CN108154070A - Face identification method and device - Google Patents
Face identification method and device Download PDFInfo
- Publication number
- CN108154070A CN108154070A CN201611103853.3A CN201611103853A CN108154070A CN 108154070 A CN108154070 A CN 108154070A CN 201611103853 A CN201611103853 A CN 201611103853A CN 108154070 A CN108154070 A CN 108154070A
- Authority
- CN
- China
- Prior art keywords
- face
- facial image
- user
- skin detection
- face characteristic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
- G06V40/173—Classification, e.g. identification face re-identification, e.g. recognising unknown faces across different face tracks
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Collating Specific Patterns (AREA)
Abstract
The present invention relates to a kind of face identification system grade method, the system operation in electronic device, including:Acquisition module, for when receiving recognition of face request, acquiring the facial image of active user;Detection module for carrying out In vivo detection to the facial image, judges whether the facial image is real human face;Identification module, for when the facial image is real human face, being identified to the facial image, obtaining the face characteristic in the facial image;Comparing module for the face characteristic to be compared with pre-stored skin detection, and counts the quantity with the matched face characteristic of the skin detection;Authentication module, for when the quantity with the matched face characteristic of the skin detection reaches preset value, judging that the active user passes through face verification.Recognition of face can be rapidly completed using the present invention to verify, improve user experience.
Description
【Technical field】
The present invention relates to identification technology field more particularly to a kind of face identification methods and device.
【Background technology】
Recognition of face is a kind of biological identification technology that the facial feature information based on people carries out identification.With camera shooting
Machine or camera acquisition image or video flowing containing face, and automatic detect and track face in the picture, and then to detection
The face that arrives carries out a series of the relevant technologies of face, usually also referred to as Identification of Images, face recognition.
Traditional recognition of face, is usually previously stored with multiple face templates, and different face templates has different
Face characteristic.The facial image of user is acquired during verification, then identifies the face characteristic in acquired facial image, Zhi Houzai
The face characteristic that will identify that is compared one by one with the face characteristic of pre-set face template.In this way, pass through face mould
Plate judges face template and whether acquires facial image with acquiring the mode that the feature of facial image is compared one by one
Matching, to determine whether user's face passes through verification.However, when the feature quantity of face template, face template is more, tradition
Recognition of face flow can spend the more time, influence user experience.
【Invention content】
The present invention proposes a kind of face identification method and device, it is intended to it solves conventional face's identification process and spends the time long,
The technical issues of influencing user experience.
In order to solve the above technical problems, the present invention provides following technical scheme:
On the one hand, the present invention provides a kind of face identification method, and this method is applied to electronic device, the recognition of face side
Method includes:
When receiving recognition of face request, the facial image of active user is acquired;
In vivo detection is carried out to the facial image, judges whether the facial image is real human face;
If the facial image is real human face, the facial image is identified, is obtained in the facial image
Face characteristic;
The face characteristic with pre-stored skin detection is compared, and is counted and the face characteristic mould
The quantity of the matched face characteristic of plate;
If reaching preset value with the quantity of the matched face characteristic of the skin detection, judge described current
User passes through face verification.
Preferably, it is described when receiving recognition of face request, before the step of acquiring the facial image of user, also wrap
It includes:
The facial image of repeated acquisition user;
When the facial image is real human face, the facial image is identified, the face obtained in the facial image is special
Sign;
Face characteristic acquired in storage is the skin detection.
Preferably, it is described when receiving recognition of face request, before the step of acquiring the facial image of user, this method
It further includes:
Obtain the electronic device ID and user's login account;
The skin detection is stored respectively with the electronic device ID, the binding of user's login account.
Preferably, it is described that the face characteristic is compared with pre-stored skin detection, and statistics and institute
The step of stating the quantity of the matched face characteristic of skin detection, specifically includes:
Obtain the skin detection with electronic device ID or described users login account binding;
The face characteristic is compared respectively with acquired skin detection;
It is obtaining with the skin detection counting if being matched there are face characteristic with the skin detection
Increase number one on the basis of the quantity of the matched face characteristic.
Preferably, the preset value is 50% arbitrary value not less than skin detection sum.
Compared to the prior art, face identification method proposed by the invention by acquiring user's facial image in advance, obtains
Take skin detection;Then in verification by the face characteristic of the user's facial image acquired and the skin detection
It is compared, when acquired face characteristic major part matches with the skin detection, that is, judges that the face of user leads to
Cross verification.In this way, without all face characteristics of user's face are all compared, the time of face verification is shortened.In addition,
The face identification method also by the way that user's login account, electronic device ID are bound respectively with skin detection, to
It can carry out the choosing of deleting of skin detection in advance by user's login account or electronic device ID in verification, reduce and carry out face
The range of aspect ratio pair further shortens the time of recognition of face flow, improves user experience.
On the other hand, the present invention provides a kind of face identification system, and the system operation is in electronic device, the recognition of face
System includes:
Acquisition module, for when receiving recognition of face request, acquiring the facial image of active user;
Detection module for carrying out In vivo detection to the facial image, judges whether the facial image is true people
Face;
Identification module, for when the facial image is real human face, the facial image to be identified, obtaining should
Face characteristic in facial image;
Comparing module, for the face characteristic to be compared with pre-stored skin detection, and count with
The quantity of the matched face characteristic of skin detection;
Authentication module, for reaching preset value in the quantity with the matched face characteristic of the skin detection
When, judge that the active user passes through face verification.
Preferably, which further includes memory module, wherein:
The acquisition module is additionally operable to before recognition of face request is received, the facial image of repeated acquisition user;
The identification module is additionally operable to, when the facial image is real human face, identify the facial image, and obtaining should
Face characteristic in facial image;
The memory module is the skin detection for storing acquired face characteristic.
Preferably, which further includes acquisition module, wherein:
The acquisition module, for obtaining the electronic device ID and user's login account;
The memory module is additionally operable to the verification face characteristic logging in account with the electronic device ID, user respectively
Family binding storage.
Preferably, the comparing module, is additionally operable to:
Obtain the skin detection with electronic device ID or described users login account binding;
The face characteristic is compared respectively with acquired skin detection;
It is obtaining with the skin detection counting if being matched there are face characteristic with the skin detection
Increase number one on the basis of the quantity of the matched face characteristic.
Preferably, the preset value is 50% arbitrary value not less than skin detection sum.
Compared to the prior art, face identification system proposed by the invention by acquiring user's facial image in advance, obtains
Take skin detection;Then in verification by the face characteristic of the user's facial image acquired and the skin detection
It is compared, when acquired face characteristic major part matches with the skin detection, that is, judges that the face of user leads to
Cross verification.In this way, without all face characteristics of user's face are all compared, the time of face verification is shortened.In addition,
The face identification system also by the way that user's login account, electronic device ID are bound respectively with skin detection, to
It can carry out the choosing of deleting of skin detection in advance by user's login account or electronic device ID in verification, reduce and carry out face
The range of aspect ratio pair further shortens the time of recognition of face flow, improves user experience.
【Description of the drawings】
Fig. 1 is each one optional application environment schematic diagram of embodiment of the present invention;
Fig. 2 is the functional block diagram of face identification system first embodiment of the present invention;
Fig. 3 is the functional block diagram of face identification system second embodiment of the present invention;
Fig. 4 is the functional block diagram of face identification system 3rd embodiment of the present invention;
Fig. 5 is the implementation process diagram of the present inventor's face recognition method first embodiment;
Fig. 6 is the implementation process diagram of the present inventor's face recognition method second embodiment;
Fig. 7 is the implementation process diagram of the present inventor's face recognition method 3rd embodiment.
Reference numeral:
Electronic device | 1 |
Memory | 11 |
Processor | 12 |
Display | 13 |
Camera | 14 |
Face identification system | 200 |
Acquisition module | 201 |
Detection module | 202 |
Identification module | 203 |
Comparing module | 204 |
Authentication module | 205 |
Memory module | 206 |
Acquisition module | 207 |
Process step | S501-505、S601-S603、S701-S703 |
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
【Specific embodiment】
In order to make the purpose , technical scheme and advantage of the present invention be clearer, with reference to the accompanying drawings and embodiments, it is right
The present invention is further elaborated.It should be appreciated that specific embodiment described herein is only to explain the present invention, not
For limiting the present invention.Based on the embodiments of the present invention, those of ordinary skill in the art are not before creative work is made
All other embodiments obtained are put, shall fall within the protection scope of the present invention.
It should be noted that the description for being related to " first ", " second " etc. in the present invention is only used for description purpose, and cannot
It is interpreted as indicating or implies its relative importance or imply the quantity of the technical characteristic indicated by indicating.Define as a result, " the
One ", at least one this feature can be expressed or be implicitly included to the feature of " second ".In addition, the skill between each embodiment
Art scheme can be combined with each other, but must can be implemented as basis with those of ordinary skill in the art, when technical solution
Will be understood that the combination of this technical solution is not present with reference to there is conflicting or can not realize when, also not the present invention claims
Protection domain within.
As shown in fig.1, it is each one optional application environment schematic diagram of embodiment of the present invention.In the present embodiment, institute
The face identification system 200 stated is installed and is run in electronic device 1, and the electronic device 1 can be mobile phone, intelligence electricity
Words, laptop, digit broadcasting receiver, PDA (personal digital assistant), PAD (tablet computer), PMP (portable multimedias
Player), the mobile terminal of navigation device etc. and such as number TV, desktop computer, notebook, server etc. consolidate
Determine terminal.The electronic device 1 may include, but be not limited only to, memory 11, processor 12, display 13 and camera 14,
The said modules 11-14 of the electronic device 1 can be communicated to connect by system bus.It should be pointed out that Fig. 1 is shown with each
The electronic device 1 of kind component it should be appreciated that be not required for implementing all components shown, can alternatively implement
More or fewer components.Said modules 11-14 will be described in detail hereinafter.
The memory 11 can include the storage medium of at least one type, the storage medium include flash memory, hard disk,
Multimedia card, card-type memory (for example, SD or DX memories etc.), random access storage device (RAM), static random-access are deposited
Reservoir (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read only memory
(PROM), magnetic storage, disk, CD etc..The memory 11 can be the internal storage unit of the electronic device 1, example
The hard disk or memory of such as electronic device 1.The memory 11 can also be the External memory equipment of the electronic device 1, such as
The plug-in type hard disk being equipped on the electronic device 1, SMC card (Smart Media Card:Intelligent memory card), SD card (Secure
Digital:Safe digital card), FC cards (Flash Card:Flash card) etc..Further, the memory 11 can also be wrapped both
The internal storage unit for including the electronic device 1 also includes External memory equipment.The memory 11 is installed commonly used in storage
In the application software and Various types of data of the electronic device 1.In the present embodiment, the memory 11 is known for storing the face
The program code of other system 200, the ID of the skin detection of 1 user of electronic device, user's login account and the electronic device 1
Deng.
The processor 12 can be central processing unit (Central Processing Unit, CPU), controller, micro-control
It is one or more in device processed, microprocessor or other data processing chips.The processor 12 is commonly used in control electronic device
1 overall operation, such as relevant control and the processing such as execution communicates with voice communication, data, video calling.The present embodiment
In, which is installed on the program code of the memory 11 or processing data for running, such as runs the face
Identifying system 200, with facial image of identification acquisition etc..
The display 13 is include but are not limited to, and liquid crystal display (LCD), has thin film transistor (TFT) LCD (TFT-LCD)
At least one of machine light emitting diode (OLED) display, flexible display, three-dimensional (3D) display etc..Further,
Some in these displays may be constructed such that transparence so that user to be allowed to be watched from outside, this is properly termed as transparence display
Device, typical transparent display can be, for example, transparent organic light emitting diode (TOLED) display etc..The display 13 is logical
It is usually used in the information that handles in the electronic apparatus 1 of display, such as user interface (UI) or graphic user interface (GUI), image, regards
UI or GUI of frequency and correlation function etc..In the present embodiment, the display 13 is for display and the relevant letter of recognition of face
Breath, such as when the electronic device 1 is in face drainage pattern, which can be used for display and the recognition of face system
It unites 200 relevant user interfaces (UI) or graphic user interface (GUI), the facial image of acquisition, user's face video for recording
Deng.
The camera 14 is include but are not limited to, and the front camera or postposition set on the electronic device 1 image
Head.The camera 14 generates image graphic or video etc. commonly used in capturing the image in 14 front of camera.This reality
It applies in example, the camera 14 is used to acquire user's facial image.
So far, oneself according to its function through describing electronic device 1.In the following, by the hardware knot based on above-mentioned electronic device 1
Structure proposes each embodiment of the present invention.
First, the present invention proposes a kind of face identification system 200.
As shown in fig.2, it is the functional block diagram of 200 first embodiment of face identification system of the present invention.In the present embodiment
In, the face identification system 200 can be divided into one or more modules, and one or more of modules are stored
In the memory 11, and it is performed by one or more processors (being the processor 12 in the present embodiment), to complete
The present invention.For example, in fig. 2, the face identification system 200 can be divided into acquisition module 201, detection module 202,
Identification module 203, comparing module 204 and authentication module 205.The so-called function module of the present invention be refer to complete it is specific
The series of computation machine program instruction section of function, than program more suitable for describing the face identification system 200 in the electronics
Implementation procedure in device 1.The function of putting up with each function module 201-205 below is described in detail.
The acquisition module 201, for when receiving recognition of face request, passing through the camera of the electronic device 1
The facial image of 14 acquisition active users.
Usually, face identification functions are mainly used for verifying the identity of user, include but are not limited to, with
The identity of user is verified when family is unlocked the electronic device 1, is tested when user is paid using the electronic device 1
Identity, the identity of verification user etc. when user browses preset secret file for demonstrate,proving user.Therefore in the present embodiment, when above-mentioned
When operation associated with the face identification functions of the electronic device 1 occurs, the recognition of face request can be triggered, and will
Recognition of face request is sent to the acquisition module 201.It is described to adopt meanwhile when receiving the recognition of face request
Collection module 101 can call the camera 14 to acquire the image in front of the camera 14.The camera 14 can be described
The rear camera of the front camera of electronic device 1 or the electronic device 1.Acquired image includes at least, but
It is not limited only to, the facial image of 1 active user of electronic device.
For example, it is assumed that 1 user preset of electronic device by the way of recognition of face come to the electronic device 1 into
Row unlock, then when the preset unlock operation triggering (such as the power key of the electronic device 1 is clicked) of the electronic device 1,
Recognition of face request is generated in the electronic device 1.The acquisition module 201 receives the recognition of face request, and then according to this
The camera 14 of electronic device 1 described in recognition of face request call acquires the facial image of the active user of the electronic device 1.
The detection module 202, for the facial image carry out In vivo detection, judge the facial image whether be
Real human face.
The photo of invalid user stealing validated user, picture etc. come through face verification in order to prevent, and the present embodiment is passing
The flow of In vivo detection is increased in the face verification flow of system.Specifically, as the active user for collecting the electronic device 1
Facial image when, which is sent to the detection module 202, so that the detection module 202 passes through In vivo detection
Technology carries out the facial image In vivo detection, and judgement show whether the facial image is true face.Wherein, the live body
Detection can be the In vivo detection mode of actions such as nodded, shaken the head by voice or text prompt user, opened one's mouth, can also
It is any other suitable In vivo detection mode.The In vivo detection is the prior art, and details are not described herein again.
The identification module 203, for when the facial image is real human face, knowing to the facial image
Not, the face characteristic in the facial image is obtained.
In the present embodiment, the identification module 203 is identified the facial image using face recognition technology, from institute
It states and face characteristic is obtained in facial image.The face characteristic may include, but be not limited only to, each position of face shape, face
The features such as the position of (mouth, eye, nose etc.), each position shape of face, face mask.It should be noted that the face characteristic
It can be the part face characteristic in all face characteristics of the facial image or the facial image.Wherein, it is described
Face recognition technology is the prior art, and details are not described herein again.
The comparing module 204, for the face characteristic to be compared with pre-stored skin detection, and
Statistics and the quantity of the matched face characteristic of the skin detection.
In the present embodiment, if the face characteristic of a facial image is identical with a skin detection, institute
It states comparing module 204 and judges that the face characteristic is matched with the skin detection.If the face characteristic of a facial image
It is differed with the skin detection, then the comparing module 204 judges the face characteristic and the skin detection
It mismatches.
For example, if the face characteristic acquired from the facial image is 4 face characteristics, and the electronics
5 skin detections are previously provided in device 1, then the comparing module 204 is chosen from 4 face characteristics one by one
Go out a face characteristic, to be compared respectively with 5 skin detections.If the face characteristic and 5 face spies
A matching in template is levied, then the comparing module 204 judges that the face characteristic is matched with the skin detection.Instead
It, if the face characteristic is mismatched with 5 skin detections, the comparing module 204 judges the face characteristic
It is mismatched with the skin detection.
Further, when the face characteristic of all facial images is mismatched with the skin detection, institute
It states comparing module 204 and shows corresponding prompting on the display screen 13 of the electronic device 1.It should be noted that the present embodiment
In, whenever a face characteristic is matched with the skin detection, the comparing module 204 will statistics obtain with
Increase number one on the basis of the quantity of the matched face characteristic of skin detection, counted and the face with this
The quantity of the matched face characteristic of feature templates.
The authentication module 205, for reaching in the quantity with the matched face characteristic of the skin detection
During preset value, judge that the active user passes through face verification.
In the present embodiment, it in order to overcome in traditional recognition of face when carrying out face characteristic comparison, needs to have compared
Whether all people's face feature just can determine that the facial image of acquisition by verification, and too long in flow wastes time excessive lack
It falls into, the preset value can be no more than the arbitrary value of the skin detection sum.Meanwhile in order to ensure to compare as far as possible
To the correctness of result, which should be 50% numerical value not less than skin detection sum.For example, when using
When the preset face characteristic masterplate in family is 8, the preset value can be any one in 4,5,6,7 threes, and specific choice can
With depending on the actual demand of user.
It will be recalled from above that if the quantity with the matched face characteristic of the skin detection reaches above-mentioned default
Value, hence it is evident that can illustrate, acquire the face characteristic of image and face corresponding with the face characteristic masterplate (namely legal use
The face at family) there is higher similarity (most of matching), then it can be determined that acquired image includes and face spy
The corresponding face of masterplate is levied, that is, the active user for carrying out face verification is validated user.Therefore the authentication module 205 can evidence
This judges that the active user passes through the face verification.
By above-mentioned function module 201-205, face identification system 200 of the present invention in face verification by adopting
Collect user's facial image, the face characteristic of the user's facial image acquired is compared with the skin detection,
When acquired face characteristic major part matches with the skin detection, that is, judge that the face of user passes through verification.In this way,
Without all face characteristics of user's face are all compared, the time of face verification is shortened, improves user experience.
Further, the first embodiment based on the invention described above face identification system 200 proposes recognition of face of the present invention
The second embodiment of system 200.
As shown in fig.3, it is the high-level schematic functional block diagram of 200 second embodiment of face identification system of the present invention.In this reality
It applies in example, the face identification system 200 further includes memory module 206 in addition to function module 201-205.Wherein:
The acquisition module 201 is additionally operable to before the recognition of face request is received, the face of repeated acquisition user
Image.
In the present embodiment, when the face identification system 200 is run for the first time, user's typing face of oneself may require that
As face masterplate, to create the face characteristic masterplate.Specifically, the acquisition module 201 can pass through voice or text
The mode of word, guiding user make what the camera 14 of the electronic device 1 was acquired by adjusting the orientation of the electronic device 1
User's face can be shown in preset face input interface, and then complete the face typing work.
The identification module 203 is additionally operable to, when the facial image is real human face, identify the facial image, obtain
Take the face characteristic in the facial image.
In the present embodiment, the face of user institute typing is identified in the identification module 203, therefrom extracts user people
The face characteristic of face, when next user initiates face verification, to be completed by the comparison of face characteristic to user identity
Verification.It should be pointed out that identification module 203 described herein as much as possible from the face of user institute typing should extract
The face characteristic of user, to reduce erroneous judgement probability during follow-up progress face characteristic comparison.
The memory module 206 is the skin detection for storing acquired face characteristic.The face characteristic
Masterplate is used to, when user carries out face verification, be compared by the face characteristic with active user, judge active user's
Whether identity is legal.
By above-mentioned module 201,203,206, face identification system 200 of the present invention by acquiring user's in advance
Face extracts the face characteristic in the face and is stored as face characteristic masterplate, can judge currently to use when carrying out face verification
The identity at family.
Further, the first and second embodiments based on the invention described above face identification system 200 propose the present inventor
The 3rd embodiment of face identifying system 200.
As shown in fig.4, it is the high-level schematic functional block diagram of 200 3rd embodiment of face identification system of the present invention.In this reality
It applies in example, the face identification system 200 further includes acquisition module 207 in addition to function module 201-206.Wherein:
The acquisition module 207, for obtaining the ID of the electronic device 1 and user's logon account.
In the present embodiment, the ID of the electronic device 1 refers to identity with uniqueness in the electronic device 1, can
To include but are not limited to, hardware address, factory number, product string number of the electronic device 1 etc..The user logs in account
Family refers to that the validated user of the electronic device 1 operates used account during the electronic device 1, include but are not limited to, and uses
Family logs in the account of the operating system of the electronic device 1, user logs in the account (example of application-specific in the electronic device 1
Such as wechat account, Alipay account).
The memory module 206 is additionally operable to respectively log in the skin detection with the electronic device ID, user
Account binding storage.
In the present embodiment, the memory module 206 by by the ID of the electronic device 1 and user's logon account respectively with
The face characteristic masterplate carries out binding storage, can be conveniently subsequently when 1 user of electronic device initiates face verification, advance root
According to the ID of the electronic device 1 or user's logon account, from the pre-stored face characteristic masterplate, filter out with it is described
The face characteristic masterplate of ID or user's logon account binding of electronic device 1, and then the active user's face characteristic that will be acquired
It is compared with the face character modules version.In such manner, it is possible to reduce the range of face characteristic comparison, shorten the time of face verification.
The comparing module 204 is additionally operable to obtain the people with electronic device ID or described users login account binding
Face feature templates, and the face characteristic is compared respectively with acquired skin detection.
By above-mentioned function module 204,206,207, face identification system 200 of the present invention by obtaining electricity in advance
The ID of sub-device 1 and user's logon account, and the ID of the electronic device 1 and user's logon account is special with the face respectively
Sign masterplate carries out binding storage, can be according to the ID of the electronic device 1 or user's logon account, in advance when making face verification
It is filtered out from the face characteristic masterplate of storage special with the face of the ID of the electronic device 1 or the binding of user's logon account
Masterplate is levied to be compared.In this way, reducing the range that face characteristic compares, further shorten the time of face verification, improve
User experience.
Further it is proposed that a kind of face identification method.
As shown in fig.5, it is the implementation process diagram of the present inventor's face recognition method first embodiment.In the present embodiment
In, according to different demands, the execution sequence of the step in flow chart shown in fig. 5 can change, and certain steps can be omitted.
The face identification method includes:
When receiving recognition of face request, current use is acquired by the camera 14 of the electronic device 1 by step S501
The facial image at family.
Usually, face identification functions are mainly used for verifying the identity of user, include but are not limited to, with
The identity of user is verified when family is unlocked the electronic device 1, is tested when user is paid using the electronic device 1
Identity, the identity of verification user etc. when user browses preset secret file for demonstrate,proving user.Therefore in the present embodiment, when above-mentioned
When operation associated with the face identification functions of the electronic device 1 occurs, the recognition of face request can be triggered.When connecing
When receiving the recognition of face request, the camera 14 can be called to acquire the image in 14 front of camera.The camera shooting
First 14 can be the front camera of the electronic device 1 or the rear camera of the electronic device 1.It is acquired
Image includes at least, but is not limited only to, the facial image of 1 active user of electronic device.
For example, it is assumed that 1 user preset of electronic device by the way of recognition of face come to the electronic device 1 into
Row unlock, then when the preset unlock operation triggering (such as the power key of the electronic device 1 is clicked) of the electronic device 1,
Recognition of face request is generated in the electronic device 1.The camera of the electronic device 1 can be called according to recognition of face request
14 acquire the facial image of the active user of the electronic device 1.
Step S502 carries out In vivo detection to the facial image, judges whether the facial image is real human face.If
The facial image is real human face, then enters step S503;Otherwise, return to step 501.
The photo of invalid user stealing validated user, picture etc. come through face verification in order to prevent, and the present embodiment is passing
The flow of In vivo detection is increased in the face verification flow of system.Specifically, as the active user for collecting the electronic device 1
Facial image when, by In vivo detection technology to the facial image carry out In vivo detection, judgement whether obtain the facial image
For true face.Wherein, the In vivo detection can be nodded, shaken the head by voice or text prompt user, opened one's mouth
Wait the In vivo detection mode of actions or any other suitable In vivo detection mode.The In vivo detection is existing skill
Art, details are not described herein again.
The facial image is identified in step S503, obtains the face characteristic in the facial image.
In the present embodiment, the facial image can be identified using face recognition technology, from the facial image
Middle acquisition face characteristic.The face characteristic may include, but be not limited only to, each position of face shape, face (mouth, eye, nose
Deng) the features such as position, each position shape of face, face mask.It should be noted that the face characteristic can be the people
Part face characteristic in all face characteristics or the facial image of face image.Wherein, the face recognition technology
For the prior art, details are not described herein again.
The face characteristic is compared step S504 with pre-stored skin detection, and count with it is described
The quantity of the matched face characteristic of skin detection.
In the present embodiment, if the face characteristic of a facial image is identical with a skin detection, sentence
The fixed face characteristic is matched with the skin detection.If the face characteristic of a facial image and the face characteristic mould
Plate differs, then judges that the face characteristic is mismatched with the skin detection.
For example, if the face characteristic acquired from the facial image is 4 face characteristics, and the electronics
5 skin detections are previously provided in device 1, then select a face characteristic from 4 face characteristics one by one, are come
It is compared respectively with 5 skin detections.If the face characteristic and one in 5 skin detections
Match, then judge that the face characteristic is matched with the skin detection.If conversely, the face characteristic and 5 face characteristics
Template mismatches, then judges that the face characteristic is mismatched with the skin detection.
It further, can when the face characteristic of all facial images is mismatched with the skin detection
To show corresponding prompting on the display screen 13 of the electronic device 1.It should be noted that in the present embodiment, whenever an institute
It states face characteristic to match with the skin detection, will be obtained in statistics matched described with the skin detection
Increase number one on the basis of the quantity of face characteristic, counted and the matched face characteristic of the skin detection with this
Quantity.
Step S505 when the quantity with the matched face characteristic of the skin detection reaches preset value, sentences
The fixed active user passes through face verification.
In the present embodiment, it in order to overcome in traditional recognition of face when carrying out face characteristic comparison, needs to have compared
Whether all people's face feature just can determine that the facial image of acquisition by verification, and too long in flow wastes time excessive lack
It falls into, the preset value can be no more than the arbitrary value of the skin detection sum.Meanwhile in order to ensure to compare as far as possible
To the correctness of result, which should be 50% numerical value not less than skin detection sum.For example, when using
When the preset face characteristic masterplate in family is 8, the preset value can be any one in 4,5,6,7 threes, and specific choice can
With depending on the actual demand of user.
It will be recalled from above that if the quantity with the matched face characteristic of the skin detection reaches above-mentioned default
Value, hence it is evident that can illustrate, acquire the face characteristic of image and face corresponding with the face characteristic masterplate (namely legal use
The face at family) there is higher similarity (most of matching), then it can be determined that acquired image includes and face spy
The corresponding face of masterplate is levied, that is, the active user for carrying out face verification is validated user.Therefore the current use can be judged accordingly
Family passes through the face verification.
By above-mentioned steps S501-S505, face identification method of the present invention is used by being acquired in face verification
The face characteristic of the user's facial image acquired with the skin detection is compared, is being adopted by family facial image
When collection face characteristic major part matches with the skin detection, that is, judge that the face of user passes through verification.It in this way, need not
All face characteristics of user's face are all compared, the time of face verification is shortened, improves user experience.
Further, the first embodiment based on the invention described above face identification method proposes recognition of face side of the present invention
The second embodiment of method.
As shown in fig.6, it is the implementation process diagram of the present inventor's face recognition method second embodiment.This method packet
It includes:
Step S601, before the recognition of face request is received, the facial image of repeated acquisition user.
In the present embodiment, when the face identification system 200 is run for the first time, user's typing face of oneself may require that
As face masterplate, to create the face characteristic masterplate.Specifically, it can guide and use by way of voice or word
Family enables user's face that the camera 14 of the electronic device 1 is acquired to show by adjusting the orientation of the electronic device 1
In preset face input interface, and then complete the face typing work.
Step S602 when the facial image is real human face, identifies the facial image, obtains in the facial image
Face characteristic.
In the present embodiment, the face of user institute typing can be identified, the face for therefrom extracting user's face is special
Sign, when next user initiates face verification, the verification to user identity is completed by the comparison of face characteristic.It needs to refer to
Go out, herein should from the face of user institute typing the face characteristic as much as possible for extracting user, it is follow-up to reduce
Carry out erroneous judgement probability during face characteristic comparison.
Step S603, face characteristic acquired in storage are the skin detection.The face characteristic masterplate is used for
When user carries out face verification, it is compared by the face characteristic with active user, judges whether the identity of active user closes
Method.
By above-mentioned module S601-S603, face identification method of the present invention by acquiring the face of user in advance,
It extracts the face characteristic in the face and is stored as face characteristic masterplate, the body of active user can be judged when carrying out face verification
Part.
Further, the first and second embodiments based on the invention described above face identification method propose face of the present invention
The 3rd embodiment of recognition methods.
As shown in fig.7, it is the high-level schematic functional block diagram of the present inventor's face recognition method 3rd embodiment.This method packet
It includes:
Step S701 obtains the ID of the electronic device 1 and user's logon account.
In the present embodiment, the ID of the electronic device 1 refers to identity with uniqueness in the electronic device 1, can
To include but are not limited to, hardware address, factory number, product string number of the electronic device 1 etc..The user logs in account
Family refers to that the validated user of the electronic device 1 operates used account during the electronic device 1, include but are not limited to, and uses
Family logs in the account of the operating system of the electronic device 1, user logs in the account (example of application-specific in the electronic device 1
Such as wechat account, Alipay account).
Step S702 stores the skin detection with the electronic device ID, the binding of user's login account respectively.
In the present embodiment, by by the ID of the electronic device 1 and user's logon account respectively with the face characteristic mould
Version carries out binding storage, can be conveniently subsequently when 1 user of electronic device initiates face verification, previously according to the electronic device
1 ID or user's logon account from the pre-stored face characteristic masterplate, filters out the ID with the electronic device 1
Or the face characteristic masterplate of user's logon account binding, and then by the active user's face characteristic acquired and the face character modules
Version is compared.In such manner, it is possible to reduce the range of face characteristic comparison, shorten the time of face verification.
Step S703 obtains the skin detection with electronic device ID or described users login account binding, and
The face characteristic is compared respectively with acquired skin detection.
By above-mentioned steps S701-703, face identification method of the present invention by obtaining electronic device 1 in advance
ID and user's logon account, and by the ID of the electronic device 1 and user's logon account respectively with the face characteristic masterplate into
Row binding storage, can be according to the ID of the electronic device 1 or user's logon account, in advance from storage when making face verification
The face characteristic masterplate with the ID of the electronic device 1 or the binding of user's logon account is filtered out in the face characteristic masterplate
It is compared.In this way, reducing the range that face characteristic compares, further shorten the time of face verification, improve user experience.
The embodiments of the present invention are for illustration only, do not represent the quality of embodiment.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can add the mode of required general hardware platform to realize by software, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on such understanding, technical scheme of the present invention substantially in other words does the prior art
Going out the part of contribution can be embodied in the form of software product, which is stored in a storage medium
In (such as ROM/RAM, magnetic disc, CD), used including some instructions so that a station terminal equipment (can be mobile phone, computer takes
Be engaged in device, air conditioner or the network equipment etc.) perform method described in each embodiment of the present invention.
It these are only the preferred embodiment of the present invention, be not intended to limit the scope of the invention, it is every to utilize this hair
The equivalent structure or equivalent flow shift that bright specification and accompanying drawing content are made directly or indirectly is used in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of face identification method, applied to electronic device, which is characterized in that this method includes:
When receiving recognition of face request, the facial image of active user is acquired;
In vivo detection is carried out to the facial image, judges whether the facial image is real human face;
If the facial image is real human face, the facial image is identified, obtains the face in the facial image
Feature;
The face characteristic with pre-stored skin detection is compared, and is counted and the skin detection
The quantity of the face characteristic matched;
If reaching preset value with the quantity of the matched face characteristic of the skin detection, the active user is judged
Pass through face verification.
2. face identification method as described in claim 1, which is characterized in that it is described when receiving recognition of face request, it adopts
Before the step of collecting the facial image of user, further include:
The facial image of repeated acquisition user;
When the facial image is real human face, identifies the facial image, obtain the face characteristic in the facial image;
Face characteristic acquired in storage is the skin detection.
3. face identification method as claimed in claim 2, which is characterized in that it is described when receiving recognition of face request, it adopts
Before the step of collecting the facial image of user, this method further includes:
Obtain the electronic device ID and user's login account;
The skin detection is stored respectively with the electronic device ID, the binding of user's login account.
4. face identification method as claimed in claim 3, which is characterized in that it is described by the face characteristic with it is pre-stored
Skin detection is compared, and the step of statistics and quantity of the matched face characteristic of the skin detection,
It specifically includes:
Obtain the skin detection with electronic device ID or described users login account binding;
The face characteristic is compared respectively with acquired skin detection;
If being matched there are face characteristic with the skin detection, matched what statistics obtained with the skin detection
The face characteristic quantity on the basis of increase number one.
5. such as claim 1-4 any one of them face identification methods, which is characterized in that the preset value is not less than described
50% arbitrary value of skin detection sum.
6. a kind of face identification system, runs on electronic device, which is characterized in that the system includes:
Acquisition module, for when receiving recognition of face request, acquiring the facial image of active user;
Detection module for carrying out In vivo detection to the facial image, judges whether the facial image is real human face;
Identification module, for when the facial image is real human face, being identified to the facial image, obtaining the face
Face characteristic in image;
Comparing module, for the face characteristic to be compared with pre-stored skin detection, and count with it is described
The quantity of the matched face characteristic of skin detection;
Authentication module, for when the quantity with the matched face characteristic of the skin detection reaches preset value, sentencing
The fixed active user passes through face verification.
7. face identification system as claimed in claim 6, which is characterized in that the system further includes memory module, wherein:
The acquisition module is additionally operable to before recognition of face request is received, the facial image of repeated acquisition user;
The identification module is additionally operable to, when the facial image is real human face, identify the facial image, obtain the face
Face characteristic in image;
The memory module is the skin detection for storing acquired face characteristic.
8. face identification system as claimed in claim 7, which is characterized in that the system further includes acquisition module, wherein:
The acquisition module, for obtaining the electronic device ID and user's login account;
The memory module is additionally operable to respectively tie up the verification face characteristic with the electronic device ID, user's login account
Fixed storage.
9. face identification system as claimed in claim 8, which is characterized in that the comparing module is additionally operable to:
Obtain the skin detection with electronic device ID or described users login account binding;
The face characteristic is compared respectively with acquired skin detection;
If being matched there are face characteristic with the skin detection, matched what statistics obtained with the skin detection
The face characteristic quantity on the basis of increase number one.
10. such as claim 6-9 any one of them face identification systems, which is characterized in that the preset value is not less than institute
State 50% arbitrary value of skin detection sum.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611103853.3A CN108154070A (en) | 2016-12-05 | 2016-12-05 | Face identification method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611103853.3A CN108154070A (en) | 2016-12-05 | 2016-12-05 | Face identification method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108154070A true CN108154070A (en) | 2018-06-12 |
Family
ID=62470519
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611103853.3A Pending CN108154070A (en) | 2016-12-05 | 2016-12-05 | Face identification method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108154070A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108805109A (en) * | 2018-08-07 | 2018-11-13 | 深圳市云康创新网络科技有限公司 | A kind of exercise data capture display system |
CN109522792A (en) * | 2018-10-09 | 2019-03-26 | 浙江吉利控股集团有限公司 | A kind of driving authentication system and method |
CN110008889A (en) * | 2019-03-29 | 2019-07-12 | 镇江阿贝信息科技有限公司 | Profile based on recognition of face compares matching process and system |
CN110705451A (en) * | 2019-09-27 | 2020-01-17 | 支付宝(杭州)信息技术有限公司 | Face recognition method, face recognition device, terminal and server |
-
2016
- 2016-12-05 CN CN201611103853.3A patent/CN108154070A/en active Pending
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108805109A (en) * | 2018-08-07 | 2018-11-13 | 深圳市云康创新网络科技有限公司 | A kind of exercise data capture display system |
CN108805109B (en) * | 2018-08-07 | 2024-04-23 | 深圳市天玖隆科技有限公司 | Motion data capturing and displaying system |
CN109522792A (en) * | 2018-10-09 | 2019-03-26 | 浙江吉利控股集团有限公司 | A kind of driving authentication system and method |
CN110008889A (en) * | 2019-03-29 | 2019-07-12 | 镇江阿贝信息科技有限公司 | Profile based on recognition of face compares matching process and system |
CN110705451A (en) * | 2019-09-27 | 2020-01-17 | 支付宝(杭州)信息技术有限公司 | Face recognition method, face recognition device, terminal and server |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10699103B2 (en) | Living body detecting method and apparatus, device and storage medium | |
US10817707B2 (en) | Attack sample generating method and apparatus, device and storage medium | |
CN111886842B (en) | Remote user authentication using threshold-based matching | |
CN108399665A (en) | Method for safety monitoring, device based on recognition of face and storage medium | |
CN107093066A (en) | Service implementation method and device | |
CN106599872A (en) | Method and equipment for verifying living face images | |
CN108154070A (en) | Face identification method and device | |
CN110322317B (en) | Transaction data processing method and device, electronic equipment and medium | |
CN106557678A (en) | A kind of intelligent terminal's mode switching method and its device | |
CN107609508A (en) | A kind of face identification method, terminal and computer-readable recording medium | |
CN110247898B (en) | Identity verification method, identity verification device, identity verification medium and electronic equipment | |
US20170228582A1 (en) | Fingerprint authentication display device and authentication display method | |
JP6969663B2 (en) | Devices and methods for identifying the user's imaging device | |
WO2018045977A1 (en) | Shared resource display method, device and storage medium | |
US10521580B1 (en) | Open data biometric identity validation | |
WO2019174073A1 (en) | Method and device for modifying client information in conversation, computer device and storage medium | |
CN108805005A (en) | Auth method and device, electronic equipment, computer program and storage medium | |
CN107995170A (en) | Auth method, device, computer equipment and computer-readable recording medium | |
CN108241999A (en) | A kind of generation method of invoice information, apparatus and system | |
CN109191635A (en) | Objective method, apparatus and storage medium are sentenced based on face recognition technology | |
CN109635878A (en) | A kind of painting and calligraphy fidelity identification method and device | |
CN107656959B (en) | Message leaving method and device and message leaving equipment | |
CN112989299A (en) | Interactive identity recognition method, system, device and medium | |
CN103984415B (en) | A kind of information processing method and electronic equipment | |
CN108734099A (en) | Auth method and device, electronic equipment, computer program and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180612 |