image to be identified.
As it is shown in fig. 7, in some embodiments of face identification system, also include:
Feature database more new module, for special corresponding to the new reference of new identity information to the write of described face characteristic storehouse
Reference ceases.
In certain embodiments, face characteristic storehouse includes the first face feature database and the second face characteristic storehouse, described first
Face characteristic storehouse is for storing the fixed reference feature information corresponding to described sample facial image, and described second face characteristic storehouse is used for
Store the new fixed reference feature information corresponding to new identity information.
The face identification system of the invention described above embodiment can be used for performing the face identification method of the embodiment of the present invention, and
Reach the technique effect that the face identification method of the invention described above embodiment is reached accordingly, repeat no more here.
On the other hand, the embodiment of the present invention is also disclosed a kind of server, and this server includes:
Memorizer, is used for depositing computer-managed instruction；
Processor, for performing the computer-managed instruction of described memorizer storage, to perform:
The facial image to be identified obtained is inputted to the first degree of depth convolutional neural networks to determine described face to be identified
Image is someone probability, and described first degree of depth convolutional neural networks carries out degree of depth study based on sample facial image and determines；
When described probability is more than predetermined threshold value, determine described facial image to be identified derive from described someone；
When described probability is less than predetermined threshold value, described facial image to be identified is inputted to the second degree of depth convolutional Neural net
Network is to extract the characteristic information of described facial image to be identified；
Described characteristic information is compared with the fixed reference feature information of storage in face characteristic storehouse and waits to know described in identifying
Other facial image, described fixed reference feature information is at least based on described sample Face image synthesis.
As shown in Figure 8, for the structural representation of server in the above embodiment of the present invention one embodiment, the application is specifically real
Execute example not limit with implementing of server 800, comprising:
Processor (processor) 810, communication interface (Communications Interface) 820, memorizer
(memory) 830 and communication bus 840.Wherein:
Processor 810, communication interface 820 and memorizer 830 complete mutual communication by communication bus 840.
Communication interface 820, for the net element communication with such as third party's access end etc..
Processor 810, is used for the program that performs 832, specifically can perform the correlation step in said method embodiment.
Specifically, program 832 can include that program code, described program code include computer-managed instruction.
Processor 810 is probably a central processor CPU, or specific integrated circuit ASIC (Application
Specific Integrated Circuit), or it is configured to implement the one or more integrated electricity of the embodiment of the present application
Road.
Embodiment of the method described above is only schematically, and the wherein said unit illustrated as separating component can
To be or to may not be physically separate, the parts shown as unit can be or may not be physics list
Unit, i.e. may be located at a place, or can also be distributed on multiple NE.Can be selected it according to the actual needs
In some or all of module realize the purpose of the present embodiment scheme.Those of ordinary skill in the art are not paying creativeness
Work in the case of, be i.e. appreciated that and implement.
By the description of above embodiment, those skilled in the art is it can be understood that can be by each embodiment
Software adds the mode of required general hardware platform and realizes, naturally it is also possible to pass through hardware.Based on such understanding, above-mentioned skill
The part that prior art is contributed by art scheme the most in other words can embody with the form of software product, this calculating
Machine software product can store in a computer-readable storage medium, such as ROM/RAM, magnetic disc, CD etc., uses including some instructions
So that computer equipment (can be personal computer, server, or the network equipment etc.) perform each embodiment or
The method described in some part of person's embodiment.
Those skilled in the art are it should be appreciated that embodiments of the invention can be provided as method, system or computer program
Product.Therefore, the reality in terms of the present invention can use complete hardware embodiment, complete software implementation or combine software and hardware
Execute the form of example.And, the present invention can use at one or more computers wherein including computer usable program code
The shape of the upper computer program implemented of usable storage medium (including but not limited to disk memory and optical memory etc.)
Formula.
The present invention is with reference to method, equipment (system) and the flow process of computer program according to embodiments of the present invention
Figure and/or block diagram describe.It should be understood that can the most first-class by computer program instructions flowchart and/or block diagram
Flow process in journey and/or square frame and flow chart and/or block diagram and/or the combination of square frame.These computer programs can be provided
Instruction arrives the processor of general purpose computer, special-purpose computer, Embedded Processor or other programmable data processing device to produce
A raw machine so that the instruction performed by the processor of computer or other programmable data processing device is produced for real
The device of the function specified in one flow process of flow chart or multiple flow process and/or one square frame of block diagram or multiple square frame now.
These computer program instructions may be alternatively stored in and computer or other programmable data processing device can be guided with spy
Determine in the computer-readable memory that mode works so that the instruction being stored in this computer-readable memory produces and includes referring to
Make the manufacture of device, this command device realize at one flow process of flow chart or multiple flow process and/or one square frame of block diagram or
The function specified in multiple square frames.These computer program instructions also can be loaded into computer or other programmable datas process and set
It is standby upper so that on computer or other programmable devices, execution sequence of operations step is to produce computer implemented process,
Thus the instruction performed on computer or other programmable devices provides for realizing at one flow process of flow chart or multiple stream
The step of the function specified in journey and/or one square frame of block diagram or multiple square frame.
Last it is noted that above example is only in order to illustrate technical scheme, it is not intended to limit；Although
With reference to previous embodiment, the present invention is described in detail, it will be understood by those within the art that: it still may be used
So that the technical scheme described in foregoing embodiments to be modified, or wherein portion of techniques feature is carried out equivalent；
And these amendment or replace, do not make appropriate technical solution essence depart from various embodiments of the present invention technical scheme spirit and
Scope.
Claims (10)
1. a face identification method, including:
The facial image to be identified obtained is inputted to the first degree of depth convolutional neural networks to determine described facial image to be identified
For someone probability, described first degree of depth convolutional neural networks carries out degree of depth study based on sample facial image and determines；
When described probability is more than predetermined threshold value, determine described facial image to be identified derive from described someone；
When described probability less than predetermined threshold value time, will described facial image to be identified input to the second degree of depth convolutional neural networks with
Extract the characteristic information of described facial image to be identified；
Compare to identify described people to be identified with the fixed reference feature information of storage in face characteristic storehouse by described characteristic information
Face image, described fixed reference feature information is at least based on described sample Face image synthesis.
Method the most according to claim 1, wherein, described by described facial image to be identified input to the second degree of depth convolution
Neutral net includes with the characteristic information extracting described facial image to be identified:
By the input of described facial image to be identified to described second degree of depth convolutional neural networks；
The characteristic information of described facial image to be identified is obtained from the full articulamentum of described second degree of depth convolutional neural networks.
Method the most according to claim 2, wherein, described by the reference of storage in described characteristic information and face characteristic storehouse
Characteristic information compares to identify that described facial image to be identified includes:
Calculate the similarity between all fixed reference feature information of storage in described characteristic information and described face characteristic storehouse respectively
Value；
To calculated all Similarity value according to being ranked up from big to small, and take the preceding Similarity value of multiple ranking；
Determine number of repetition in the identity information corresponding to the preceding Similarity value of the plurality of ranking is respectively most for described
The identity information of facial image to be identified, or
Determine the identity information that the identity information corresponding to Similarity value is described facial image to be identified of maximum.
Method the most according to claim 3, wherein, also includes: write corresponding to new identity to described face characteristic storehouse
The new fixed reference feature information of information.
Method the most according to claim 4, wherein, described face characteristic storehouse includes the first face feature database and the second face
Feature database, described first face feature database for storage corresponding to the fixed reference feature information of described sample facial image, described the
Two face characteristic storehouses are for storing the new fixed reference feature information corresponding to new identity information.
6. a face identification system, including:
First identification module, inputs to the first degree of depth convolutional neural networks for the facial image to be identified that will obtain to determine
Stating the probability that facial image to be identified is for someone, described first degree of depth convolutional neural networks carries out the degree of depth based on sample facial image
Study determines；
Threshold value judgment module, is used for judging that whether described probability is more than described predetermined threshold value；
First performs module, for when described probability is more than predetermined threshold value, determining that described facial image to be identified derives from institute
State someone；
Second performs module, for when described probability is less than predetermined threshold value, inputting described facial image to be identified to second
Degree of depth convolutional neural networks is to extract the characteristic information of described facial image to be identified；
Second identification module, for the fixed reference feature information of storage in described characteristic information and face characteristic storehouse is compared with
Identifying described facial image to be identified, described fixed reference feature information is at least based on described sample Face image synthesis.
System the most according to claim 6, wherein, described second performs module includes:
Image transmitting unit, for by described facial image to be identified input extremely described second degree of depth convolutional neural networks；
Characteristic acquisition unit, for obtaining described people to be identified from the full articulamentum of described second degree of depth convolutional neural networks
The characteristic information of face image.
System the most according to claim 7, wherein, described second identification module includes:
Similarity calculated, special for calculating all references of storage in described characteristic information and described face characteristic storehouse respectively
Similarity value between reference breath；
Similarity value acquiring unit, is used for calculated all Similarity value according to being ranked up from big to small, and takes many
The preceding Similarity value of individual ranking；
Identity information determines unit, for determining in the identity information corresponding to the plurality of ranking preceding Similarity value difference
The identity information for described facial image to be identified that number of repetition is most, or determine the body corresponding to Similarity value of maximum
Part information is the identity information of described facial image to be identified.
System the most according to claim 8, wherein, also includes:
Feature database more new module, for believing corresponding to the new fixed reference feature of new identity information to the write of described face characteristic storehouse
Breath.
System the most according to claim 9, wherein, described face characteristic storehouse includes the first face feature database and the second people
Face feature database, described first face feature database is for storing the fixed reference feature information corresponding to described sample facial image, described
Second face characteristic storehouse is for storing the new fixed reference feature information corresponding to new identity information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610538736.3A CN106203333A (en) | 2016-07-08 | 2016-07-08 | Face identification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610538736.3A CN106203333A (en) | 2016-07-08 | 2016-07-08 | Face identification method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106203333A true CN106203333A (en) | 2016-12-07 |
Family
ID=57474123
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610538736.3A Pending CN106203333A (en) | 2016-07-08 | 2016-07-08 | Face identification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106203333A (en) |
Cited By (37)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106920310A (en) * | 2017-03-06 | 2017-07-04 | 珠海习悦信息技术有限公司 | Access control method, apparatus and system |
| CN106919918A (en) * | 2017-02-27 | 2017-07-04 | 腾讯科技（上海）有限公司 | A kind of face tracking method and device |
| CN107123117A (en) * | 2017-04-26 | 2017-09-01 | 广东工业大学 | A kind of IC pin quality of welding spot detection method and device based on deep learning |
| CN107153820A (en) * | 2017-05-10 | 2017-09-12 | 电子科技大学 | A kind of recognition of face and movement locus method of discrimination towards strong noise |
| CN107644209A (en) * | 2017-09-21 | 2018-01-30 | 百度在线网络技术（北京）有限公司 | Method for detecting human face and device |
| CN107704809A (en) * | 2017-09-11 | 2018-02-16 | 安徽慧视金瞳科技有限公司 | Based on interference characteristic vector data collection 1 than N face feature vector comparison methods |
| CN107958215A (en) * | 2017-11-23 | 2018-04-24 | 深圳市分期乐网络科技有限公司 | A kind of antifraud recognition methods, device, server and storage medium |
| CN108154085A (en) * | 2017-12-06 | 2018-06-12 | 北京顺源开华科技有限公司 | The method, apparatus and electronic equipment of identification are carried out based on electrocardiogram (ECG) data |
| CN108171158A (en) * | 2017-12-27 | 2018-06-15 | 北京迈格威科技有限公司 | Biopsy method, device, electronic equipment and storage medium |
| CN108197628A (en) * | 2017-12-07 | 2018-06-22 | 维森软件技术（上海）有限公司 | The joint judgment method of characteristics of image based on deep neural network |
| CN108229297A (en) * | 2017-09-30 | 2018-06-29 | 深圳市商汤科技有限公司 | Face identification method and device, electronic equipment, computer storage media |
| CN108229673A (en) * | 2016-12-27 | 2018-06-29 | 北京市商汤科技开发有限公司 | Processing method, device and the electronic equipment of convolutional neural networks |
| CN108734673A (en) * | 2018-04-20 | 2018-11-02 | 平安科技（深圳）有限公司 | Descreening systematic training method, descreening method, apparatus, equipment and medium |
| CN108875502A (en) * | 2017-11-07 | 2018-11-23 | 北京旷视科技有限公司 | Face identification method and device |
| CN108921008A (en) * | 2018-05-14 | 2018-11-30 | 深圳市商汤科技有限公司 | Portrait identification method, device and electronic equipment |
| CN109036575A (en) * | 2018-07-13 | 2018-12-18 | 希蓝科技（北京）有限公司 | A kind of data processing method and device |
| CN109387521A (en) * | 2017-08-04 | 2019-02-26 | 欧姆龙株式会社 | Image processing system |
| WO2019037346A1 (en) * | 2017-08-25 | 2019-02-28 | 广州视源电子科技股份有限公司 | Method and device for optimizing human face picture quality evaluation model |
| CN109472292A (en) * | 2018-10-11 | 2019-03-15 | 平安科技（深圳）有限公司 | A kind of sensibility classification method of image, storage medium and server |
| CN109583348A (en) * | 2018-11-22 | 2019-04-05 | 阿里巴巴集团控股有限公司 | A kind of face identification method, device, equipment and system |
| CN109583387A (en) * | 2018-11-30 | 2019-04-05 | 龙马智芯（珠海横琴）科技有限公司 | Identity identifying method and device |
| CN109615750A (en) * | 2018-12-29 | 2019-04-12 | 深圳市多度科技有限公司 | The recognition of face control method and device of door access machine, access control equipment, storage medium |
| CN109671241A (en) * | 2017-10-16 | 2019-04-23 | 中国电信股份有限公司 | Alarm method and system |
| CN109800707A (en) * | 2019-01-17 | 2019-05-24 | 中控智慧科技股份有限公司 | A kind of face identification method based on CNN model, device and storage medium |
| CN109961000A (en) * | 2018-10-22 | 2019-07-02 | 大连艾米移动科技有限公司 | A kind of intelligence examination hall anti-cheating system |
| CN110688941A (en) * | 2019-09-25 | 2020-01-14 | 支付宝(杭州)信息技术有限公司 | Face image recognition method and device |
| CN110826525A (en) * | 2019-11-18 | 2020-02-21 | 天津高创安邦技术有限公司 | Face recognition method and system |
| CN110869937A (en) * | 2017-07-21 | 2020-03-06 | 北京市商汤科技开发有限公司 | Face image duplication removal method and apparatus, electronic device, storage medium, and program |
| CN111191563A (en) * | 2019-12-26 | 2020-05-22 | 三盟科技股份有限公司 | Face recognition method and system based on data sample and test data set training |
| CN111325240A (en) * | 2020-01-23 | 2020-06-23 | 杭州睿琪软件有限公司 | Weed-related computer-executable method and computer system |
| CN111368101A (en) * | 2020-03-05 | 2020-07-03 | 腾讯科技（深圳）有限公司 | Multimedia resource information display method, device, equipment and storage medium |
| CN111368622A (en) * | 2019-10-18 | 2020-07-03 | 杭州海康威视系统技术有限公司 | Personnel identification method and device, and storage medium |
| CN111860066A (en) * | 2019-04-30 | 2020-10-30 | 百度时代网络技术（北京）有限公司 | Face recognition method and device |
| CN112084903A (en) * | 2020-08-26 | 2020-12-15 | 武汉普利商用机器有限公司 | Method and system for updating face recognition base photo |
| CN112101215A (en) * | 2020-09-15 | 2020-12-18 | Oppo广东移动通信有限公司 | Face input method, terminal equipment and computer readable storage medium |
| CN112699803A (en) * | 2020-12-31 | 2021-04-23 | 竹间智能科技（上海）有限公司 | Face recognition method, system, device and readable storage medium |
| CN115880761A (en) * | 2023-02-09 | 2023-03-31 | 数据空间研究院 | Face recognition method, system, storage medium and application based on strategy optimization |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5699449A (en) * | 1994-11-14 | 1997-12-16 | The University Of Connecticut | Method and apparatus for implementation of neural networks for face recognition |
| CN104008395A (en) * | 2014-05-20 | 2014-08-27 | 中国科学技术大学 | Intelligent bad video detection method based on face retrieval |
| CN104778448A (en) * | 2015-03-24 | 2015-07-15 | 孙建德 | Structure adaptive CNN (Convolutional Neural Network)-based face recognition method |
| CN105631403A (en) * | 2015-12-17 | 2016-06-01 | 小米科技有限责任公司 | Method and device for human face recognition |
| CN105654033A (en) * | 2015-12-21 | 2016-06-08 | 小米科技有限责任公司 | Face image verification method and device |
-
2016
- 2016-07-08 CN CN201610538736.3A patent/CN106203333A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5699449A (en) * | 1994-11-14 | 1997-12-16 | The University Of Connecticut | Method and apparatus for implementation of neural networks for face recognition |
| CN104008395A (en) * | 2014-05-20 | 2014-08-27 | 中国科学技术大学 | Intelligent bad video detection method based on face retrieval |
| CN104778448A (en) * | 2015-03-24 | 2015-07-15 | 孙建德 | Structure adaptive CNN (Convolutional Neural Network)-based face recognition method |
| CN105631403A (en) * | 2015-12-17 | 2016-06-01 | 小米科技有限责任公司 | Method and device for human face recognition |
| CN105654033A (en) * | 2015-12-21 | 2016-06-08 | 小米科技有限责任公司 | Face image verification method and device |
Cited By (50)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108229673A (en) * | 2016-12-27 | 2018-06-29 | 北京市商汤科技开发有限公司 | Processing method, device and the electronic equipment of convolutional neural networks |
| CN106919918B (en) * | 2017-02-27 | 2022-11-29 | 腾讯科技（上海）有限公司 | Face tracking method and device |
| CN106919918A (en) * | 2017-02-27 | 2017-07-04 | 腾讯科技（上海）有限公司 | A kind of face tracking method and device |
| CN106920310A (en) * | 2017-03-06 | 2017-07-04 | 珠海习悦信息技术有限公司 | Access control method, apparatus and system |
| CN107123117A (en) * | 2017-04-26 | 2017-09-01 | 广东工业大学 | A kind of IC pin quality of welding spot detection method and device based on deep learning |
| CN107123117B (en) * | 2017-04-26 | 2020-10-20 | 广东工业大学 | IC pin welding spot quality detection method and device based on deep learning |
| CN107153820A (en) * | 2017-05-10 | 2017-09-12 | 电子科技大学 | A kind of recognition of face and movement locus method of discrimination towards strong noise |
| CN110869937A (en) * | 2017-07-21 | 2020-03-06 | 北京市商汤科技开发有限公司 | Face image duplication removal method and apparatus, electronic device, storage medium, and program |
| CN109387521A (en) * | 2017-08-04 | 2019-02-26 | 欧姆龙株式会社 | Image processing system |
| US10885620B2 (en) | 2017-08-04 | 2021-01-05 | Omron Corporation | Neural network image processing system |
| WO2019037346A1 (en) * | 2017-08-25 | 2019-02-28 | 广州视源电子科技股份有限公司 | Method and device for optimizing human face picture quality evaluation model |
| CN107704809A (en) * | 2017-09-11 | 2018-02-16 | 安徽慧视金瞳科技有限公司 | Based on interference characteristic vector data collection 1 than N face feature vector comparison methods |
| CN107644209A (en) * | 2017-09-21 | 2018-01-30 | 百度在线网络技术（北京）有限公司 | Method for detecting human face and device |
| CN108229297A (en) * | 2017-09-30 | 2018-06-29 | 深圳市商汤科技有限公司 | Face identification method and device, electronic equipment, computer storage media |
| CN108229297B (en) * | 2017-09-30 | 2020-06-05 | 深圳市商汤科技有限公司 | Face recognition method and device, electronic equipment and computer storage medium |
| CN109671241A (en) * | 2017-10-16 | 2019-04-23 | 中国电信股份有限公司 | Alarm method and system |
| CN108875502B (en) * | 2017-11-07 | 2021-11-16 | 北京旷视科技有限公司 | Face recognition method and device |
| CN108875502A (en) * | 2017-11-07 | 2018-11-23 | 北京旷视科技有限公司 | Face identification method and device |
| CN107958215A (en) * | 2017-11-23 | 2018-04-24 | 深圳市分期乐网络科技有限公司 | A kind of antifraud recognition methods, device, server and storage medium |
| CN108154085B (en) * | 2017-12-06 | 2022-02-18 | 北京顺源开华科技有限公司 | Method and device for identity recognition based on electrocardiogram data and electronic equipment |
| CN108154085A (en) * | 2017-12-06 | 2018-06-12 | 北京顺源开华科技有限公司 | The method, apparatus and electronic equipment of identification are carried out based on electrocardiogram (ECG) data |
| CN108197628B (en) * | 2017-12-07 | 2021-06-18 | 上海为森车载传感技术有限公司 | Image feature joint judgment method based on deep neural network |
| CN108197628A (en) * | 2017-12-07 | 2018-06-22 | 维森软件技术（上海）有限公司 | The joint judgment method of characteristics of image based on deep neural network |
| CN108171158A (en) * | 2017-12-27 | 2018-06-15 | 北京迈格威科技有限公司 | Biopsy method, device, electronic equipment and storage medium |
| CN108171158B (en) * | 2017-12-27 | 2022-05-17 | 北京迈格威科技有限公司 | Living body detection method, living body detection device, electronic apparatus, and storage medium |
| CN108734673A (en) * | 2018-04-20 | 2018-11-02 | 平安科技（深圳）有限公司 | Descreening systematic training method, descreening method, apparatus, equipment and medium |
| CN108921008A (en) * | 2018-05-14 | 2018-11-30 | 深圳市商汤科技有限公司 | Portrait identification method, device and electronic equipment |
| CN109036575A (en) * | 2018-07-13 | 2018-12-18 | 希蓝科技（北京）有限公司 | A kind of data processing method and device |
| CN109472292A (en) * | 2018-10-11 | 2019-03-15 | 平安科技（深圳）有限公司 | A kind of sensibility classification method of image, storage medium and server |
| CN109961000A (en) * | 2018-10-22 | 2019-07-02 | 大连艾米移动科技有限公司 | A kind of intelligence examination hall anti-cheating system |
| CN109583348A (en) * | 2018-11-22 | 2019-04-05 | 阿里巴巴集团控股有限公司 | A kind of face identification method, device, equipment and system |
| CN109583387A (en) * | 2018-11-30 | 2019-04-05 | 龙马智芯（珠海横琴）科技有限公司 | Identity identifying method and device |
| CN109615750A (en) * | 2018-12-29 | 2019-04-12 | 深圳市多度科技有限公司 | The recognition of face control method and device of door access machine, access control equipment, storage medium |
| CN109800707A (en) * | 2019-01-17 | 2019-05-24 | 中控智慧科技股份有限公司 | A kind of face identification method based on CNN model, device and storage medium |
| CN111860066A (en) * | 2019-04-30 | 2020-10-30 | 百度时代网络技术（北京）有限公司 | Face recognition method and device |
| CN111860066B (en) * | 2019-04-30 | 2023-10-27 | 百度时代网络技术（北京）有限公司 | Face recognition method and device |
| CN110688941A (en) * | 2019-09-25 | 2020-01-14 | 支付宝(杭州)信息技术有限公司 | Face image recognition method and device |
| CN111368622B (en) * | 2019-10-18 | 2024-01-12 | 杭州海康威视系统技术有限公司 | Personnel identification method and device and storage medium |
| CN111368622A (en) * | 2019-10-18 | 2020-07-03 | 杭州海康威视系统技术有限公司 | Personnel identification method and device, and storage medium |
| CN110826525B (en) * | 2019-11-18 | 2023-05-26 | 天津高创安邦技术有限公司 | Face recognition method and system |
| CN110826525A (en) * | 2019-11-18 | 2020-02-21 | 天津高创安邦技术有限公司 | Face recognition method and system |
| CN111191563A (en) * | 2019-12-26 | 2020-05-22 | 三盟科技股份有限公司 | Face recognition method and system based on data sample and test data set training |
| CN111325240A (en) * | 2020-01-23 | 2020-06-23 | 杭州睿琪软件有限公司 | Weed-related computer-executable method and computer system |
| CN111368101A (en) * | 2020-03-05 | 2020-07-03 | 腾讯科技（深圳）有限公司 | Multimedia resource information display method, device, equipment and storage medium |
| CN111368101B (en) * | 2020-03-05 | 2021-06-18 | 腾讯科技（深圳）有限公司 | Multimedia resource information display method, device, equipment and storage medium |
| CN112084903A (en) * | 2020-08-26 | 2020-12-15 | 武汉普利商用机器有限公司 | Method and system for updating face recognition base photo |
| CN112101215A (en) * | 2020-09-15 | 2020-12-18 | Oppo广东移动通信有限公司 | Face input method, terminal equipment and computer readable storage medium |
| CN112699803A (en) * | 2020-12-31 | 2021-04-23 | 竹间智能科技（上海）有限公司 | Face recognition method, system, device and readable storage medium |
| CN112699803B (en) * | 2020-12-31 | 2024-01-16 | 竹间智能科技（上海）有限公司 | Face recognition method, system, equipment and readable storage medium |
| CN115880761A (en) * | 2023-02-09 | 2023-03-31 | 数据空间研究院 | Face recognition method, system, storage medium and application based on strategy optimization |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106203333A (en) | Face identification method and system | |
| CN108182394B (en) | Convolutional neural network training method, face recognition method and face recognition device | |
| US8832124B2 (en) | Biometric matching engine | |
| WO2021139324A1 (en) | Image recognition method and apparatus, computer-readable storage medium and electronic device | |
| CN108229335A (en) | It is associated with face identification method and device, electronic equipment, storage medium, program | |
| CN106203387A (en) | Face verification method and system | |
| JP7058665B2 (en) | Methods and devices for user authentication based on feature information | |
| CN113128478B (en) | Model training method, pedestrian analysis method, device, equipment and storage medium | |
| CN113761261A (en) | Image retrieval method, image retrieval device, computer-readable medium and electronic equipment | |
| KR102593835B1 (en) | Face recognition technology based on heuristic Gaussian cloud transformation | |
| CN107871103B (en) | Face authentication method and device | |
| CN106295501A (en) | The degree of depth based on lip movement study personal identification method | |
| CN107679457A (en) | User identity method of calibration and device | |
| CN110298240A (en) | A kind of user vehicle recognition methods, device, system and storage medium | |
| KR20220076398A (en) | Object recognition processing apparatus and method for ar device | |
| KR20210033940A (en) | How to Train Neural Networks for Human Facial Recognition | |
| CN111177469A (en) | Face retrieval method and face retrieval device | |
| Haji et al. | Real time face recognition system (RTFRS) | |
| CN111667275A (en) | User identity identification method, device, equipment and medium thereof | |
| CN112634158A (en) | Face image recovery method and device, computer equipment and storage medium | |
| Takemura et al. | Model extraction attacks on recurrent neural networks | |
| CN111291780A (en) | Cross-domain network training and image recognition method | |
| WO2022217784A1 (en) | Data processing methods and apparatus, device, and medium | |
| CN115035608A (en) | Living body detection method, device, equipment and system | |
| CN110263196B (en) | Image retrieval method, image retrieval device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20161207 |