CN107609508A - A kind of face identification method, terminal and computer-readable recording medium - Google Patents
A kind of face identification method, terminal and computer-readable recording medium Download PDFInfo
- Publication number
- CN107609508A CN107609508A CN201710807664.2A CN201710807664A CN107609508A CN 107609508 A CN107609508 A CN 107609508A CN 201710807664 A CN201710807664 A CN 201710807664A CN 107609508 A CN107609508 A CN 107609508A
- Authority
- CN
- China
- Prior art keywords
- face
- image
- face characteristic
- facial image
- identified
- 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.)
- Withdrawn
Links
Abstract
The embodiment of the invention discloses a kind of face identification method, terminal and computer-readable recording medium, wherein, face identification method includes:Obtain the first face characteristic corresponding to face to be identified;If the second face characteristic data to match with the first face characteristic are included in default facial feature database, the second face characteristic data are then identified as to target face characteristic to be identified, the pixel of facial image corresponding to the second face characteristic data is higher than the pixel of facial image corresponding to the first face characteristic;If it is identified as recognition of face success comprising the face characteristic data to match with the target face characteristic in registered face information.Because face characteristic data are as target face characteristic to be identified corresponding to the facial image using higher pixel, so as to improve the accuracy rate of recognition of face.
Description
Technical field
The present invention relates to electronic technology field, more particularly to a kind of face identification method, terminal and computer-readable storage
Medium.
Background technology
Face recognition technology is that one kind develops biometrics identification technology earlier, the face feature letter that it can be based on people
Breath carries out authentication to people.At present, face recognition technology is in safe access control, visual monitoring, the image inspection based on content
The application value in the field such as rope and man-machine interface of new generation is increasing, therefore, improve the accuracy rate of recognition of face increasingly by
The attention of researcher.And the factor for influenceing face recognition accuracy rate includes but is not limited to face recognition algorithms, picture quality, data
Storehouse etc..Exemplified by face recognition technology is applied into the unblock of intelligent terminal, when the facial image that intelligent terminal is captured
When picture quality is relatively low, the accuracy rate of recognition of face can be caused to reduce, so that the accuracy of terminal unlocking.
The content of the invention
The embodiment of the present invention provides a kind of face identification method, terminal and computer-readable recording medium, it is possible to increase people
The accuracy rate of face identification.
In a first aspect, the embodiments of the invention provide a kind of face identification method, the face identification method includes:
Obtain the first face characteristic corresponding to face to be identified;
It is special that if the second face to match with the first face characteristic is included in default facial feature database
Data are levied, then the second face characteristic data are identified as to target face characteristic to be identified;Wherein, second people
The pixel of facial image corresponding to face characteristic is higher than the pixel of facial image corresponding to the first face characteristic;
If including the face characteristic data to match with the target face characteristic in registered face information,
It is identified as recognition of face success.
Second aspect, the embodiments of the invention provide a kind of terminal, the terminal includes being used to perform above-mentioned first aspect
The unit of method.
The third aspect, the embodiments of the invention provide another terminal, including processor, input equipment, output equipment and
Memory, the processor, input equipment, output equipment and memory are connected with each other, wherein, the memory is used to store branch
The computer program that terminal performs the above method is held, the computer program includes programmed instruction, and the processor is configured to use
In calling described program instruction, the method for performing above-mentioned first aspect.
Fourth aspect, the embodiments of the invention provide a kind of computer-readable recording medium, the computer-readable storage medium
Computer program is stored with, the computer program includes programmed instruction, and described program instruction makes institute when being executed by a processor
The method for stating the above-mentioned first aspect of computing device.
The embodiment of the present invention is by obtaining the first face characteristic corresponding to face to be identified;If default face is special
Comprising the second face characteristic data to match with the first face characteristic in sign database, then by second face
Characteristic is identified as target face characteristic to be identified;Wherein, face figure corresponding to the second face characteristic data
As pixel higher than facial image corresponding to the first face characteristic pixel;If included in registered face information
The face characteristic data to match with the target face characteristic, then it is identified as recognition of face success.Terminal is used with treating
Face characteristic data corresponding to the facial image for the higher pixel that the face of identification matches carry out recognition of face, so as to improve
The accuracy rate of recognition of face.
Brief description of the drawings
Technical scheme in order to illustrate the embodiments of the present invention more clearly, it is required in being described below to embodiment to use
Accompanying drawing is briefly described, it should be apparent that, drawings in the following description are some embodiments of the present invention, general for this area
For logical technical staff, on the premise of not paying creative work, other accompanying drawings can also be obtained according to these accompanying drawings.
Fig. 1 is a kind of schematic flow diagram of face identification method provided in an embodiment of the present invention;
Fig. 2 is a kind of schematic flow diagram for face identification method that another embodiment of the present invention provides;
Fig. 3 is a kind of schematic block diagram of terminal provided in an embodiment of the present invention;
Fig. 4 is a kind of schematic block diagram for terminal that another embodiment of the present invention provides;
Fig. 5 is a kind of schematic block diagram for terminal that yet another embodiment of the invention provides.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is part of the embodiment of the present invention, rather than whole embodiments.Based on this hair
Embodiment in bright, the every other implementation that those of ordinary skill in the art are obtained under the premise of creative work is not made
Example, belongs to the scope of protection of the invention.
It should be appreciated that ought be in this specification and in the appended claims in use, term " comprising " and "comprising" instruction
Described feature, entirety, step, operation, the presence of element and/or component, but it is not precluded from one or more of the other feature, whole
Body, step, operation, element, component and/or its presence or addition for gathering.
It is also understood that the term used in this description of the invention is merely for the sake of the mesh for describing specific embodiment
And be not intended to limit the present invention.As used in description of the invention and appended claims, unless on
Other situations are hereafter clearly indicated, otherwise " one " of singulative, "one" and "the" are intended to include plural form.
It will be further appreciated that the term "and/or" used in description of the invention and appended claims is
Refer to any combinations of one or more of the associated item listed and be possible to combine, and including these combinations.
As used in this specification and in the appended claims, term " if " can be according to context quilt
Be construed to " when ... " or " once " or " in response to determining " or " in response to detecting ".Similarly, phrase " if it is determined that " or
" if detecting [described condition or event] " can be interpreted to mean according to context " once it is determined that " or " in response to true
It is fixed " or " once detecting [described condition or event] " or " in response to detecting [described condition or event] ".
In the specific implementation, the terminal described in the embodiment of the present invention is including but not limited to such as with touch sensitive surface
The mobile phone, laptop computer or tablet PC of (for example, touch-screen display and/or touch pad) etc it is other just
Portable device.It is to be further understood that in certain embodiments, the equipment is not portable communication device, but with tactile
Touch the desktop computer of sensing surface (for example, touch-screen display and/or touch pad).
In discussion below, the terminal including display and touch sensitive surface is described.It is, however, to be understood that
It is that terminal can include one or more of the other physical user-interface device of such as physical keyboard, mouse and/or control-rod.
Terminal supports various application programs, such as one or more of following:Drawing application program, demonstration application journey
Sequence, word-processing application, website create application program, disk imprinting application program, spreadsheet applications, game application
Program, telephony application, videoconference application, email application, instant messaging applications, exercise
Support application program, photo management application program, digital camera application program, digital camera application program, web-browsing application
Program, digital music player application and/or video frequency player application program.
The various application programs that can be performed in terminal can use at least one public of such as touch sensitive surface
Physical user-interface device.It can adjust and/or change among applications and/or in corresponding application programs and touch sensitive table
The corresponding information shown in the one or more functions and terminal in face.So, the public physical structure of terminal is (for example, touch quick
Sense surface) the various application programs with user interface directly perceived and transparent for a user can be supported.
Referring to Fig. 1, Fig. 1 is a kind of schematic flow diagram of face identification method provided in an embodiment of the present invention.The present embodiment
The executive agent of middle face identification method is terminal.Terminal can be the mobile terminals such as mobile phone, tablet personal computer, but be not limited to
This, can also be other-end.Face identification method in the present embodiment can be applied to the unlocking screen or payment cipher of terminal
The scenes such as checking, it can be also used for other any required scenes that proof of identity is carried out by face information.People as shown in Figure 1
Face recognition method may comprise steps of:
S101:Obtain the first face characteristic corresponding to face to be identified.
During terminal normal work, if receiving default recognition of face instruction, the is obtained corresponding to face to be identified
One face characteristic data.Wherein, face to be identified is face corresponding to the user of current operation control terminal.
Terminal receives default recognition of face instruction and includes but is not limited to following two scenes:
Scene one:When the unlocking manner of terminal is arranged to face unblock by user, i.e. user is by the unlocking pin of terminal
When being arranged to face information, default recognition of face instruction can be for the unlock instruction of terminal screen or for predetermined encryption
The unlock instruction of application.If terminal is received for the unlock instruction of terminal screen or referred to for the unblock of predetermined encryption application
Order, then it is identified as receiving default recognition of face instruction.
The unlock instruction that terminal receives for terminal screen can be that terminal detects the default unblock behaviour of user's triggering
Make, such as detect that user presses default release tab (such as power key).If terminal detects that user triggers default solution
Lock operation, then be identified as receiving the unlock instruction for terminal screen, that is, is identified as receiving default recognition of face instruction.
Terminal receives the unlock instruction applied for predetermined encryption, and terminal detects that user clicks on predetermined encryption
The application icon of application.Wherein, predetermined encryption applies the application being encrypted for user beforehand through face information, predetermined encryption
Using can be configured according to the actual requirements by user.If terminal detects that user clicks on the application drawing of predetermined encryption application
Mark, then it is identified as receiving the unlock instruction for default application, that is, is identified as receiving default recognition of face instruction.
Scene two:When user will can be used for electronics corresponding to the application (application, APP) of e-payment in terminal
When payment cipher is arranged to face information, default recognition of face instruction can be that the payment cipher operated for e-payment is tested
Card instruction.If terminal receives the payment cipher checking instruction for e-payment operation, it is identified as receiving default people
Face identification instruction.
It can be that terminal detects that user clicks on that terminal, which receives the payment cipher checking instruction operated for e-payment,
The confirmation payment options of payment interface.If terminal detects that user clicks on the confirmation payment options of payment interface, it is identified as connecing
The payment cipher checking instruction for e-payment operation is received, that is, is identified as receiving default recognition of face instruction.
In the present embodiment, terminal is provided with front camera and rear camera, before the pixel of rear camera is higher than
Put the pixel of camera.And operated for the ease of user, when terminal receives default recognition of face instruction, it can start preposition
Camera captures facial image or video corresponding to face (face of the user of current operation control terminal) to be identified.
Terminal extracts the first face characteristic corresponding to face to be identified from the facial image or video captured.
It is understood that can to extract its from the facial image or video captured using existing face recognition algorithms right for terminal
Existing face recognition algorithms are no longer repeated by the first face characteristic answered herein.
S102:If the second people to match with the first face characteristic is included in default facial feature database
Face characteristic, then the second face characteristic data are identified as to target face characteristic to be identified.
After terminal gets the first face characteristic corresponding to face to be identified, default face characteristic data are detected
Whether the face characteristic data to match with the first face characteristic are included in storehouse.Wherein, default facial feature database
In be stored with face characteristic data corresponding to the face of at least one people.Can only it be stored in i.e. default facial feature database
Face characteristic data corresponding to the face of one people, the face that can also store two or more different peoples are each self-corresponding
Face characteristic data, are not limited herein.
The face characteristic data stored in default facial feature database can be from face corresponding to corresponding face
Obtained in image.It should be noted that in the present embodiment, it is special as the face stored in default facial feature database
The pixel for levying the facial image in the source of data is higher than the pixel of facial image corresponding to the first face characteristic, i.e., default
The pixel of each self-corresponding facial image of face characteristic data stored in facial feature database is higher than the first face characteristic
The pixel of facial image corresponding to data.
It is understood that in actual applications, pass through the pixel of the facial image captured by the rear camera of terminal
Far above the pixel of the facial image captured by the front camera by terminal, and pass through the face captured by rear camera
Face location in image is generally relatively rectified.And for recognition of face, pixel is high and face location is proper face figure
As more human face characteristic points can be extracted.By the image captured by the front camera or rear camera of terminal or regard
Frequency generally default storage is in this map office of terminal, and that stored in this map office of terminal is terminal user mostly
Image, or some understanding people image.It is therefore possible to use what is stored in terminal local image passes through rear camera
Source of the facial image of shooting as the face characteristic data stored in default facial feature database.
Specifically, before recognition of face is carried out, terminal can beforehand through face recognition technology from this map office
Screening includes the facial image of individual human face in one image set.Wherein, first image set of this map office passes through end for storage
Image captured by the rear camera at end.The facial image for including individual human face that terminal is filtered out from the first image set
It can be one, or at least two.When the facial image comprising individual human face filtered out is at least two, this is extremely
Few two facial images comprising individual human face can correspond to the face of same person, can also correspond to the face of different people, this
Place is not limited.
After terminal filters out the facial image comprising individual human face from the first image set, the facial image that will be filtered out
It is divided at least one image subset.Specifically, facial image corresponding to same person is divided into same image by terminal
Concentrate, facial image corresponding to different people is divided into different image subsets.That is, what same image subset included
Face images correspond to same face, and the facial image that different images subset includes corresponds to different faces.Wherein, each image
An at least facial image is included in subset.For each image subset, terminal can be according to institute in the image subset
There are face characteristic data corresponding to facial image to determine face characteristic data corresponding to the image subset.And all image subsets are each
Self-corresponding face characteristic data constitute default facial feature database.Because the facial image in each image subset is equal
It is to be shot by the rear camera of terminal, therefore, compared to by corresponding to the facial image captured by front camera
For first face characteristic, the human face characteristic point that face characteristic data corresponding to each image subset are included is more complete
With it is clear.
, can be by the first face characteristic after terminal gets the first face characteristic corresponding to face to be identified
Contrasted one by one with all face characteristics stored in default facial feature database.If terminal detects default
It is comprising the second face characteristic data to match with the first face characteristic in facial feature database, then the second face is special
Sign data are identified as target face characteristic to be identified, i.e., terminal using the second face characteristic data as with registered people
The target face characteristic that face information is compared, by the way that target face characteristic and registered face information are carried out
Compare, so as to realize the proof of identity to active user.Second face characteristic data refer specifically to fisrt feature data match,
The matching degree of second face characteristic data and the first face characteristic is more than the first preset matching degree threshold value.Wherein, first is pre-
If matching degree threshold value can be configured according to the actual requirements, it is not limited herein.For example, the first preset matching degree threshold value can be with
For 80%.
Because the pixel of the facial image captured by the front camera by terminal is relatively low, therefore, to active user
When carrying out recognition of face, if directly can as target facial image to be identified using the facial image captured by front camera
Can be relatively low due to pixel and reduce the accuracy rate of recognition of face.And in the present embodiment, due to the second face characteristic data pair
The pixel for the facial image answered is higher than the pixel of facial image corresponding to the first face characteristic, therefore, by by the second people
Face characteristic is compared as target face characteristic to be identified with registered face information, it is possible to increase face
The accuracy rate of identification.
It should be noted that before registered face information carries out proof of identity for user by face information, at end
Hold the benchmark face information for being used to carry out user proof of identity registered in advance.Registered face information can only include one
Face characteristic data corresponding to personal face, each self-corresponding face characteristic number of face of at least two people can also be included
According to not being limited herein.
Terminal can be carried out target face characteristic and registered face information comprising all face characteristics
Contrast one by one, so as to realize the verification to current user identities.
S103:If the face characteristic number to match with the target face characteristic is included in registered face information
According to, then be identified as recognition of face success.
If terminal is detected in registered face information comprising the face characteristic to match with target face characteristic
Data, then it is identified as recognition of face success.Recognition of face success then illustrates that face to be identified registered in advance is (current in terminal
The face of the user of operation control terminal) corresponding to face information, that is, illustrate active user for authorized user.In recognition of face success
Afterwards, terminal can perform current face and identify unblock operation or delivery operation etc. corresponding to operation.
It is used to identify with target face characteristic with the face characteristic data that target face characteristic matches
Face characteristic data with degree more than the second preset matching degree threshold value.If terminal detect in registered face information include with
The matching degree of target face characteristic is more than the face characteristic data of the second preset matching degree threshold value, then is identified as recognition of face
Success.Wherein, the second preset matching degree threshold value can be configured according to the actual requirements, be not limited herein.For example, second is pre-
If matching degree threshold value can be 95%.
Do not include and target face characteristic phase it is understood that if terminal is detected in registered face information
The face characteristic data of matching, then it is identified as recognition of face failure.Recognition of face failure then illustrate in terminal it is not registered in advance with
Face information corresponding to face (face of the user of current operation control terminal) to be identified, that is, illustrate that active user uses for unauthorized
Family.After recognition of face failure, terminal can not perform current face and identify unblock operation or delivery operation etc. corresponding to operation;
Or terminal can be with output error prompt message, to prompt the proof of identity for active user to fail.
Such scheme, terminal obtain the first face characteristic corresponding to face to be identified;If default face characteristic
It is comprising the second face characteristic data to match with the first face characteristic in database, then second face is special
Sign data are identified as target face characteristic to be identified;The pixel of facial image corresponding to the second face characteristic data
Higher than the pixel of facial image corresponding to the first face characteristic;If included and the mesh in registered face information
The face characteristic data of face characteristic data match are marked, then are identified as recognition of face success.Terminal uses and people to be identified
Face characteristic data corresponding to the facial image for the higher pixel that face matches carry out recognition of face, so as to improve recognition of face
Accuracy rate.
Referring to Fig. 2, Fig. 2 is a kind of schematic flow diagram for face identification method that another embodiment of the present invention provides.This reality
The executive agent for applying face identification method in example is terminal.Terminal can be the mobile terminals such as mobile phone, tablet personal computer, but and unlimited
Can also be other-end in this.Face identification method in the present embodiment can be applied to the unlocking screen of terminal or pay close
The scenes such as code checking, it can be also used for other any required scenes that proof of identity is carried out by face information.As shown in Figure 2
Face identification method may comprise steps of:
S201:Obtain third party's face characteristic corresponding to face to be registered.
In the present embodiment, if user needs to use the face identification functions of terminal to carry out authority to the user of operation control terminal
Control, then user can register in the terminal in advance believes for carrying out the benchmark face of proof of identity to the user of operation control terminal
Breath.If terminal receives default face information register instruction, third party's face characteristic corresponding to face to be registered is obtained
According to.
Terminal receives default face information register instruction, and terminal detects that user triggers face information and set
The option of the addition face information at interface.I.e. if terminal detects that user triggers the choosing of the addition face information at face information interface
Select, be then identified as receiving default face information register instruction.
Operated in order to facilitate user, when terminal receives default face information register instruction, preposition shooting can be started
Head captures facial image or video corresponding to face (face of the user of current operation control terminal) to be registered.Terminal can be from catching
Third party's face characteristic corresponding to face to be registered is extracted in the facial image or video that receive.It is understood that eventually
It is special that end can extract its corresponding third party's face using existing face recognition algorithms from the facial image or video captured
Data are levied, no longer existing face recognition algorithms are repeated herein.
Preferably, terminal can also export the second prompt message while facial image is captured by front camera.
Second prompt message is used to prompt user to ajust head.
, can be directly by third party's face feature after terminal gets third party's face characteristic corresponding to face to be registered
Data register is face information corresponding to face to be registered.Because facial image corresponding to third party's face characteristic is to pass through
The front camera capture of terminal, and the pixel of the facial image captured by front camera is relatively low, therefore, the 3rd
The human face characteristic point that face characteristic data are included may be imperfect.If directly using third party's face characteristic as to be registered
Face information corresponding to face, then the accuracy rate of recognition of face is may result in follow-up face recognition process to be reduced.
Therefore, in order to improve the accuracy rate of recognition of face, in registered face information, terminal can be according to third party's face characteristic
Face to be registered matches the facial image of higher pixel.It is for example, special getting third party's face corresponding to face to be registered
After levying data, terminal can detect in default facial feature database whether include what is matched with third party's face characteristic
Face characteristic data.For example, terminal can be by included in third party's face characteristic and default facial feature database
Whether face characteristic data are contrasted one by one, and detect in default facial feature database and include and third party's face characteristic
According to matching degree be more than the 3rd preset matching degree threshold value face characteristic data.If terminal detects default face characteristic data
The matching degree of the 4th face characteristic data and third party's face characteristic in storehouse is more than the face of the 3rd preset matching degree threshold value
Characteristic, then it is identified as in default facial feature database comprising the face characteristic to match with third party's face characteristic
Data.Wherein, the 3rd preset matching degree threshold value can be configured according to the actual requirements, is not limited herein.For example, the 3rd is pre-
If matching degree threshold value can be 70%.
If terminal is detected in default facial feature database comprising the 4th to match with third party's face characteristic
Face characteristic data, then perform step S2021.Do not include if terminal detects in default facial feature database and the third party
The 4th face characteristic data that face characteristic matches, then perform step S2022.
Wherein, the face characteristic data stored in default facial feature database can be from corresponding to corresponding face
Obtained in facial image.It should be noted that in the present embodiment, as the people stored in default facial feature database
The pixel of the facial image in the source of face characteristic is higher than the pixel of facial image corresponding to third party's face characteristic, i.e., pre-
If facial feature database in the pixel of each self-corresponding facial image of face characteristic data that is stored be higher than third party's face
The pixel of facial image corresponding to characteristic.
It is understood that in actual applications, pass through the pixel of the facial image captured by the rear camera of terminal
Far above the pixel of the facial image captured by the front camera by terminal, and pass through the face captured by rear camera
Face location in image is generally relatively rectified.And for recognition of face, pixel is high and face location is proper face figure
As more human face characteristic points can be extracted.By the image captured by the front camera or rear camera of terminal or regard
Frequency generally default storage is in this map office of terminal, and that stored in this map office of terminal is terminal user mostly
Image, or some understanding people image.It is therefore possible to use what is stored in terminal local image passes through rear camera
Source of the facial image of shooting as the face characteristic data stored in default facial feature database.
Further, before step S201, face identification method can also comprise the following steps:
Screening includes the facial image of individual human face from first image set of this map office, and will be by described comprising single
The image set that the facial image of face is formed is identified as the second image set;Wherein, the pixel for the image that described first image is concentrated
Higher than the pixel of facial image corresponding to the first face characteristic;
Recognition of face is carried out to the facial image in second image set, and according to face recognition result by described second
Image set is divided at least one image subset;
Each self-corresponding face characteristic data of facial image in described image subset, determine described image subset pair
The face characteristic data answered;
The default face characteristic data are generated according to each self-corresponding face characteristic data of all described image subsets
Storehouse.
Before face information registration is carried out, the first figure that terminal can be beforehand through face recognition technology from this map office
Screening includes the facial image of individual human face, and the image that the facial image comprising individual human face filtered out is formed in image set
Collection is identified as the second image set.Wherein, first image set of this map office is used to store and clapped by the rear camera of terminal
The image taken the photograph.It is understood that the facial image that user is downloaded by network can also be stored in the first image set, only need to protect
The pixel for the facial image that card is downloaded by network is higher than by the pixel of the facial image captured by terminal front camera
Can.
The facial image included in second image set can be one, or at least two.When in the second image set
Comprising facial image be at least two when, at least two facial images can correspond to the face of same person for this, can also be right
The face of different people is answered, is not limited herein.
, can be to every facial image in the second image set after terminal filters out the second image set from the first image set
Recognition of face is carried out, and the second image set is divided into by least one image subset according to face recognition result.Specifically, terminal
Facial image corresponding to same person is divided into same image subset, facial image corresponding to different people is divided into not
In same image subset.That is, the face images that same image subset includes correspond to same face, different images
Collect the facial image included and correspond to different faces.Wherein, an at least facial image is included in each image subset.For each
For individual image subset, terminal can determine according to each self-corresponding face characteristic data of the facial image in the image subset should
Face characteristic data corresponding to image subset.And all each self-corresponding face characteristic data of image subset constitute default people
Face property data base.Because the facial image in each image subset is shot by the rear camera of terminal, therefore,
Compared to by corresponding to the facial image captured by front camera for third party's face characteristic, each image subset pair
The human face characteristic point that the face characteristic data answered are included is more complete and clear.
Further, screening includes the facial image of individual human face from first image set of this map office, and will be by institute
State the image set that the facial image comprising individual human face is formed and be identified as the second image set, may comprise steps of:
Face figure of the screening image storage time in preset period of time and comprising individual human face is concentrated from described first image
Picture, and will be identified as by the described image storage time image set that the facial image comprising individual human face is formed in preset period of time
Second image set.
In the present embodiment, in order to ensure the timeliness of face characteristic data stored in default facial feature database
Property, further to improve the accuracy rate of recognition of face, terminal from the first image set screening include the face figure of individual human face
During picture, recent facial image can be only screened.I.e. terminal can screen image storage time default from the first image set
In period and the facial image comprising individual human face.Wherein, preset period of time can be configured according to the actual requirements, not done herein
Limitation.For example, it is assumed that this year is 2017, then preset period of time can be for 2016 so far, i.e., terminal is only from the first image set
Screening image storage time is more than or equal to 2016 and the facial image comprising individual human face.Terminal will be from the first image set
The image storage time filtered out the image set that the facial image comprising individual human face is formed in preset period of time is identified as second
Image set.
It is understood that each self-corresponding face of image subset that terminal can also include to the second image set in real time is special
Sign data are updated.Specifically, terminal can detect in real time whether have in the first image set it is newly-increased comprising individual human face
Facial image, if the first image is concentrated with the newly-increased facial image for including individual human face, individual human face is included to newly-increased
Facial image be identified, and detect the second image set in whether there is and the newly-increased facial image phase comprising individual human face
The image subset of matching.If image to match with the newly-increased facial image comprising individual human face in the second image set be present
Collection, then newly-increased facial image is added in the image subset to match with it;If it is not present in the second image set with increasing newly
The image subset that matches of the facial image comprising individual human face, then terminal can in the second image set a newly-built image
Subset stores newly-increased facial image.If terminal is updated to a certain image subset in the second image set, basis
Image subset after renewal redefines face characteristic data corresponding to the image subset.
Each self-corresponding face of image subset that terminal can also include according to default time interval to the second image set
Characteristic is updated.Specific update mode is same as above, and here is omitted.Wherein, default time interval can be according to reality
Border demand is configured.For example, default time interval can be 2 days, terminal was every 2 days images included to the second image set
Each self-corresponding face characteristic data of subset are once updated.
Further, each self-corresponding face characteristic data of facial image in described image subset, it is determined that described
Face characteristic data corresponding to image subset, may comprise steps of:
The facial image that described image subset includes is extracted in the facial image included from described image subset each to correspond to
Human face characteristic point;
According to the human face characteristic point extracted, described image subset is screened in the facial image included from described image subset
Corresponding target facial image;Wherein, the quantity of human face characteristic point corresponding to the target facial image is more than default characteristic point
Threshold value;
The human face characteristic point of target facial image corresponding to described image subset is integrated, and by the face after integration
Feature point recognition is face characteristic data corresponding to described image subset.
In the present embodiment, for an image subset, although the facial image in same image subset is corresponding
The face of same person, but due to the influence of face location in facial image or light etc., every face in the image subset
Image can not possibly be identical, therefore, the human face characteristic point extracted in the every facial image included from image subset
Quantity is typically different.Terminal determines the image in each self-corresponding face characteristic data of the facial image in the image subset
Corresponding to subset during face characteristic data, each self-corresponding people of face images that the image subset includes can be extracted respectively
Face characteristic point, and human face characteristic point corresponding to face images is integrated, it is special to obtain face corresponding to the image subset
Levy data.
It is understood that in order to improve the data-handling efficiency of terminal, terminal can be from the people that image subset is included
The quantity that human face characteristic point is filtered out in face image is more than the facial image of default characteristic point threshold value, and by the number of human face characteristic point
Amount be more than the facial image of default characteristic point threshold value corresponding to human face characteristic point integrated, and by the human face characteristic point after integration
It is identified as face characteristic data corresponding to the image subset.Wherein, presetting characteristic point threshold value can be set according to the actual requirements
Put, be not limited herein.
Preferably, in order that the accuracy rate of recognition of face is higher, if the face in facial image can be divided into by terminal
Dry region (such as face can be divided into 5 regions according to face), and in the facial image included from image subset
The most facial image of each region human face characteristic point is screened, each self-corresponding human face characteristic point of the image filtered out is carried out
Integrate, and the human face characteristic point after integration is identified as face characteristic data corresponding to the image subset.
Human face characteristic point corresponding to different facial images is carried out integration by terminal, and terminal is by different facial images pair
The human face characteristic point answered carries out duplicate removal superposition.
S2021:If corresponding with third party's face characteristic the is included in the default facial feature database
Four face characteristic data, then it is face information corresponding to the face to be registered by the 4th face characteristic data register.
Wherein, the pixel of facial image corresponding to the 4th face characteristic data is higher than people corresponding to third party's face characteristic
The pixel of face image.
If terminal is detected in default facial feature database comprising corresponding with third party's face characteristic the
Four face characteristic data, then it is face information corresponding to face to be registered by the 4th face characteristic data register, i.e., terminal will
4th face characteristic data are as the benchmark face information for being used to verify user identity in follow-up face recognition process.Due to the 4th
The pixel of facial image corresponding to face characteristic data is higher than the pixel of facial image corresponding to third party's face characteristic, because
This, is face information corresponding to face to be registered by the 4th face characteristic data register, can improve follow-up recognition of face
Accuracy rate.
S2022:If do not include in the default facial feature database corresponding with third party's face characteristic
Face characteristic data, then third party's face characteristic is registered as into face information corresponding to the face to be registered.
If terminal is detected in default facial feature database not comprising corresponding with third party's face characteristic
Face characteristic data, then third party's face characteristic is directly registered as into face information corresponding to face to be registered.
It is understood that terminal includes and third party's face feature in default facial feature database is detected
After 4th face characteristic data corresponding to data, the second prompt message can be exported.Second prompt message is used to prompt user
Whether it is face information corresponding to face to be registered by the 4th face characteristic data register.If terminal receives user response
Two prompt messages and the confirmation inputted, then it is that face corresponding to face to be registered is believed by the 4th face characteristic data register
Breath;If the cancellation information that terminal receives the prompt message of user response second and inputted, third party's face characteristic is registered
For face information corresponding to face to be registered.
S203:Obtain the first face characteristic corresponding to face to be identified.
After user is completed to the registration of face information, registered face information can be applied to face and unlock or prop up
Pay the scenes such as password authentification.
It should be noted that the realization of the step S102 in step S203 embodiments corresponding with Fig. 1 in the present embodiment
Mode is identical, specifically refers to the associated description of the step S102 in embodiment corresponding to Fig. 1, here is omitted.
S204:If the second people to match with the first face characteristic is included in default facial feature database
Face characteristic, then the second face characteristic data are identified as to target face characteristic to be identified.
After terminal gets the first face characteristic corresponding to face to be identified, default face characteristic data are detected
Whether the face characteristic data to match with the first face characteristic are included in storehouse.Specifically, terminal can be by the first face
Characteristic is contrasted one by one with all face characteristics stored in default facial feature database, and detection is default
Whether the people for being more than the first preset matching degree threshold value with the matching degree of the first face characteristic is included in facial feature database
Face characteristic.If terminal detects the second face characteristic data stored in default facial feature database and the first face
The matching degree of characteristic is more than the first preset matching degree threshold value, then the second face characteristic data is identified as into target to be identified
Face characteristic data, i.e. terminal are using the second face characteristic data as the target face being compared with registered face information
Characteristic, by the way that target face characteristic is compared with registered face information, so as to realize to active user
Proof of identity.Wherein, the first preset matching degree threshold value can be configured according to the actual requirements, be not limited herein.For example,
First preset matching degree threshold value can be 80%.
After terminal gets target face characteristic to be identified, can by target face characteristic with it is registered
Face information is contrasted one by one comprising all face characteristics, so as to realize the verification to current user identities.
Do not include and the first face characteristic it is understood that if terminal is detected in default facial feature database
According to the face characteristic data to match, then the first face characteristic is identified as target face characteristic to be identified by terminal.
S2051:If the face characteristic to match with the target face characteristic is included in registered face information
Data, then it is identified as recognition of face success.
It should be noted that the realization of the step S103 in step S2051 embodiments corresponding with Fig. 1 in the present embodiment
Mode is identical, specifically refers to the associated description of the step S103 in embodiment corresponding to Fig. 1, here is omitted.
S2052:If it is special not include the face to match with the target face characteristic in registered face information
Data are levied, then are identified as recognition of face failure.
If terminal detects the face spy for not including in registered face information and matching with target face characteristic
Data are levied, then are identified as recognition of face failure.Recognition of face failure then illustrates face not registered in advance and to be identified in terminal
Face information corresponding to (face of the user of current operation control terminal), that is, it is unauthorized user to illustrate active user.Know in face
Not Shi Bai after, terminal can not perform current face and identify unblock operation or delivery operation etc. corresponding to operation;Or terminal can
With output error prompt message, to prompt the proof of identity for active user to fail.
It should be noted that step arranged side by side each other step S2051 and step S2052 in the present embodiment, both regardless of
Sequencing.If terminal performs step S2051, step S2052 is no longer performed;If terminal performs step S2052, no
Step S2051 is performed again.
Such scheme, terminal obtain the first face characteristic corresponding to face to be identified;If default face characteristic
It is comprising the second face characteristic data to match with the first face characteristic in database, then second face is special
Sign data are identified as the pixel of facial image corresponding to the second face characteristic data described in target face characteristic to be identified
Higher than the pixel of facial image corresponding to the first face characteristic;If included and the mesh in registered face information
The face characteristic data of face characteristic data match are marked, then are identified as recognition of face success.Terminal uses and people to be identified
Face characteristic data corresponding to the facial image for the higher pixel that face matches carry out recognition of face, so as to improve recognition of face
Accuracy rate.
Terminal is by the corresponding face characteristic data register of the facial image of the higher pixel to match with face to be registered
For face information corresponding to face to be registered, the accuracy rate of recognition of face is further increased.
Terminal preferentially uses the image stored in this map office as the face characteristic in default facial feature database
The source of data, because what is stored in this map office is mostly the facial image of terminal user, therefore face can be improved
The reliability of identification.
Referring to Fig. 3, Fig. 3 is a kind of schematic block diagram of terminal provided in an embodiment of the present invention.Terminal 300 can be intelligence
The mobile terminals such as mobile phone, tablet personal computer.The each unit that the terminal 300 of the present embodiment includes is used to perform embodiment corresponding to Fig. 1
In each step, referring specifically to the associated description in embodiment corresponding to Fig. 1 and Fig. 1, do not repeat herein.The end of the present embodiment
End 300 includes first acquisition unit 301, the first recognition unit 302 and face identification unit 303.
First acquisition unit 301 is used to obtain the first face characteristic corresponding to face to be identified.First obtains list
Member 301 sends the first face characteristic to the first recognition unit 302.
First recognition unit 302 is used for the first face characteristic for receiving the transmission of first acquisition unit 301, if default
Comprising the second face characteristic data for matching with the first face characteristic in facial feature database, then by described the
Two face characteristic data are identified as target face characteristic to be identified;Wherein, corresponding to the second face characteristic data
The pixel of facial image is higher than the pixel of facial image corresponding to the first face characteristic.First recognition unit 302 will
Target face characteristic is sent to face identification unit 303.
Face identification unit 303 is used to receive the target face characteristic that the first recognition unit 302 is sent, if registered
Face information in comprising the face characteristic data that match with the target face characteristic, then be identified as recognition of face into
Work(.
Such scheme, terminal obtain the first face characteristic corresponding to face to be identified;If default face characteristic
It is comprising the second face characteristic data to match with the first face characteristic in database, then second face is special
Sign data are identified as target face characteristic to be identified;The pixel of facial image corresponding to the second face characteristic data
Higher than the pixel of facial image corresponding to the first face characteristic;If included and the mesh in registered face information
The face characteristic data of face characteristic data match are marked, then are identified as recognition of face success.Terminal uses and people to be identified
Face characteristic data corresponding to the facial image for the higher pixel that face matches carry out recognition of face, so as to improve recognition of face
Accuracy rate.
Referring to Fig. 4, Fig. 4 is a kind of schematic block diagram for terminal that another embodiment of the present invention provides.Terminal 400 can be
The mobile terminals such as smart mobile phone, tablet personal computer.The each unit that the terminal 400 of the present embodiment includes is used to perform real corresponding to Fig. 2
Each step in example is applied, referring specifically to the associated description in embodiment corresponding to Fig. 2 and Fig. 2, is not repeated herein.The present embodiment
Terminal 400 include first acquisition unit 401, the first recognition unit 402, face identification unit 403, second acquisition unit 404,
Face information registering unit 405, the first screening unit 406, taxon 407, determining unit 408 and database generation unit
409。
First screening unit 406 is used for the face figure that screening includes individual human face from first image set of this map office
Picture, and the image set being made up of the facial image comprising individual human face is identified as the second image set;Wherein, described first
The pixel of image in image set is higher than the pixel of facial image corresponding to the first face characteristic.First screening unit
406 send the second image set to taxon 407.
Taxon 407 is used to receive the second image set that the first screening unit 406 is sent, in second image set
Facial image carry out recognition of face, and second image set is divided into by least one image according to face recognition result
Collection;Wherein, described image subset includes an at least facial image, the face images pair that same described image subset includes
Same face is answered, the facial image that different described image subsets include corresponds to different faces.Taxon 407 sends out image subset
Deliver to determining unit 408.
Determining unit 408 is used for the image subset for receiving the transmission of taxon 407, according to the face in described image subset
Each self-corresponding face characteristic data of image, determine face characteristic data corresponding to described image subset.Determining unit 408 is by institute
There are each self-corresponding face characteristic data of image subset to send to database generation unit 409.
Database generation unit 409 is used for each self-corresponding face of all image subsets for receiving the transmission of determining unit 408
Characteristic, the default face characteristic data are generated according to each self-corresponding face characteristic data of all described image subsets
Storehouse.Default facial feature database is sent to face information registering unit 405 and first and identified by database generation unit 409
Unit 402.
Second acquisition unit 404 is used to obtain third party's face characteristic corresponding to face to be registered.Second obtains list
Member 404 sends third party's face characteristic to face information registering unit 405.
Face information registering unit 405 is used for the third party's face characteristic sum for receiving the transmission of second acquisition unit 404
According to storehouse generation unit 409 send default facial feature database, if in the default facial feature database include with
4th face characteristic data corresponding to third party's face characteristic, then it is described by the 4th face characteristic data register
Face information corresponding to face to be registered;Wherein, the pixel of facial image is higher than corresponding to the 4th face characteristic data
The pixel of facial image corresponding to third party's face characteristic.
If face information registering unit 405 is additionally operable to not include and the described 3rd in the default facial feature database
Face characteristic data corresponding to face characteristic data, then third party's face characteristic is registered as into the face to be registered
Corresponding face information.
First acquisition unit 401 is used to obtain the first face characteristic corresponding to face to be identified.First obtains list
Member 401 sends the first face characteristic to the first recognition unit 402.
First recognition unit 402 is used for the first face characteristic and database for receiving the transmission of first acquisition unit 401
The default facial feature database that generation unit 409 is sent, if being included and described first in default facial feature database
Second face characteristic data of face characteristic data match, then be identified as mesh to be identified by the second face characteristic data
Mark face characteristic data;Wherein, the pixel of facial image corresponding to the second face characteristic data is higher than first face
The pixel of facial image corresponding to characteristic.First recognition unit 402 sends target face characteristic to recognition of face
Unit 403.
Face identification unit 403 is used to receive the target face characteristic that the first recognition unit 402 is sent, if registered
Face information in comprising the face characteristic data that match with the target face characteristic, then be identified as recognition of face into
Work(.
If face identification unit 403 is additionally operable to not include and the target face characteristic in registered face information
The face characteristic data to match, then it is identified as recognition of face failure.
Further, the first screening unit 406 is additionally operable to concentrate screening image storage time pre- from described first image
If in the period and the facial image comprising individual human face, and single people will be included in preset period of time by described image storage time
The image set that the facial image of face is formed is identified as second image set.
Further, determining unit 408 includes feature point extraction unit, the second screening unit and characteristic point integral unit.
Extraction described image subset includes in the facial image that feature point extraction unit is used to include from described image subset
Each self-corresponding human face characteristic point of facial image.The facial image that feature point extraction unit includes image subset each corresponds to
Human face characteristic point send to the second screening unit.
Second screening unit is each right for receiving the facial image that the image subset of feature point extraction unit transmission includes
The human face characteristic point answered, according to the human face characteristic point extracted, in the facial image included from described image subset described in screening
Target facial image corresponding to image subset;Wherein, the quantity of human face characteristic point corresponding to the target facial image is more than pre-
If characteristic point threshold value.Each self-corresponding target person face image of each image subset is sent to characteristic point and integrated by the second screening unit
Unit.
Characteristic point integral unit is used to receive each self-corresponding target person of each image subset that the second screening unit is sent
Face image, the human face characteristic point of target facial image corresponding to described image subset is integrated, and by the face after integration
Feature point recognition is face characteristic data corresponding to described image subset.
Such scheme, terminal obtain the first face characteristic corresponding to face to be identified;If default face characteristic
It is comprising the second face characteristic data to match with the first face characteristic in database, then second face is special
Sign data are identified as target face characteristic to be identified;The pixel of facial image corresponding to the second face characteristic data
Higher than the pixel of facial image corresponding to the first face characteristic;If included and the mesh in registered face information
The face characteristic data of face characteristic data match are marked, then are identified as recognition of face success.Terminal uses and people to be identified
Face characteristic data corresponding to the facial image for the higher pixel that face matches carry out recognition of face, so as to improve recognition of face
Accuracy rate.
Terminal is by the corresponding face characteristic data register of the facial image of the higher pixel to match with face to be registered
For face information corresponding to face to be registered, the accuracy rate of recognition of face is further increased.
Terminal preferentially uses the image stored in this map office as the face characteristic in default facial feature database
The source of data, because what is stored in this map office is mostly the facial image of terminal user, therefore face can be improved
The reliability of identification.
Referring to Fig. 5, Fig. 5 is a kind of schematic block diagram for terminal that yet another embodiment of the invention provides.This reality as shown in Figure 5
The terminal 500 applied in example can include:One or more processors 501, one or more input equipments 502, one or more
Then output equipment 503 and one or more memories 504.Above-mentioned processor 501, input equipment 502, then output equipment 503 and
Memory 504 completes mutual communication by communication bus 505.Memory 504 is used to store computer program, the calculating
Machine program includes programmed instruction.Processor 501 is used for the programmed instruction for performing the storage of memory 504.Wherein, the quilt of processor 501
It is configured to call described program instruction to perform following operate:
Obtain the first face characteristic corresponding to face to be identified;
It is special that if the second face to match with the first face characteristic is included in default facial feature database
Data are levied, then the second face characteristic data are identified as to target face characteristic to be identified;Wherein, second people
The pixel of facial image corresponding to face characteristic is higher than the pixel of facial image corresponding to the first face characteristic;
If including the face characteristic data to match with the target face characteristic in registered face information,
It is identified as recognition of face success.
Processor 501 is additionally configured to call described program instruction to perform following operate:
If not including the face characteristic data to match with the target face characteristic in registered face information,
Then it is identified as recognition of face failure.
Processor 501 is additionally configured to call described program instruction to perform following operate:
Obtain third party's face characteristic corresponding to face to be registered;
If the 4th face corresponding with third party's face characteristic is included in the default facial feature database
Characteristic, then it is face information corresponding to the face to be registered by the 4th face characteristic data register;Wherein, institute
The pixel for stating facial image corresponding to the 4th face characteristic data is higher than facial image corresponding to third party's face characteristic
Pixel.
Processor 501 is additionally configured to call described program instruction to perform following operate:
If it is special not include face corresponding with third party's face characteristic in the default facial feature database
Data are levied, then third party's face characteristic are registered as into face information corresponding to the face to be registered.
Processor 501 is additionally configured to call described program instruction to perform following operate:
Screening includes the facial image of individual human face from first image set of this map office, and will be by described comprising single
The image set that the facial image of face is formed is identified as the second image set;Wherein, the pixel for the image that described first image is concentrated
Higher than the pixel of facial image corresponding to the first face characteristic;
Recognition of face is carried out to the facial image in second image set, and according to face recognition result by described second
Image set is divided at least one image subset;Wherein, described image subset includes an at least facial image, the same figure
The face images included as subset correspond to same face, and the facial image that different described image subsets include corresponds to different people
Face;
Each self-corresponding face characteristic data of facial image in described image subset, determine described image subset pair
The face characteristic data answered;
The default face characteristic data are generated according to each self-corresponding face characteristic data of all described image subsets
Storehouse.
Processor 501 is specifically arranged to call described program instruction to perform following operate:
Face figure of the screening image storage time in preset period of time and comprising individual human face is concentrated from described first image
Picture, and will be identified as by the described image storage time image set that the facial image comprising individual human face is formed in preset period of time
Second image set.
Processor 501 is specifically arranged to call described program instruction to perform following operate:
The facial image that described image subset includes is extracted in the facial image included from described image subset each to correspond to
Human face characteristic point;
According to the human face characteristic point extracted, described image subset is screened in the facial image included from described image subset
Corresponding target facial image;Wherein, the quantity of human face characteristic point corresponding to the target facial image is more than default characteristic point
Threshold value;
The human face characteristic point of target facial image corresponding to described image subset is integrated, and by the face after integration
Feature point recognition is face characteristic data corresponding to described image subset.
Such scheme, terminal obtain the first face characteristic corresponding to face to be identified;If default face characteristic
It is comprising the second face characteristic data to match with the first face characteristic in database, then second face is special
Sign data are identified as target face characteristic to be identified;The pixel of facial image corresponding to the second face characteristic data
Higher than the pixel of facial image corresponding to the first face characteristic;If included and the mesh in registered face information
The face characteristic data of face characteristic data match are marked, then are identified as recognition of face success.Terminal uses and people to be identified
Face characteristic data corresponding to the facial image for the higher pixel that face matches carry out recognition of face, so as to improve recognition of face
Accuracy rate.
Terminal is by the corresponding face characteristic data register of the facial image of the higher pixel to match with face to be registered
For face information corresponding to face to be registered, the accuracy rate of recognition of face is further increased.
It should be appreciated that in embodiments of the present invention, alleged processor 501 can be CPU (Central
Processing Unit, CPU), the processor can also be other general processors, digital signal processor (Digital
Signal Processor, DSP), application specific integrated circuit (Application Specific Integrated Circuit,
ASIC), ready-made programmable gate array (Field-Programmable Gate Array, FPGA) or other FPGAs
Device, discrete gate or transistor logic, discrete hardware components etc..General processor can be microprocessor or this at
It can also be any conventional processor etc. to manage device.
Input equipment 502 can include Trackpad, fingerprint adopt sensor (finger print information that is used to gathering user and fingerprint
Directional information), microphone etc., output equipment 503 can include display (LCD etc.), loudspeaker etc..
The memory 504 can include read-only storage and random access memory, and to processor 501 provide instruction and
Data.The a part of of memory 504 can also include nonvolatile RAM.For example, memory 504 can also be deposited
Store up the information of device type.
In the specific implementation, processor 501, input equipment 502, the output equipment 503 described in the embodiment of the present invention can
The implementation described in the first embodiment and second embodiment of face identification method provided in an embodiment of the present invention is performed,
Also the implementation of the terminal described by the embodiment of the present invention is can perform, will not be repeated here.
A kind of computer-readable recording medium, the computer-readable storage medium are provided in another embodiment of the invention
Matter is stored with computer program, and the computer program includes programmed instruction, and described program instruction is realized when being executed by processor:
Obtain the first face characteristic corresponding to face to be identified;
It is special that if the second face to match with the first face characteristic is included in default facial feature database
Data are levied, then the second face characteristic data are identified as to target face characteristic to be identified;Wherein, second people
The pixel of facial image corresponding to face characteristic is higher than the pixel of facial image corresponding to the first face characteristic;
If including the face characteristic data to match with the target face characteristic in registered face information,
It is identified as recognition of face success.
Further, also realized when the computer program is executed by processor:
If not including the face characteristic data to match with the target face characteristic in registered face information,
Then it is identified as recognition of face failure.
Further, also realized when the computer program is executed by processor:
Obtain third party's face characteristic corresponding to face to be registered;
If the 4th face corresponding with third party's face characteristic is included in the default facial feature database
Characteristic, then it is face information corresponding to the face to be registered by the 4th face characteristic data register;Wherein, institute
The pixel for stating facial image corresponding to the 4th face characteristic data is higher than facial image corresponding to third party's face characteristic
Pixel.
Further, also realized when the computer program is executed by processor:
If it is special not include face corresponding with third party's face characteristic in the default facial feature database
Data are levied, then third party's face characteristic are registered as into face information corresponding to the face to be registered.
Further, also realized when the computer program is executed by processor:
Screening includes the facial image of individual human face from first image set of this map office, and will be by described comprising single
The image set that the facial image of face is formed is identified as the second image set;Wherein, the pixel for the image that described first image is concentrated
Higher than the pixel of facial image corresponding to the first face characteristic;
Recognition of face is carried out to the facial image in second image set, and according to face recognition result by described second
Image set is divided at least one image subset;Wherein, described image subset includes an at least facial image, the same figure
The face images included as subset correspond to same face, and the facial image that different described image subsets include corresponds to different people
Face;
Each self-corresponding face characteristic data of facial image in described image subset, determine described image subset pair
The face characteristic data answered;
The default face characteristic data are generated according to each self-corresponding face characteristic data of all described image subsets
Storehouse.
Further, implemented when the computer program is executed by processor:
Face figure of the screening image storage time in preset period of time and comprising individual human face is concentrated from described first image
Picture, and will be identified as by the described image storage time image set that the facial image comprising individual human face is formed in preset period of time
Second image set.
Further, implemented when the computer program is executed by processor:
The facial image that described image subset includes is extracted in the facial image included from described image subset each to correspond to
Human face characteristic point;
According to the human face characteristic point extracted, described image subset is screened in the facial image included from described image subset
Corresponding target facial image;Wherein, the quantity of human face characteristic point corresponding to the target facial image is more than default characteristic point
Threshold value;
The human face characteristic point of target facial image corresponding to described image subset is integrated, and by the face after integration
Feature point recognition is face characteristic data corresponding to described image subset.
The computer-readable recording medium can be the internal storage unit of the terminal described in foregoing any embodiment, example
Such as the hard disk or internal memory of terminal.The computer-readable recording medium can also be the External memory equipment of the terminal, such as
The plug-in type hard disk being equipped with the terminal, intelligent memory card (Smart Media Card, SMC), secure digital (Secure
Digital, SD) card, flash card (Flash Card) etc..Further, the computer-readable recording medium can also be wrapped both
Including the internal storage unit of the terminal also includes External memory equipment.The computer-readable recording medium is described for storing
Other programs and data needed for computer program and the terminal.The computer-readable recording medium can be also used for temporarily
The data that ground storage has been exported or will exported.
Those of ordinary skill in the art are it is to be appreciated that the list of each example described with reference to the embodiments described herein
Member and algorithm steps, it can be realized with electronic hardware, computer software or the combination of the two, in order to clearly demonstrate hardware
With the interchangeability of software, the composition and step of each example are generally described according to function in the above description.This
A little functions are performed with hardware or software mode actually, application-specific and design constraint depending on technical scheme.Specially
Industry technical staff can realize described function using distinct methods to each specific application, but this realization is not
It is considered as beyond the scope of this invention.
It is apparent to those skilled in the art that for convenience of description and succinctly, the end of foregoing description
End and the specific work process of unit, may be referred to the corresponding process in preceding method embodiment, will not be repeated here.
In several embodiments provided herein, it should be understood that disclosed terminal and method, it can be passed through
Its mode is realized.For example, device embodiment described above is only schematical, for example, the division of the unit, only
Only a kind of division of logic function, there can be other dividing mode when actually realizing, such as multiple units or component can be tied
Another system is closed or is desirably integrated into, or some features can be ignored, or do not perform.In addition, shown or discussed phase
Coupling or direct-coupling or communication connection between mutually can be INDIRECT COUPLING or the communication by some interfaces, device or unit
Connection or electricity, the connection of mechanical or other forms.
The unit illustrated as separating component can be or may not be physically separate, show as unit
The part shown can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On NE.Some or all of unit therein can be selected to realize scheme of the embodiment of the present invention according to the actual needs
Purpose.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, can also
It is that unit is individually physically present or two or more units are integrated in a unit.It is above-mentioned integrated
Unit can both be realized in the form of hardware, can also be realized in the form of SFU software functional unit.
If the integrated unit is realized in the form of SFU software functional unit and is used as independent production marketing or use
When, it can be stored in a computer read/write memory medium.Based on such understanding, technical scheme is substantially
The part to be contributed in other words to prior art, or all or part of the technical scheme can be in the form of software product
Embody, the computer software product is stored in a storage medium, including some instructions are causing a computer
Equipment (can be personal computer, server, or network equipment etc.) performs the complete of each embodiment methods described of the present invention
Portion or part steps.And foregoing storage medium includes:USB flash disk, mobile hard disk, read-only storage (ROM, Read-Only
Memory), random access memory (RAM, Random Access Memory), magnetic disc or CD etc. are various can store journey
The medium of sequence code.
The foregoing is only a specific embodiment of the invention, but protection scope of the present invention is not limited thereto, any
Those familiar with the art the invention discloses technical scope in, various equivalent modifications can be readily occurred in or replaced
Change, these modifications or substitutions should be all included within the scope of the present invention.Therefore, protection scope of the present invention should be with right
It is required that protection domain be defined.
Claims (10)
- A kind of 1. face identification method, it is characterised in that including:Obtain the first face characteristic corresponding to face to be identified;If the second face characteristic number to match with the first face characteristic is included in default facial feature database According to the second face characteristic data to be then identified as to target face characteristic to be identified;Wherein, second face is special The pixel for levying facial image corresponding to data is higher than the pixel of facial image corresponding to the first face characteristic;If identified in registered face information comprising the face characteristic data to match with the target face characteristic Work(is identified as face.
- 2. face identification method according to claim 1, it is characterised in that also include:If not including the face characteristic data to match with the target face characteristic in registered face information, know Wei not face recognition failures.
- 3. face identification method according to claim 1, it is characterised in that described to obtain corresponding to face to be identified the Before one face characteristic data, in addition to:Obtain third party's face characteristic corresponding to face to be registered;If the 4th face characteristic corresponding with third party's face characteristic is included in the default facial feature database Data, then it is face information corresponding to the face to be registered by the 4th face characteristic data register;Wherein, described The pixel of facial image corresponding to four face characteristic data is higher than the picture of facial image corresponding to third party's face characteristic Element.
- 4. face identification method according to claim 3, it is characterised in that described to obtain corresponding to face to be identified the Before one face characteristic data, after third party's face characteristic corresponding to acquisition face to be registered, in addition to:If face characteristic number corresponding with third party's face characteristic is not included in the default facial feature database According to third party's face characteristic then is registered as into face information corresponding to the face to be registered.
- 5. face identification method according to claim 3, it is characterised in that described to obtain corresponding to face to be registered the Before three face characteristic data, in addition to:Screening includes the facial image of individual human face from first image set of this map office, and will include individual human face by described Facial image form image set be identified as the second image set;Wherein, the pixel for the image that described first image is concentrated is higher than The pixel of facial image corresponding to the first face characteristic;Recognition of face is carried out to the facial image in second image set, and according to face recognition result by second image Collection is divided at least one image subset;Wherein, described image subset includes an at least facial image, same described image Collect the face images included and correspond to same face, the facial image that different described image subsets include corresponds to different faces;Each self-corresponding face characteristic data of facial image in described image subset, are determined corresponding to described image subset Face characteristic data;The default facial feature database is generated according to each self-corresponding face characteristic data of all described image subsets.
- 6. face identification method according to claim 5, it is characterised in that in first image set from this map office Screening includes the facial image of individual human face, and the image set being made up of the facial image comprising individual human face is identified as Second image set, including:Screening image storage time is concentrated in preset period of time and the facial image comprising individual human face from described first image, and It will be identified as by the described image storage time image set that the facial image comprising individual human face is formed in preset period of time described Second image set.
- 7. face identification method according to claim 5, it is characterised in that the face in the subset according to described image Each self-corresponding face characteristic data of image, determine face characteristic data corresponding to described image subset, including:Each self-corresponding people of facial image that described image subset includes is extracted in the facial image included from described image subset Face characteristic point;It is corresponding that described image subset is screened according to the human face characteristic point extracted, in the facial image included from described image subset Target facial image;Wherein, the quantity of human face characteristic point corresponding to the target facial image is more than default characteristic point threshold value;The human face characteristic point of target facial image corresponding to described image subset is integrated, and by the face characteristic after integration Point is identified as face characteristic data corresponding to described image subset.
- 8. a kind of terminal, it is characterised in that including the list for performing the method as described in claim 1-7 any claims Member.
- 9. a kind of terminal, it is characterised in that the processor, defeated including processor, input equipment, output equipment and memory Enter equipment, output equipment and memory to be connected with each other, wherein, the memory is used to store computer program, the computer Program includes programmed instruction, and the processor is arranged to call described program instruction, performed such as any one of claim 1-7 Described method.
- A kind of 10. computer-readable recording medium, it is characterised in that the computer-readable storage medium is stored with computer program, The computer program includes programmed instruction, and described program instruction makes the computing device such as right when being executed by a processor It is required that the method described in any one of 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710807664.2A CN107609508A (en) | 2017-09-08 | 2017-09-08 | A kind of face identification method, terminal and computer-readable recording medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710807664.2A CN107609508A (en) | 2017-09-08 | 2017-09-08 | A kind of face identification method, terminal and computer-readable recording medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107609508A true CN107609508A (en) | 2018-01-19 |
Family
ID=61063209
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710807664.2A Withdrawn CN107609508A (en) | 2017-09-08 | 2017-09-08 | A kind of face identification method, terminal and computer-readable recording medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107609508A (en) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108280422A (en) * | 2018-01-22 | 2018-07-13 | 百度在线网络技术(北京)有限公司 | The method and apparatus of face for identification |
CN108573038A (en) * | 2018-04-04 | 2018-09-25 | 北京市商汤科技开发有限公司 | Image procossing, auth method, device, electronic equipment and storage medium |
CN109064613A (en) * | 2018-09-18 | 2018-12-21 | 广州佳都数据服务有限公司 | Face identification method and device |
CN109087157A (en) * | 2018-06-08 | 2018-12-25 | 成都第二记忆科技有限公司 | A kind of video-photographic works sale service system and method and business model |
CN109361994A (en) * | 2018-10-12 | 2019-02-19 | Oppo广东移动通信有限公司 | Speaker control method, mobile terminal and computer readable storage medium |
CN110069445A (en) * | 2019-03-12 | 2019-07-30 | 深圳壹账通智能科技有限公司 | Face image processing process, server and computer readable storage medium |
CN110097368A (en) * | 2018-01-30 | 2019-08-06 | 财付通支付科技有限公司 | Recognition methods, server, terminal and the service equipment of facial image |
CN110825765A (en) * | 2019-10-23 | 2020-02-21 | 中国建设银行股份有限公司 | Face recognition method and device |
CN111523346A (en) * | 2019-02-01 | 2020-08-11 | 深圳市商汤科技有限公司 | Image recognition method and device, electronic equipment and storage medium |
CN111626161A (en) * | 2020-05-15 | 2020-09-04 | Oppo(重庆)智能科技有限公司 | Face recognition method and device, terminal and readable storage medium |
CN111782855A (en) * | 2020-07-15 | 2020-10-16 | 上海依图网络科技有限公司 | Face image processing method, device, equipment and medium |
CN112784823A (en) * | 2021-03-17 | 2021-05-11 | 中国工商银行股份有限公司 | Face image recognition method, face image recognition device, computing equipment and medium |
WO2022174699A1 (en) * | 2021-02-22 | 2022-08-25 | Oppo广东移动通信有限公司 | Image updating method and apparatus, and electronic device and computer-readable medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101477621A (en) * | 2009-02-20 | 2009-07-08 | 深圳华为通信技术有限公司 | Image updating process and apparatus based on human face recognition |
CN103824068A (en) * | 2014-03-19 | 2014-05-28 | 上海看看智能科技有限公司 | Human face payment authentication system and method |
CN105740808A (en) * | 2016-01-28 | 2016-07-06 | 北京旷视科技有限公司 | Human face identification method and device |
CN105809154A (en) * | 2016-05-10 | 2016-07-27 | 清华大学 | Face identification method and device |
CN106156688A (en) * | 2015-03-10 | 2016-11-23 | 上海骏聿数码科技有限公司 | A kind of dynamic human face recognition methods and system |
CN106372624A (en) * | 2016-10-15 | 2017-02-01 | 杭州艾米机器人有限公司 | Human face recognition method and human face recognition system |
CN106446816A (en) * | 2016-09-14 | 2017-02-22 | 北京旷视科技有限公司 | Face recognition method and device |
-
2017
- 2017-09-08 CN CN201710807664.2A patent/CN107609508A/en not_active Withdrawn
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101477621A (en) * | 2009-02-20 | 2009-07-08 | 深圳华为通信技术有限公司 | Image updating process and apparatus based on human face recognition |
CN103824068A (en) * | 2014-03-19 | 2014-05-28 | 上海看看智能科技有限公司 | Human face payment authentication system and method |
CN106156688A (en) * | 2015-03-10 | 2016-11-23 | 上海骏聿数码科技有限公司 | A kind of dynamic human face recognition methods and system |
CN105740808A (en) * | 2016-01-28 | 2016-07-06 | 北京旷视科技有限公司 | Human face identification method and device |
CN105809154A (en) * | 2016-05-10 | 2016-07-27 | 清华大学 | Face identification method and device |
CN106446816A (en) * | 2016-09-14 | 2017-02-22 | 北京旷视科技有限公司 | Face recognition method and device |
CN106372624A (en) * | 2016-10-15 | 2017-02-01 | 杭州艾米机器人有限公司 | Human face recognition method and human face recognition system |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108280422A (en) * | 2018-01-22 | 2018-07-13 | 百度在线网络技术(北京)有限公司 | The method and apparatus of face for identification |
CN110097368A (en) * | 2018-01-30 | 2019-08-06 | 财付通支付科技有限公司 | Recognition methods, server, terminal and the service equipment of facial image |
US11270142B2 (en) | 2018-04-04 | 2022-03-08 | Beijing Sensetime Technology Development Co., Ltd. | Methods and apparatuses for processing image and identity verification, electronic devices, and storage media |
CN108573038A (en) * | 2018-04-04 | 2018-09-25 | 北京市商汤科技开发有限公司 | Image procossing, auth method, device, electronic equipment and storage medium |
WO2019192216A1 (en) * | 2018-04-04 | 2019-10-10 | 北京市商汤科技开发有限公司 | Method and device for image processing and identity authentication, electronic device, and storage medium |
CN109087157A (en) * | 2018-06-08 | 2018-12-25 | 成都第二记忆科技有限公司 | A kind of video-photographic works sale service system and method and business model |
CN109064613A (en) * | 2018-09-18 | 2018-12-21 | 广州佳都数据服务有限公司 | Face identification method and device |
CN109361994A (en) * | 2018-10-12 | 2019-02-19 | Oppo广东移动通信有限公司 | Speaker control method, mobile terminal and computer readable storage medium |
CN111523346A (en) * | 2019-02-01 | 2020-08-11 | 深圳市商汤科技有限公司 | Image recognition method and device, electronic equipment and storage medium |
CN111523346B (en) * | 2019-02-01 | 2024-04-02 | 深圳市商汤科技有限公司 | Image recognition method and device, electronic equipment and storage medium |
CN110069445A (en) * | 2019-03-12 | 2019-07-30 | 深圳壹账通智能科技有限公司 | Face image processing process, server and computer readable storage medium |
CN110825765A (en) * | 2019-10-23 | 2020-02-21 | 中国建设银行股份有限公司 | Face recognition method and device |
CN111626161A (en) * | 2020-05-15 | 2020-09-04 | Oppo(重庆)智能科技有限公司 | Face recognition method and device, terminal and readable storage medium |
CN111782855A (en) * | 2020-07-15 | 2020-10-16 | 上海依图网络科技有限公司 | Face image processing method, device, equipment and medium |
WO2022174699A1 (en) * | 2021-02-22 | 2022-08-25 | Oppo广东移动通信有限公司 | Image updating method and apparatus, and electronic device and computer-readable medium |
CN112784823A (en) * | 2021-03-17 | 2021-05-11 | 中国工商银行股份有限公司 | Face image recognition method, face image recognition device, computing equipment and medium |
CN112784823B (en) * | 2021-03-17 | 2023-04-07 | 中国工商银行股份有限公司 | Face image recognition method, face image recognition device, computing equipment and medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107609508A (en) | A kind of face identification method, terminal and computer-readable recording medium | |
US20180315049A1 (en) | Multi factor authentication rule-based intelligent bank cards | |
CN108537030A (en) | Management method, device and the electronic equipment of identity-based identification | |
CN106534572A (en) | Information display method and device and terminal | |
CN106716436A (en) | Information display method and system | |
CN107800672A (en) | A kind of Information Authentication method, electronic equipment, server and information authentication system | |
CN107491732A (en) | A kind of identity authentication method and terminal | |
CN107633169A (en) | A kind of terminal unlock method, terminal and computer-readable recording medium | |
CN107085791A (en) | A kind of electric paying method and terminal | |
CN106845181A (en) | The acquisition methods and electronic equipment of a kind of password | |
WO2019174155A1 (en) | Display method for application icon, and terminal device | |
CN109274582A (en) | Methods of exhibiting, device, equipment and the storage medium of instant communication information | |
US20130290728A1 (en) | Method and system for a secure, searchable and sharable digital notary journal | |
CN107196971A (en) | Information processing method, device, electronic equipment and server | |
CN107656959A (en) | A kind of message leaving method, device and message equipment | |
CN117275138A (en) | Identity authentication method, device, equipment and storage medium based on automatic teller machine | |
US20240028698A1 (en) | System and method for perfecting and accelerating biometric identification via evolutionary biometrics via continual registration | |
CN107742073A (en) | Information displaying method, device, computer installation and computer-readable recording medium | |
CN111079119A (en) | Verification method, device, equipment and storage medium | |
CN105844815B (en) | A kind of enchashment control method of ATM machine | |
CN106779717A (en) | A kind of payment authentication method and device | |
CN106682612B (en) | Alarm method, terminal, server and system based on image recognition | |
CN111666014A (en) | Message pushing method, device, equipment and computer readable storage medium | |
JP2010073112A (en) | Face collating system | |
CN105550543B (en) | A kind of iris information processing method and user terminal |
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 | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20180119 |