CN106407914A - Method for detecting human faces, device and remote teller machine system - Google Patents
Method for detecting human faces, device and remote teller machine system Download PDFInfo
- Publication number
- CN106407914A CN106407914A CN201610798437.3A CN201610798437A CN106407914A CN 106407914 A CN106407914 A CN 106407914A CN 201610798437 A CN201610798437 A CN 201610798437A CN 106407914 A CN106407914 A CN 106407914A
- Authority
- CN
- China
- Prior art keywords
- face
- recognized
- identified
- images
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
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
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/165—Detection; Localisation; Normalisation using facial parts and geometric relationships
-
- 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
- G06V40/40—Spoof detection, e.g. liveness detection
- G06V40/45—Detection of the body part being alive
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07F—COIN-FREED OR LIKE APPARATUS
- G07F19/00—Complete banking systems; Coded card-freed arrangements adapted for dispensing or receiving monies or the like and posting such transactions to existing accounts, e.g. automatic teller machines
- G07F19/20—Automatic teller machines [ATMs]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Collating Specific Patterns (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Geometry (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Business, Economics & Management (AREA)
Abstract
The present invention provides a method for detecting human faces, a device for detecting human faces and a remote teller machine system. The method includes the following steps that: an image pair to be recognized is acquired, wherein the image pair to be recognized includes two images to be recognized which are acquired by two cameras according to a human face to be recognized respectively; the depth information of the human face to be recognized is obtained according to the images to be recognized; a light spot pattern formed by the human face to be recognized under the illumination of an infrared structure is obtained; the texture information of the human face to be recognized is obtained according to the light spot pattern; and whether the human face to be recognized is a living body is determined based on the depth information and the texture information. The method, the device and the remote teller machine system have the advantages of low cooperation requirements, high speed and high security.
Description
Technical field
The present invention relates to field of face identification, relate more specifically to a kind of method for detecting face, device and long-range
Teller machine (ATM) system.
Background technology
Currently, unattended automation authentication system has been obtained for extensively applying, such as bank's long-distance video
Automatic teller machine (VTM), access control system of residential community etc..Artificial cognition can be solved using the authentication system based on recognition of face and make
The problem being produced with media such as IC-cards.Before recognition of face, can detect whether the face collecting belongs to live body first.Mesh
Front conventional In vivo detection mode mainly has two kinds:Do action using common camera at random by formula to be detected, with
And detected using bright pupil effect.But both modes have respective problem.Detection mode based on common camera
User is needed to do several actions at random, cooperation difficulty is higher, and the time is longer, and for mask, video and papery photo
Attack it is not easy to identify.The equipment that detection mode based on bright pupil effect is easily combined imitation pupil by various masks is attacked, with
There is safety problem in sample.
Content of the invention
Propose the present invention in view of the problems referred to above.The invention provides a kind of method for detecting face, device
With remote teller machine system.
According to an aspect of the present invention, there is provided a kind of method for detecting face.The method includes:Obtain figure to be identified
As right, two images to be recognized that described images to be recognized is gathered for face to be identified by two cameras respectively to inclusion;
According to described images to be recognized to the depth information obtaining described face to be identified;Obtain described face to be identified in infrared structure
The hot spot pattern being formed under light irradiation;Obtain the texture information of described face to be identified according to described hot spot pattern;And combine
Described depth information and described texture information determine whether described face to be identified belongs to live body.
Exemplarily, methods described further includes:If for collection in the preset period of time after start time
All images to be recognized are not belonging to live body it is determined that In vivo detection fails to the described face to be identified of determination;And if be directed to
In described preset period of time after described start time, the specific images to be recognized of collection to be identified face described to determination belongs to
In live body it is determined that In vivo detection passes through.
Exemplarily, pass through afterwards in described determination In vivo detection, methods described further includes:When in described beginning
Carve and adopt to the time period in the collection moment of described specific images to be recognized pair, by the specific camera head in described two cameras
The top-quality images to be recognized of face is selected at least part of images to be recognized of collection;And utilize selected figure to be identified
As recognition of face is carried out to described face to be identified.
Exemplarily, described using selected images to be recognized, described face to be identified is carried out recognition of face it
Before, methods described further includes:Obtain the ID card information of the affiliated object of described face to be identified, described ID card information bag
Include identity card face;Described using selected images to be recognized, recognition of face carried out to described face to be identified and include:By institute
The face described to be identified stated in selected images to be recognized is contrasted with described identity card face, to wait to know described in determining
Whether others' face is consistent with described identity card face.
Exemplarily, described using selected images to be recognized, recognition of face carried out to described face to be identified and include:
Face described to be identified in described selected images to be recognized is contrasted with the known face in the first database, with
Determine whether described face to be identified is one of known face in described first database.
Exemplarily, the described time period from the collection moment in described start time to described specific images to be recognized pair
Interior, top-quality by selection face at least part of images to be recognized of the specific camera head collection in described two cameras
Images to be recognized includes:Wait to know for each in described at least part of images to be recognized according to one or more in following parameters
Other image scoring:Face brightness in images to be recognized for the described face to be identified, sidelight backlight degree, pitching degree, tilt
Degree, degree of eye opening and degree of opening one's mouth;And select fraction highest images to be recognized as the top-quality images to be recognized of face.
Exemplarily, depth information described in described combination and described texture information determine whether described face to be identified belongs to
Live body includes:If described texture information meets fell grain distribution rule and described depth information meets face depth profile
Rule, it is determined that described face to be identified belongs to live body, otherwise determines that described face to be identified is not belonging to live body.
Exemplarily, methods described also includes:In described acquisition images to be recognized pair, output action information, with
Indicate that the affiliated object of described face to be identified executes action corresponding with described action prompt information.
Exemplarily, before described output action information, methods described also includes:Random from the second database
Obtain at least one action prompt information, wherein, described second database includes multiple different action prompt information;Described defeated
Go out action information to include:The action prompt information being obtained by text importing form and/or the output of voice broadcast form.
According to a further aspect of the invention, a kind of device for detecting face is provided, including:Image collection module, is used for
Obtain images to be recognized pair, described images to be recognized is directed to two of face collection to be identified respectively to inclusion by two cameras
Images to be recognized;Depth information obtains module, for the depth to the described face to be identified of acquisition according to described images to be recognized
Information;Hot spot pattern acquisition module, for obtaining the hot spot pattern that described face to be identified is formed under infrared structure light irradiation;
Texture information obtains module, for obtaining the texture information of described face to be identified according to described hot spot pattern;And live body inspection
Survey module, for determining whether described face to be identified belongs to live body with reference to described depth information and described texture information.
Exemplarily, described device further includes:Failure determining module, if for for after start time
In preset period of time, all images to be recognized of collection are not belonging to live body it is determined that In vivo detection loses to the described face to be identified of determination
Lose;And pass through determining module, if for specific for gather in the described preset period of time after described start time
Images to be recognized belongs to live body it is determined that In vivo detection passes through to the described face to be identified of determination.
Exemplarily, described device further includes:Selecting module, for specific treating from described start time to described
At least partly treating in the time period in collection moment of identification image pair, by the specific camera head collection in described two cameras
The top-quality images to be recognized of face is selected in identification image;And face recognition module, for waiting to know using selected
Other image carries out recognition of face to described face to be identified.
Exemplarily, described device further includes:ID card information acquisition module, for obtaining described face to be identified
The ID card information of affiliated object, described ID card information includes identity card face;Described face recognition module includes:First pair
Ratio submodule, right for carrying out the face described to be identified in described selected images to be recognized and described identity card face
Ratio is to determine whether described face to be identified is consistent with described identity card face.
Exemplarily, described face recognition module includes:Second contrast submodule, for will be described selected to be identified
Face described to be identified in image is contrasted with the known face in the first database, to determine that described face to be identified is
No is one of known face in described first database.
Exemplarily, described selecting module includes:Scoring submodule, for according to one or more in following parameters being
Each images to be recognized scoring in described at least part of images to be recognized:People in images to be recognized for the described face to be identified
Face brightness, sidelight backlight degree, pitching degree, lateral inclination, degree of eye opening and degree of opening one's mouth;And selection submodule, for selecting to divide
Number highest images to be recognized is as the top-quality images to be recognized of face.
Exemplarily, described In vivo detection module includes:First determination sub-module, if met for described texture information
Fell grain distribution rule and described depth information meets face depth profile rule it is determined that described face to be identified belongs to
Live body;And second determination sub-module, if not meeting fell grain distribution rule or described depth for described texture information
Degree information does not meet face depth profile rule it is determined that described face to be identified is not belonging to live body.
Exemplarily, described device also includes:Action prompt module, to be identified for obtaining in described image acquisition module
During image pair, output action information, to indicate the execution of described face to be identified affiliated object and described action prompt information
Corresponding action.
Exemplarily, described device also includes:Information acquisition module, for obtain at random from the second database to
Few action prompt information, wherein, described second database includes multiple different action prompt information;Described action prompt
Module includes:Information output sub-module, dynamic for obtained by text importing form and/or the output of voice broadcast form
Make information.
According to a further aspect of the invention, provide a kind of remote teller machine system, described system includes two cameras, infrared
Structured light device and the device being previously used for detection face, described two cameras are used for for described face to be identified
Two images to be recognized of collection, obtain images to be recognized pair, and described images to be recognized is obtained mould to being sent to described image
Block;Described infrared structure light emitting devices is used for launching infrared structure light to described face to be identified, with described people to be identified
Form described hot spot pattern on the face.
Exemplarily, described system also includes display and/or speech ciphering equipment, and described display was used for described in real-time display
The images to be recognized of two camera collections, and receive action prompt information and by literary composition from the described device for detecting face
Word shows described action prompt information;Described speech ciphering equipment is used for carrying from the described described action of reception of the device for detecting face
Show information and pass through action prompt information described in voice broadcast;Wherein, described action prompt information be used for indicating described to be identified
The affiliated object of face executes action corresponding with described action prompt information.
The method for detecting face according to embodiments of the present invention, device and remote teller machine system, it is without user
Cooperation, therefore cooperation require low, speed fast, additionally, the method carries out In vivo detection with reference to depth information and texture information, permissible
Effectively prevent mask attack etc. from attacking, its security is higher.
Brief description
By combining accompanying drawing, the embodiment of the present invention is described in more detail, the above-mentioned and other purpose of the present invention,
Feature and advantage will be apparent from.Accompanying drawing is used for providing the embodiment of the present invention is further understood, and constitutes explanation
A part for book, is used for explaining the present invention together with the embodiment of the present invention, is not construed as limiting the invention.In the accompanying drawings,
Identical reference number typically represents same parts or step.
Fig. 1 illustrates to set for the exemplary electron realizing the method and apparatus for detecting face according to embodiments of the present invention
Standby schematic block diagram;
Fig. 2 illustrates the indicative flowchart of the method for detecting face according to an embodiment of the invention;
Fig. 3 illustrates the schematic block diagram of the device for detecting face according to an embodiment of the invention;And
Fig. 4 illustrates the schematic block diagram of the system for detecting face according to an embodiment of the invention.
Specific embodiment
So that the object, technical solutions and advantages of the present invention become apparent from, describe root below with reference to accompanying drawings in detail
Example embodiment according to the present invention.Obviously, described embodiment is only a part of embodiment of the present invention, rather than this
Bright whole embodiments are not it should be appreciated that the present invention is limited by example embodiment described herein.Described in the present invention
The embodiment of the present invention, the obtained all other embodiment in the case of not paying creative work of those skilled in the art
All should fall under the scope of the present invention.
In order to solve conventional In vivo detection technology (the In vivo detection technology that for example existing authentication system is adopted)
Defect, the embodiment of the present invention proposes a kind of side carrying out In vivo detection (and subsequent recognition of face) based on binocular camera
Method.
First, to describe with reference to Fig. 1 for realizing the method and apparatus for detecting face according to embodiments of the present invention
Exemplary electronic device 100.
As shown in figure 1, electronic equipment 100 includes one or more processors 102, one or more storage device 104, defeated
Enter device 106, output device 108 and image collecting device 110, these assemblies pass through bus system 112 and/or other forms
Bindiny mechanism's (not shown) interconnection.It should be noted that the assembly of electronic equipment 100 shown in Fig. 1 and structure are exemplary, and
Nonrestrictive, as needed, described electronic equipment can also have other assemblies and structure.
Described processor 102 can be CPU (CPU) or have data-handling capacity and/or instruction execution
The processing unit of the other forms of ability, and the other assemblies in described electronic equipment 100 can be controlled desired to execute
Function.
Described storage device 104 can include one or more computer programs, and described computer program can
To include various forms of computer-readable recording mediums, such as volatile memory and/or nonvolatile memory.Described easy
The property lost memory for example can include random access memory (RAM) and/or cache memory (cache) etc..Described non-
Volatile memory for example can include read-only storage (ROM), hard disk, flash memory etc..In described computer-readable recording medium
On can store one or more computer program instructions, processor 102 can run described program instruction, to realize hereafter institute
The client functionality (realized by processor) in the embodiment of the present invention stated and/or other desired function.In described meter
Various application programs and various data can also be stored in calculation machine readable storage medium storing program for executing, such as described application program using and/or
Various data producing etc..
Described input unit 106 can be the device for input instruction for the user, and can include keyboard, mouse, wheat
Gram one or more of wind and touch-screen etc..
Described output device 108 can export various information (such as image and/or sound) to outside (such as user), and
And one or more of display, loudspeaker etc. can be included.
Described image harvester 110 can gather desired image (for example needing to carry out the image of In vivo detection), and
And acquired image is stored in described storage device 104 so that other assemblies use.Image collecting device 110 can be adopted
Realized with any suitable equipment, the shooting of such as gate control system is first-class.Image collecting device 110 is only example, electronic equipment
100 can not include image collecting device 110.
Exemplarily, for realizing the exemplary electron of the method and apparatus for detecting face according to embodiments of the present invention
Equipment can be realized on the equipment of personal computer or remote server etc..
Below, with reference to Fig. 2, the according to embodiments of the present invention method being used for detecting face will be described.Fig. 2 illustrates according to this
The indicative flowchart of the method 200 for detecting face of one embodiment of invention.As shown in Fig. 2 for detecting face
Method 200 comprises the following steps.
In step S210, obtain images to be recognized pair, images to be recognized is waited to know to including being directed to by two cameras respectively
Two images to be recognized of others' face collection.
Two cameras form binocular camera, and it can simulate the eyes of the mankind.Two cameras in different positions,
Gather the image of same target from different visual angles, the depth of this object can be obtained based on the image that two cameras collect
Degree information.
Images to be recognized can come from the camera of outside, is sent to electronic equipment 100 by outside camera and is lived
(and subsequent recognition of face) is surveyed in health check-up.Additionally, images to be recognized can also be by the image collecting device 110 of electronic equipment 100
Collection obtains, and realizes above-mentioned two camera using image collecting device 110.Image collecting device 110 can will gather
To image be sent to processor 102, In vivo detection (and subsequent recognition of face) is carried out by processor 102.Images to be recognized
Can be original image or the image obtaining after original image is pre-processed.
In step S220, according to images to be recognized to the depth information obtaining face to be identified.
The depth information of face to be identified can be obtained from the images to be recognized of collection under two different visual angles.Specifically
Ground, can based on principle of parallax, using images to be recognized to the three-D profile determining face to be identified, and profile can be obtained
The three-dimensional coordinate (i.e. the depth information of face to be identified) of upper any characteristic point.
In step S230, obtain the hot spot pattern that face to be identified is formed under infrared structure light irradiation.
Infrared structure optical transmitting sets can be placed in the middle of two cameras, using infrared structure optical transmitting set to be identified
Face launches infrared structure light.Under infrared structure light irradiation, hot spot pattern is formed on face to be identified.Two can be utilized
Arbitrary camera in camera receives this hot spot pattern, is then communicated to the processor (processor for example shown in Fig. 1 of rear end
102) processed.The processor of two cameras, infrared structure optical transmitting set and rear end can form binocular stereo vision system
System.
In step S240, obtain the texture information of face to be identified according to hot spot pattern.
Different material-structures can form different hot spot patterns under structure light.Processor can be according to receiving
Hot spot pattern obtains the texture information of face, i.e. the material property on face surface.If it find that the texture information of face to be identified
Do not meet fell grain distribution rule it is determined that face to be identified is not live body, be judged as that mask is attacked.
In step S250, determine whether face to be identified belongs to live body in conjunction with depth information and texture information.
Because the mask that attacker can use apery skin material is implemented to attack, therefore, even if the texture of face to be identified
Information meets fell grain distribution rule, also not necessarily can determine that face to be identified belongs to live body, therefore can tie further
Close depth information and judge whether face to be identified belongs to live body.It should be appreciated that real face typically has fluctuating, for example,
The coordinate depth of its eye and nose areas is different, and gap is larger, and the mask fluctuating very little made of apery skin material,
The coordinate depth difference of eyes and nose areas is away from very little.Therefore, can determine whether that face to be identified is in conjunction with depth information
No belong to live body.
It is to be appreciated that two cameras can gather an images to be recognized to it is also possible to collection is multiple to be identified
Image was to that is to say, that for for each camera, it both can gather still image it is also possible to gather video.In shooting
In the case of head collection video, images to be recognized belongs to the frame in video, and for each images to be recognized to can
Execution above-mentioned steps S210-S250, to determine whether face to be identified belongs to live body.
It should be appreciated that the execution sequence of each step shown in Fig. 2 is only exemplary rather than limitation of the present invention, the present invention can
To have other rational execution sequences.For example, any one in step S230 and step S240 can step S210 it
Before, execute afterwards or simultaneously, or before step S220, execute afterwards or simultaneously.
Method for detecting face according to embodiments of the present invention coordinates without user, and therefore cooperation requires low, speed
Hurry up, additionally, the method carries out In vivo detection with reference to depth information and texture information, can effectively prevent mask attack etc. from attacking,
Its security is higher.
Exemplarily, the method for detecting face according to embodiments of the present invention can have memory and processor
Unit or system in realize.
Method for detecting face according to embodiments of the present invention can be deployed in IMAQ end, for example, it is possible to portion
Administration is at the IMAQ end of bank VTM OR gate access control system.Alternatively, the side for detecting face according to embodiments of the present invention
Method can also be deployed in server end (or high in the clouds) place.For example, it is possible to gather images to be recognized in client, client will gather
To images to be recognized send server end (or high in the clouds) to, In vivo detection is carried out by server end (or high in the clouds) (and subsequent
Recognition of face).
According to embodiments of the present invention, method 200 may further include:If during for default after start time
In section, all images to be recognized of collection are not belonging to live body it is determined that In vivo detection fails to determination face to be identified;And such as
The specific images to be recognized that fruit is directed to collection in the preset period of time after start time belongs to live body to determination face to be identified,
Then determine that In vivo detection passes through.
Preset period of time can be any suitable period, and it can set as needed, and the present invention is not limited to this.
For example, preset period of time can be 10 seconds, 20 seconds, 30 seconds, 1 minute etc..
In the present embodiment, two camera collections can be video, and images to be recognized is the frame in video.Assume
After detection starts, two cameras can collect 200 images to be recognized pair in preset period of time, i.e. each camera
Collect 200 images to be recognized respectively.Exemplarily, images to be recognized pair can be gathered, while determining people to be identified
Whether face belongs to live body.If when collecting the 150th images to be recognized pair, determine that face to be identified belongs to live body, then may be used
Passed through with determination In vivo detection, subsequent recognition of face can be entered.150th images to be recognized specific is waited to know to for above-mentioned
Other image pair.If still failing to when having gathered 200 images to be recognized pair determine that face to be identified belongs to live body, permissible
Determine In vivo detection failure, in such a case, it is possible to terminate the whole process detecting face, no longer carry out subsequent face
Identification process is it is possible to export failure result.
Set preset period of time and can facilitate the detection time controlling In vivo detection as needed.
According to embodiments of the present invention, determining In vivo detection by afterwards, method 200 may further include:From opening
Begin in the time period in moment to the collection moment of specific images to be recognized pair, by the specific camera head collection in two cameras
At least partly select the top-quality images to be recognized of face in images to be recognized;And utilize selected images to be recognized pair
Face to be identified carries out recognition of face.
Specific camera head can be any one camera in two cameras, and the present invention is not limited to this.
Continue to use above-mentioned example it is assumed that after detection starts, two cameras can collect 200 in preset period of time
Images to be recognized pair, if when collecting the 150th images to be recognized pair, determines that face to be identified belongs to live body, then permissible
Select at least a portion from front 150 images to be recognized being gathered by certain camera that face is top-quality waits to know
Other image.Top-quality images to be recognized is selected to be conducive to subsequently carrying out recognition of face.Face quality is better, detected
Face to be identified is more clear, is more possible to close to real face, the degree of accuracy of therefore recognition of face is also higher.
Recognition of face can include confirming face, that is, one-to-one carry out facial image contrast, or face identification, that is, a pair
Carry out facial image contrast more, be described below in conjunction with specific embodiments.
According to an embodiment, before recognition of face being carried out to face to be identified using selected images to be recognized,
Method 200 may further include:Obtain the ID card information of the affiliated object of face to be identified, described ID card information includes body
Part witness's face;Carry out recognition of face using selected images to be recognized to face to be identified can include:Treat selected
Face to be identified in identification image is contrasted with identity card face, with determine face to be identified whether with identity card face one
Cause.
The present embodiment can apply to such as bank VTM (Video Teller Machine, remote teller machine or long-range
Video automatic teller machine) scene such as authentication in self-service business handling.For example, in the self-service business handling of bank VTM, Yong Huke
To show the identity card of oneself, it is scanned by the scanner in VTM to obtain the ID card information of user.ID card information can
To include identity card face, it is, of course, also possible to the information such as including identification card number.After obtaining ID card information, permissible
Processed by the local processor of VTM or ID card information can be transferred to long-range server end (or high in the clouds) and carried out
Process.Subsequently acquired identity card face and face to be identified can be entered by native processor or server end (or high in the clouds)
Row contrast, confirms that face to be identified indicates whether same person with the face on identity card.Participate in contrast face to be identified be
From above-mentioned selected face top-quality images to be recognized detection with identify.
In above-mentioned face recognition process, due to having carried out In vivo detection in advance, therefore can prevent certain user from utilizing
Other people photo and identity card carry out authentication.
According to another embodiment, carrying out recognition of face using selected images to be recognized to face to be identified can wrap
Include:Face to be identified in selected images to be recognized is contrasted with the known face in the first database, to determine
Whether face to be identified is one of known face in the first database.
The present embodiment can apply to the scenes such as access control.For example, in gate control system application, can read and deposit
Contain gate control system responsible region mandate enter personnel (such as community resident) human face data database, that is, first number
According to storehouse.When someone needs to enter this region, can by all known face in face to be identified and the first database one by one
Contrasted, to determine the whether qualified entrance of the affiliated object of face to be identified.This way to manage with conventional gate control system
Similar, this is not repeated herein.
According to embodiments of the present invention, from start time to specific images to be recognized pair collection the moment time period in,
Select face top-quality to be identified at least part of images to be recognized by the specific camera head collection in two cameras
Image can include:It is each images to be recognized at least part of images to be recognized according to one or more in following parameters
Scoring:Face brightness in images to be recognized for the face to be identified, sidelight backlight degree, pitching degree, lateral inclination, eye opening degree and
Degree of opening one's mouth;And select fraction highest images to be recognized as the top-quality images to be recognized of face.
Face brightness, sidelight backlight degree, pitching degree, lateral inclination, degree of eye opening and these parameters of degree of opening one's mouth can serve as
Evaluate the index of face quality.Certainly, These parameters are only exemplary rather than limitation of the present invention, and the present invention can adopt other
Suitable index is evaluating face quality.The face brightness of face to be identified wherein is high, sidelight backlight degree is low, face is just to taking the photograph
Picture head (i.e. pitching degree and lateral inclination are low), the images to be recognized opened eyes, shut up belong to the higher image of face quality.Always
According to the attitude of face to be identified in each images to be recognized, illumination condition etc., it, may determine that face quality is high or low,
One scoring is provided for each images to be recognized, for evaluating the face quality of this images to be recognized.Subsequently, can be from above-mentioned
At least partly select fraction highest images to be recognized as the top-quality images to be recognized of face in images to be recognized, be used for
Subsequent recognition of face.
According to embodiments of the present invention, step S250 can include:If texture information meets fell grain distribution rule simultaneously
And depth information meets face depth profile rule it is determined that face to be identified belongs to live body, otherwise determines face to be identified not
Belong to live body.
In some examples of the present invention, method 200 may further include:In execution step S210, output action carries
Show information, to indicate the execution of face to be identified affiliated object and this corresponding action of action prompt information.Exemplarily, action carries
Show that information can include the information with regard to the action such as open one's mouth, shut up, close one's eyes, open eyes, nod, shake the head, smile, for example, when
When action prompt information is the information with regard to nodding, that is, indicate face to be identified affiliated object execution nodding action.
Further, according to the present invention one exemplary embodiment, before output action information, method 200 also may be used
To include:Obtain at least one action prompt information from the second database at random, wherein, described second database includes multiple
Different action prompt information;Described output action information includes:By text importing form and/or voice broadcast form
The action prompt information that output obtains.
Specifically, action prompt information Store to the second database (can be stored multiple different action prompts
Information) in it is possible to randomly select one or more action prompt information from the second database, and according to random or
Specifically sequentially point out face to be identified affiliated object execution respective action.And text importing form and/or voice can be passed through
Report form provides, to the affiliated object of face to be identified, the action prompt information obtaining.In other examples, in people to be identified
When the affiliated object of face is accurately finished respective action or fails to be accurately finished respective action according to action prompt information, permissible
(for example, to hook icon) and/or the affiliated object of verbal announcement face to be identified are shown by text importing, icon.
Understand as described above, texture information and depth information can reflect that face to be identified is people to a certain extent
Face or mask, video, photo etc., can more accurately determine whether face to be identified belongs to live body in conjunction with the two.As
The fell grain distribution rule of basis for estimation and face depth profile rule can be set based on theoretical or experience.
According to a further aspect of the invention, provide a kind of device for detecting face.Fig. 3 shows according to the present invention one
The schematic block diagram of the device 300 for detecting face of embodiment.
As shown in figure 3, the device 300 for detecting face according to embodiments of the present invention include image collection module 310,
Depth information obtains module 320, hot spot pattern acquisition module 330, texture information acquisition module 340 and In vivo detection module 350.
Image collection module 310 is used for obtaining images to be recognized pair, and described images to be recognized is taken the photograph by two respectively to inclusion
Two images to be recognized face to be identified being gathered as scalp acupuncture.Image collection module 310 can electronic equipment as shown in Figure 1
In processor 102 Running storage device 104 in storage programmed instruction realizing.
Depth information obtains module 320 and is used for according to described images to be recognized to the depth letter obtaining described face to be identified
Breath.Depth information obtains module 320 and can deposit in processor 102 Running storage device 104 in electronic equipment as shown in Figure 1
The programmed instruction of storage is realizing.
Hot spot pattern acquisition module 330 is used for obtaining the hot spot that described face to be identified is formed under infrared structure light irradiation
Pattern.Hot spot pattern acquisition module 330 can be in processor 102 Running storage device 104 in electronic equipment as shown in Figure 1
The programmed instruction of storage is realizing.
Texture information obtains module 340 and is used for obtaining the texture information of described face to be identified according to described hot spot pattern.
Texture information obtains module 340 and can store in processor 102 Running storage device 104 in electronic equipment as shown in Figure 1
Programmed instruction realizing.
In vivo detection module 350 is used for determining that described face to be identified is with reference to described depth information and described texture information
No belong to live body.In vivo detection module 350 can processor 102 Running storage device 104 in electronic equipment as shown in Figure 1
The programmed instruction of middle storage is realizing.
According to embodiments of the present invention, described device 300 further includes:Failure determining module, if opened for being directed to
In preset period of time after moment beginning, all images to be recognized of collection are not belonging to live body to the described face to be identified of determination, then really
Determine In vivo detection failure;And pass through determining module, if for for the described preset period of time after described start time
The specific images to be recognized of interior collection belongs to live body it is determined that In vivo detection passes through to the described face to be identified of determination.
According to embodiments of the present invention, described device 300 further includes:Selecting module, for from described start time
To the time period in the collection moment of described specific images to be recognized pair, by the specific camera head collection in described two cameras
At least part of images to be recognized in select the top-quality images to be recognized of face;And face recognition module, for utilizing
Selected images to be recognized carries out recognition of face to described face to be identified.
According to embodiments of the present invention, described device 300 further includes:ID card information acquisition module, for obtaining
State the ID card information of the affiliated object of face to be identified, described ID card information includes identity card face;Described recognition of face mould
Block includes:First contrast submodule, for by the face described to be identified in described selected images to be recognized and described body
Part witness's face is contrasted, to determine whether described face to be identified is consistent with described identity card face.
According to embodiments of the present invention, described face recognition module includes:Second contrast submodule, for will be described selected
Images to be recognized in face described to be identified contrasted with the known face in the first database, to wait to know described in determining
Whether others' face is one of known face in described first database.
According to embodiments of the present invention, described selecting module includes:Scoring submodule, for according in following parameters
Or multinomial each images to be recognized scoring in described at least part of images to be recognized:Described face to be identified is in figure to be identified
Face brightness in picture, sidelight backlight degree, pitching degree, lateral inclination, degree of eye opening and degree of opening one's mouth;And selection submodule, use
In selection fraction highest images to be recognized as the top-quality images to be recognized of face.
According to embodiments of the present invention, described In vivo detection module 350 includes:First determination sub-module, if for described
Texture information meets fell grain distribution rule and described depth information meets face depth profile rule it is determined that described treat
Identification face belongs to live body;And second determination sub-module, if not meeting fell grain distribution rule for described texture information
Restrain or described depth information does not meet face depth profile rule it is determined that described face to be identified is not belonging to live body.
According to embodiments of the present invention, described device 300 further includes:Action prompt module (not shown), is used for
When described image acquisition module obtains images to be recognized pair, output action information, to indicate described face institute to be identified
Belong to object and execute action corresponding with described action prompt information.
According to embodiments of the present invention, described device also includes information acquisition module (not shown), described action
Reminding module (not shown) includes information output sub-module (not shown).Wherein, information acquisition module
For obtaining at least one action prompt information from the second database at random, described second database includes multiple different moving
Make information, information output sub-module is used for exporting acquisition by text importing form and/or voice broadcast form
Action prompt information.
Those of ordinary skill in the art are it is to be appreciated that combine the list of each example of the embodiments described herein description
Unit and algorithm steps, being capable of being implemented in combination in electronic hardware or computer software and electronic hardware.These functions are actually
To be executed with hardware or software mode, the application-specific depending on technical scheme and design constraint.Professional and technical personnel
Each specific application can be used different methods to realize described function, but this realization is it is not considered that exceed
The scope of the present invention.
Fig. 4 shows the schematic block diagram of the system 400 for detecting face according to an embodiment of the invention.For
The system 400 of detection face includes image collecting device 410, storage device 420 and processor 430.
Image collecting device 410 is used for gathering images to be recognized.Image collecting device 410 is optional, for detecting people
The system 400 of face can not include image collecting device 410.
Described storage device 420 stores for realizing the phase in the method for detecting face according to embodiments of the present invention
Answer the program code of step.
Described processor 430 is used for running the program code of storage in described storage device 420, to execute according to the present invention
The corresponding steps of the method for detecting face of embodiment, and for realize according to embodiments of the present invention for detecting people
Image collection module 310 in the device of face, depth information obtain module 320, hot spot pattern acquisition module 330, texture information
Obtain module 340 and In vivo detection module 350.
In one embodiment, described program code make when being run by described processor 430 described for detecting face
System 400 executes following steps:Obtain images to be recognized pair, described images to be recognized is directed to by two cameras respectively to inclusion
Two images to be recognized of face collection to be identified;According to described images to be recognized to the depth letter obtaining described face to be identified
Breath;Obtain the hot spot pattern that described face to be identified is formed under infrared structure light irradiation;Institute is obtained according to described hot spot pattern
State the texture information of face to be identified;And determine that described face to be identified is with reference to described depth information and described texture information
No belong to live body.
In one embodiment, described program code make when being run by described processor 430 described for detecting face
System 400 executes further:If for all images to be recognized gathering in the preset period of time after start time to true
Fixed described face to be identified is not belonging to live body it is determined that In vivo detection fails;And if for after described start time
Described preset period of time in collection specific images to be recognized to determine described face to be identified belong to live body it is determined that live body inspection
Survey is passed through.
In one embodiment, make when described program code is run by described processor 430 described in be used for detecting face
The step passed through of the determination In vivo detection performed by system 400 after, when described program code is run by described processor 430
The described system 400 for detecting face is made to execute further:From in described start time to described specific images to be recognized pair
Collection the moment time period in, by described two cameras specific camera head collection at least part of images to be recognized in
Select the top-quality images to be recognized of face;And using selected images to be recognized, pedestrian is entered to described face to be identified
Face identifies.
In one embodiment, make when described program code is run by described processor 430 described in be used for detecting face
System 400 performed by using selected images to be recognized described face to be identified is carried out recognition of face step it
Before, described program code makes the described system 400 for detecting face execute further when being run by described processor 430:Obtain
Take the ID card information of the affiliated object of described face to be identified, described ID card information includes identity card face;Described program generation
Code makes the described utilization performed by system 400 for detecting face selected to be identified when being run by described processor 430
The step that image carries out recognition of face to described face to be identified includes:To treat described in described selected images to be recognized
Identification face is contrasted with described identity card face, with determine described face to be identified whether with described identity card face one
Cause.
In one embodiment, described program code make when being run by described processor 430 described for detecting face
Being included using the step that selected images to be recognized carries out recognition of face to described face to be identified performed by system 400:
Face described to be identified in described selected images to be recognized is contrasted with the known face in the first database, with
Determine whether described face to be identified is one of known face in described first database.
In one embodiment, described program code make when being run by described processor 430 described for detecting face
Performed by system 400 from described start time to described specific images to be recognized pair collection the moment time period in, by
Select at least part of images to be recognized of specific camera head collection in described two cameras that face is top-quality waits to know
The step of other image includes:Treated for each in described at least part of images to be recognized according to one or more in following parameters
Identification image scoring:Face brightness in images to be recognized for the described face to be identified, sidelight backlight degree, pitching degree, lateral tilting
Gradient, degree of eye opening and degree of opening one's mouth;And select fraction highest images to be recognized as the top-quality images to be recognized of face.
In one embodiment, described program code make when being run by described processor 430 described for detecting face
Depth information described in combination performed by system 400 and described texture information determine whether described face to be identified belongs to live body
Step includes:If described texture information meets fell grain distribution rule and described depth information meets face depth profile
Rule, it is determined that described face to be identified belongs to live body, otherwise determines that described face to be identified is not belonging to live body.
In one embodiment, described program code make when being run by described processor 430 described for detecting face
, when executing described acquisition images to be recognized to step, output action information, to indicate described face to be identified for system 400
Affiliated object execution and this corresponding action of action prompt information.
In one embodiment, make when described program code is run by described processor 430 described in be used for detecting face
The step of output action information performed by system 400 before, when described program code is run by described processor 430
The described system 400 for detecting face is made also to execute:Obtain at least one action prompt information from the second database at random,
Wherein, described second database includes multiple different action prompt information;Described program code is run by described processor 430
When so that the step of the described output action information performed by system 400 for detecting face is included:By text importing
Form and/or the action prompt information of voice broadcast form output acquisition.
Additionally, according to embodiments of the present invention, additionally providing a kind of storage medium, storing program on said storage
Instruction, when described program instruction is run by computer or processor for execute the embodiment of the present invention for detecting face
The corresponding steps of method, and for realizing the corresponding module in the device for detecting face according to embodiments of the present invention.
Described storage medium for example can include the storage card of smart phone, the memory unit of panel computer, the hard disk of personal computer,
Read-only storage (ROM), Erasable Programmable Read Only Memory EPROM (EPROM), portable compact disc read-only storage (CD-ROM),
USB storage or any combination of above-mentioned storage medium.
In one embodiment, described computer program instructions when being run by computer or processor so that calculating
Each functional module of the device for detecting face according to embodiments of the present invention realized by machine or processor, and/or can
To execute the method for detecting face according to embodiments of the present invention.
In one embodiment, described computer program instructions make below described computer execution when being run by computer
Step:Obtain images to be recognized pair, described images to be recognized is directed to face collection to be identified by two cameras respectively to inclusion
Two images to be recognized;According to described images to be recognized to the depth information obtaining described face to be identified;Treat described in acquisition
The hot spot pattern that identification face is formed under infrared structure light irradiation;Described face to be identified is obtained according to described hot spot pattern
Texture information;And determine whether described face to be identified belongs to live body with reference to described depth information and described texture information.
In one embodiment, described computer program instructions make described computer hold further when being run by computer
OK:If for all images to be recognized gathering in the preset period of time after start time to the described face to be identified of determination
It is not belonging to live body it is determined that In vivo detection fails;And if in the described preset period of time after described start time
The specific images to be recognized of collection belongs to live body it is determined that In vivo detection passes through to the described face to be identified of determination.
In one embodiment, make when being run by computer performed by described computer in described computer program instructions
The step passed through of determination In vivo detection after, described computer program instructions make described computer enter when being run by computer
One step execution:From within the time period in the collection moment of described start time to described specific images to be recognized pair, by described two
The top-quality images to be recognized of face is selected at least part of images to be recognized of specific camera head collection in individual camera;
And using selected images to be recognized, recognition of face is carried out to described face to be identified.
In one embodiment, make when being run by computer performed by described computer in described computer program instructions
Using selected images to be recognized, the step of recognition of face is carried out to described face to be identified before, described computer program
Instruction makes described computer execute further when being run by computer:Obtain the identity card of the affiliated object of described face to be identified
Information, described ID card information includes identity card face;Described computer program instructions make described meter when being run by computer
Being included using the step that selected images to be recognized carries out recognition of face to described face to be identified performed by calculation machine:By institute
The face described to be identified stated in selected images to be recognized is contrasted with described identity card face, to wait to know described in determining
Whether others' face is consistent with described identity card face.
In one embodiment, described computer program instructions make when being run by computer performed by described computer
Included using the step that selected images to be recognized carries out recognition of face to described face to be identified:Selected treat described
Face described to be identified in identification image is contrasted with the known face in the first database, to determine described people to be identified
Whether face is one of known face in described first database.
In one embodiment, described computer program instructions make when being run by computer performed by described computer
Within the time period in the collection moment of described start time to described specific images to be recognized pair, by described two cameras
Specific camera head collection at least part of images to be recognized in select the top-quality images to be recognized of face step include:
It is each images to be recognized scoring in described at least part of images to be recognized according to one or more in following parameters:Described
Face brightness in images to be recognized for the face to be identified, sidelight backlight degree, pitching degree, lateral inclination, eye opening degree and open one's mouth
Degree;And select fraction highest images to be recognized as the top-quality images to be recognized of face.
In one embodiment, described computer program instructions make when being run by computer performed by described computer
Determine that the step whether described face to be identified belongs to live body includes in conjunction with described depth information and described texture information:If institute
State that texture information meets fell grain distribution rule and described depth information meets face depth profile rule it is determined that described
Face to be identified belongs to live body, otherwise determines that described face to be identified is not belonging to live body.
In one embodiment, described computer program instructions make described computer hold further when being run by computer
OK:In described acquisition images to be recognized pair, output action information, to indicate the execution of described face to be identified affiliated object
Action corresponding with described action prompt information.
In one embodiment, make when being run by computer performed by described computer in described computer program instructions
The step of output action information before, described computer program instructions make described computer also when being run by computer
Execution:Obtain at random at least one action prompt information from the second database, wherein, described second database include multiple not
Same action prompt information;Described computer program instructions make the output performed by described computer move when being run by computer
The step making information includes:The action prompt information being obtained by text importing form and/or the output of voice broadcast form.
Method and device for detecting face according to embodiments of the present invention, it coordinates without user, and therefore cooperation will
Ask low, speed fast, additionally, the method carries out In vivo detection with reference to depth information and texture information, can effectively prevent mask from attacking
Hit etc. and to attack, its security is higher.
Based in previous embodiment for detecting the method and device of face, present invention also offers a kind of remote teller
Machine system, described system include two cameras, infrared structure light emitting devices and described in previous embodiment for detecting
The device of face.Described two cameras are used for gathering two images to be recognized for face to be identified, obtain images to be recognized
Right, and by described images to be recognized to being sent to described image acquisition module;Described infrared structure light emitting devices is used for institute
State face transmitting infrared structure light to be identified, so that hot spot pattern to be formed on described face to be identified.
In embodiments of the present invention, described system also includes display and/or speech ciphering equipment, and described display is used in real time
Show the images to be recognized of described two camera collections, and receive action prompt information from the described device for detecting face
And pass through action prompt information described in text importing;Described speech ciphering equipment is used for receiving institute from the described device for detecting face
State action prompt information and pass through action prompt information described in voice broadcast;Wherein, described action prompt information is used for indicating institute
State the affiliated object of face to be identified and execute action corresponding with described action prompt information.
Although here by reference to Description of Drawings example embodiment it should be understood that above-mentioned example embodiment is merely exemplary
, and be not intended to limit the scope of the invention to this.Those of ordinary skill in the art can carry out various changes wherein
And modification, it is made without departing from the scope of the present invention and spirit.All such changes and modifications are intended to be included in claims
Within required the scope of the present invention.
Those of ordinary skill in the art are it is to be appreciated that combine the list of each example of the embodiments described herein description
Unit and algorithm steps, being capable of being implemented in combination in electronic hardware or computer software and electronic hardware.These functions are actually
To be executed with hardware or software mode, the application-specific depending on technical scheme and design constraint.Professional and technical personnel
Each specific application can be used different methods to realize described function, but this realization is it is not considered that exceed
The scope of the present invention.
It should be understood that disclosed equipment and method in several embodiments provided herein, can be passed through it
Its mode is realized.For example, apparatus embodiments described above are only schematically, for example, the division of described unit, and only
It is only a kind of division of logic function, actual can have other dividing mode when realizing, and for example multiple units or assembly can be tied
Close or be desirably integrated into another equipment, or some features can be ignored, or do not execute.
In specification mentioned herein, illustrate a large amount of details.It is to be appreciated, however, that the enforcement of the present invention
Example can be put into practice in the case of not having these details.In some instances, known method, structure are not been shown in detail
And technology, so as not to obscure the understanding of this description.
Similarly it will be appreciated that in order to simplify the present invention and help understand one or more of each inventive aspect,
In description to the exemplary embodiment of the present invention, each feature of the present invention be sometimes grouped together into single embodiment, figure,
Or in descriptions thereof.However, this method of the present invention should be construed to reflect following intention:I.e. required for protection
Application claims more features than the feature being expressly recited in each claim.More precisely, weighing as corresponding
As sharp claim is reflected, its inventive point is can be with the spy of all features of embodiment single disclosed in certain
Levy to solve corresponding technical problem.Therefore, it then follows it is concrete that claims of specific embodiment are thus expressly incorporated in this
Embodiment, wherein each claim itself is as the separate embodiments of the present invention.
It will be understood to those skilled in the art that in addition to mutually exclusive between feature, any combinations pair can be adopted
All features disclosed in this specification (including adjoint claim, summary and accompanying drawing) and so disclosed any method
Or all processes of equipment or unit are combined.Unless expressly stated otherwise, (including adjoint right will for this specification
Ask, make a summary and accompanying drawing) disclosed in each feature can be replaced by the alternative features providing identical, equivalent or similar purpose.
Although additionally, it will be appreciated by those of skill in the art that some embodiments described herein include other embodiments
In included some features rather than further feature, but the combination of the feature of different embodiment means to be in the present invention's
Within the scope of and form different embodiments.For example, in detail in the claims, embodiment required for protection one of arbitrarily
Can in any combination mode using.
The all parts embodiment of the present invention can be realized with hardware, or to run on one or more processor
Software module realize, or with combinations thereof realize.It will be understood by those of skill in the art that can use in practice
Microprocessor or digital signal processor (DSP) are realizing in the device for detecting face according to embodiments of the present invention
The some or all functions of some modules.The present invention is also implemented as the part for executing method as described herein
Or whole program of device (for example, computer program and computer program).Such program realizing the present invention can
To store on a computer-readable medium, or can have the form of one or more signal.Such signal can be from
Download on internet website and obtain, or provide on carrier signal, or provided with any other form.
It should be noted that above-described embodiment the present invention will be described rather than limits the invention, and ability
Field technique personnel can design alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference symbol between bracket should not be configured to limitations on claims.Word "comprising" does not exclude the presence of not
Element listed in the claims or step.Word "a" or "an" before element does not exclude the presence of multiple such
Element.The present invention can come real by means of the hardware including some different elements and by means of properly programmed computer
Existing.If in the unit claim listing equipment for drying, several in these devices can be by same hardware branch
To embody.The use of word first, second, and third does not indicate that any order.These words can be explained and run after fame
Claim.
The above, the only specific embodiment of the present invention or the explanation to specific embodiment, the protection of the present invention
Scope is not limited thereto, any those familiar with the art the invention discloses technical scope in, can be easily
Expect change or replacement, all should be included within the scope of the present invention.Protection scope of the present invention should be with claim
Protection domain is defined.
Claims (20)
1. a kind of method for detecting face, including:
Obtain images to be recognized pair, described images to be recognized is directed to face collection to be identified by two cameras respectively to inclusion
Two images to be recognized;
According to described images to be recognized to the depth information obtaining described face to be identified;
Obtain the hot spot pattern that described face to be identified is formed under infrared structure light irradiation;
Obtain the texture information of described face to be identified according to described hot spot pattern;And
Determine whether described face to be identified belongs to live body in conjunction with described depth information and described texture information.
2. the method for claim 1, wherein methods described further includes:
If for all images to be recognized gathering in the preset period of time after start time to the described people to be identified of determination
Face is not belonging to live body it is determined that In vivo detection fails;And
If the specific images to be recognized for collection in the described preset period of time after described start time is described to determining
Face to be identified belongs to live body it is determined that In vivo detection passes through.
3. method as claimed in claim 2, wherein, passes through afterwards in described determination In vivo detection, methods described is wrapped further
Include:
From within the time period in the collection moment of described start time to described specific images to be recognized pair, by described two shootings
The top-quality images to be recognized of face is selected at least part of images to be recognized of specific camera head collection in head;And
Using selected images to be recognized, recognition of face is carried out to described face to be identified.
4. method as claimed in claim 3, wherein, described using selected images to be recognized to described face to be identified
Before carrying out recognition of face, methods described further includes:Obtain the ID card information of the affiliated object of described face to be identified, institute
State ID card information and include identity card face;
Described using selected images to be recognized, recognition of face carried out to described face to be identified and include:Will be described selected
Face described to be identified in images to be recognized is contrasted with described identity card face, whether to determine described face to be identified
Consistent with described identity card face.
5. method as claimed in claim 3, wherein, described is entered to described face to be identified using selected images to be recognized
Row recognition of face includes:
It is right that known face in face described to be identified in described selected images to be recognized and the first database is carried out
Ratio is to determine whether described face to be identified is one of known face in described first database.
6. method as claimed in claim 3, wherein, described from described start time to described specific images to be recognized pair
Select at least part of images to be recognized in the time period in collection moment, by the specific camera head collection in described two cameras
Select the top-quality images to be recognized of face to include:
It is each images to be recognized scoring in described at least part of images to be recognized according to one or more in following parameters:
Face brightness in images to be recognized for the described face to be identified, sidelight backlight degree, pitching degree, lateral inclination, eye opening degree and
Degree of opening one's mouth;And
Select fraction highest images to be recognized as the top-quality images to be recognized of face.
7. the method as described in any one of claim 1 to 6, wherein, depth information described in described combination and described texture information
Determine whether described face to be identified belongs to live body and include:
If described texture information meets fell grain distribution rule and described depth information meets face depth profile rule,
Then determine that described face to be identified belongs to live body, otherwise determine that described face to be identified is not belonging to live body.
8. the method for claim 1, wherein methods described also includes:In described acquisition images to be recognized pair, output
Action prompt information, to indicate the execution action corresponding with described action prompt information of described face to be identified affiliated object.
9. method as claimed in claim 8, wherein, before described output action information, methods described also includes:
Obtain at random at least one action prompt information from the second database, wherein, described second database include multiple not
Same action prompt information;
Described output action information includes:
The action prompt information being obtained by text importing form and/or the output of voice broadcast form.
10. a kind of device for detecting face, including:
Image collection module, for obtaining images to be recognized pair, described images to be recognized is to inclusion respectively by two shooting scalp acupunctures
Two images to be recognized to face to be identified collection;
Depth information obtains module, for the depth information to the described face to be identified of acquisition according to described images to be recognized;
Hot spot pattern acquisition module, for obtaining the hot spot pattern that described face to be identified is formed under infrared structure light irradiation;
Texture information obtains module, for obtaining the texture information of described face to be identified according to described hot spot pattern;And
With reference to described depth information and described texture information, In vivo detection module, for determining whether described face to be identified belongs to
Live body.
11. devices as claimed in claim 10, wherein, described device further includes:
Failure determining module, if for all images to be recognized pair for collection in the preset period of time after start time
Determine that described face to be identified is not belonging to live body it is determined that In vivo detection fails;And
By determining module, if for waiting to know for the specific of collection in the described preset period of time after described start time
Other image belongs to live body it is determined that In vivo detection passes through to the described face to be identified of determination.
12. devices as claimed in claim 11, wherein, described device further includes:
Selecting module, for from described start time to described specific images to be recognized pair collection the moment time period in,
Select at least part of images to be recognized by the specific camera head collection in described two cameras that face is top-quality treats
Identification image;And
Face recognition module, for carrying out recognition of face using selected images to be recognized to described face to be identified.
13. devices as claimed in claim 12, wherein, described device further includes:ID card information acquisition module, is used for
Obtain the ID card information of the affiliated object of described face to be identified, described ID card information includes identity card face;
Described face recognition module includes:First contrast submodule, for by described in described selected images to be recognized
Face to be identified is contrasted with described identity card face, with determine described face to be identified whether with described identity card face one
Cause.
14. devices as claimed in claim 12, wherein, described face recognition module includes:Second contrast submodule, for inciting somebody to action
Face described to be identified in described selected images to be recognized is contrasted with the known face in the first database, with true
Whether fixed described face to be identified is one of known face in described first database.
15. devices as claimed in claim 12, wherein, described selecting module includes:
Scoring submodule, for being each in described at least part of images to be recognized according to one or more in following parameters
Images to be recognized scores:Face brightness in images to be recognized for the described face to be identified, sidelight backlight degree, pitching degree, left and right
Gradient, degree of eye opening and degree of opening one's mouth;And
Select submodule, for selecting fraction highest images to be recognized as the top-quality images to be recognized of face.
16. devices as described in any one of claim 10 to 15, wherein, described In vivo detection module includes:
First determination sub-module, if meet fell grain distribution rule and described depth information symbol for described texture information
Close face depth profile rule it is determined that described face to be identified belongs to live body;And
Second determination sub-module, if do not meet fell grain distribution rule or described depth information for described texture information
Do not meet face depth profile rule it is determined that described face to be identified is not belonging to live body.
17. devices as claimed in claim 10, wherein, described device also includes:Action prompt module, in described image
When acquisition module obtains images to be recognized pair, output action information, to indicate the execution of described face to be identified affiliated object
Action corresponding with described action prompt information.
18. devices as claimed in claim 17, wherein,
Described device also includes:Information acquisition module, carries for obtaining at least one action from the second database at random
Show information, wherein, described second database includes multiple different action prompt information;
Described action prompt module includes:Information output sub-module, for by text importing form and/or voice broadcast
The action prompt information that form output obtains.
A kind of 19. remote teller machine systems, wherein, described system include two cameras, infrared structure light emitting devices and
The device for detecting face as described in any one of claim 10 to 18,
Described two cameras are used for gathering two images to be recognized for described face to be identified, obtain images to be recognized pair,
And by described images to be recognized to being sent to described image acquisition module;
Described infrared structure light emitting devices is used for launching infrared structure light to described face to be identified, with described people to be identified
Form described hot spot pattern on the face.
20. systems as claimed in claim 19, wherein, described system also includes display and/or speech ciphering equipment,
Described display is used for the images to be recognized of real-time display described two camera collection, and from described for detecting face
Device receive action prompt information and by action prompt information described in text importing;
Described speech ciphering equipment is used for from the described described action prompt information of reception of the device for detecting face and is broadcast by voice
Report described action prompt information;
Wherein, described action prompt information is used for indicating the execution of described face to be identified affiliated object and described action prompt information
Corresponding action.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610798437.3A CN106407914B (en) | 2016-08-31 | 2016-08-31 | Method and device for detecting human face and remote teller machine system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610798437.3A CN106407914B (en) | 2016-08-31 | 2016-08-31 | Method and device for detecting human face and remote teller machine system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106407914A true CN106407914A (en) | 2017-02-15 |
CN106407914B CN106407914B (en) | 2019-12-10 |
Family
ID=58000726
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610798437.3A Active CN106407914B (en) | 2016-08-31 | 2016-08-31 | Method and device for detecting human face and remote teller machine system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106407914B (en) |
Cited By (38)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107392137A (en) * | 2017-07-18 | 2017-11-24 | 艾普柯微电子(上海)有限公司 | Face identification method and device |
CN107392874A (en) * | 2017-07-31 | 2017-11-24 | 广东欧珀移动通信有限公司 | U.S. face processing method, device and mobile device |
CN107590430A (en) * | 2017-07-26 | 2018-01-16 | 百度在线网络技术(北京)有限公司 | Biopsy method, device, equipment and storage medium |
CN107609515A (en) * | 2017-09-13 | 2018-01-19 | 天津麒麟信息技术有限公司 | A kind of face alignment system and method for the double verification based on platform of soaring |
CN107832712A (en) * | 2017-11-13 | 2018-03-23 | 深圳前海微众银行股份有限公司 | Biopsy method, device and computer-readable recording medium |
CN107944378A (en) * | 2017-11-20 | 2018-04-20 | 广东金赋科技股份有限公司 | The personal identification method and self-help serving system of a kind of Self-Service |
CN108171113A (en) * | 2017-12-01 | 2018-06-15 | 国政通科技股份有限公司 | A kind of identity authentication method and system |
CN108335394A (en) * | 2018-03-16 | 2018-07-27 | 东莞市华睿电子科技有限公司 | A kind of long-range control method of intelligent door lock |
CN108509868A (en) * | 2018-03-12 | 2018-09-07 | 杭州软库科技有限公司 | A kind of face identification system and method based on light-field camera |
CN108573203A (en) * | 2017-03-17 | 2018-09-25 | 北京旷视科技有限公司 | Identity identifying method and device and storage medium |
CN108596061A (en) * | 2018-04-12 | 2018-09-28 | Oppo广东移动通信有限公司 | Face identification method, device and mobile terminal, storage medium |
CN108629259A (en) * | 2017-03-17 | 2018-10-09 | 北京旷视科技有限公司 | Identity identifying method and device and storage medium |
CN108694357A (en) * | 2017-04-10 | 2018-10-23 | 北京旷视科技有限公司 | Method, apparatus and computer storage media for In vivo detection |
CN108734057A (en) * | 2017-04-18 | 2018-11-02 | 北京旷视科技有限公司 | The method, apparatus and computer storage media of In vivo detection |
CN108776786A (en) * | 2018-06-04 | 2018-11-09 | 北京京东金融科技控股有限公司 | Method and apparatus for generating user's truth identification model |
CN108875331A (en) * | 2017-08-01 | 2018-11-23 | 北京旷视科技有限公司 | Face unlocking method, device and system and storage medium |
CN108875452A (en) * | 2017-05-11 | 2018-11-23 | 北京旷视科技有限公司 | Face identification method, device, system and computer-readable medium |
CN108875546A (en) * | 2018-04-13 | 2018-11-23 | 北京旷视科技有限公司 | Face auth method, system and storage medium |
CN108875508A (en) * | 2017-11-23 | 2018-11-23 | 北京旷视科技有限公司 | In vivo detection algorithm update method, device, client, server and system |
CN109147116A (en) * | 2018-07-25 | 2019-01-04 | 深圳市飞瑞斯科技有限公司 | The method that smart lock and control smart lock are opened |
CN109635539A (en) * | 2018-10-30 | 2019-04-16 | 华为技术有限公司 | A kind of face identification method and electronic equipment |
CN110222486A (en) * | 2019-05-18 | 2019-09-10 | 王�锋 | User ID authentication method, device, equipment and computer readable storage medium |
WO2019205742A1 (en) * | 2018-04-28 | 2019-10-31 | Oppo广东移动通信有限公司 | Image processing method, apparatus, computer-readable storage medium, and electronic device |
CN110443237A (en) * | 2019-08-06 | 2019-11-12 | 北京旷视科技有限公司 | Certificate recognition methods, device, electronic equipment and computer readable storage medium |
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 |
CN110720105A (en) * | 2019-09-11 | 2020-01-21 | 深圳市汇顶科技股份有限公司 | Face anti-counterfeiting detection method, device, chip, electronic equipment and computer readable medium |
WO2020073993A1 (en) * | 2018-10-12 | 2020-04-16 | 杭州海康威视数字技术股份有限公司 | Face anti-spoof detection method, device and multi-view camera |
CN111311792A (en) * | 2020-02-12 | 2020-06-19 | 德施曼机电(中国)有限公司 | Intelligent lock verification system and method |
WO2020134238A1 (en) * | 2018-12-29 | 2020-07-02 | 北京市商汤科技开发有限公司 | Living body detection method and apparatus, and storage medium |
CN111382639A (en) * | 2018-12-30 | 2020-07-07 | 深圳市光鉴科技有限公司 | Living body face detection method and device |
CN111611843A (en) * | 2020-03-30 | 2020-09-01 | 北京爱接力科技发展有限公司 | Face detection preprocessing method, device, equipment and storage medium |
US10796178B2 (en) | 2016-12-15 | 2020-10-06 | Beijing Kuangshi Technology Co., Ltd. | Method and device for face liveness detection |
WO2020232889A1 (en) * | 2019-05-23 | 2020-11-26 | 平安科技(深圳)有限公司 | Check encashment method, apparatus and device, and computer-readable storage medium |
CN113066237A (en) * | 2021-03-26 | 2021-07-02 | 中国工商银行股份有限公司 | Face living body detection and identification method for automatic teller machine and automatic teller machine |
US11256903B2 (en) | 2018-04-12 | 2022-02-22 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Image processing method, image processing device, computer readable storage medium and electronic device |
US11410458B2 (en) | 2018-04-12 | 2022-08-09 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Face identification method and apparatus, mobile terminal and storage medium |
WO2023156319A1 (en) * | 2022-02-15 | 2023-08-24 | Trinamix Gmbh | Image manipulation for material information determination |
WO2023156315A1 (en) * | 2022-02-15 | 2023-08-24 | Trinamix Gmbh | Face authentication including material data extracted from image |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102622588A (en) * | 2012-03-08 | 2012-08-01 | 无锡数字奥森科技有限公司 | Dual-certification face anti-counterfeit method and device |
CN104598878A (en) * | 2015-01-07 | 2015-05-06 | 深圳市唯特视科技有限公司 | Multi-modal face recognition device and method based on multi-layer fusion of gray level and depth information |
CN104834901A (en) * | 2015-04-17 | 2015-08-12 | 北京海鑫科金高科技股份有限公司 | Binocular stereo vision-based human face detection method, device and system |
CN105022994A (en) * | 2015-06-30 | 2015-11-04 | 国网山东省电力公司日照供电公司 | Identity authentication method of network safety access of power system |
CN105138996A (en) * | 2015-09-01 | 2015-12-09 | 北京上古视觉科技有限公司 | Iris identification system with living body detecting function |
CN204944450U (en) * | 2015-09-18 | 2016-01-06 | 上海图漾信息科技有限公司 | Depth data measuring system |
CN105513221A (en) * | 2015-12-30 | 2016-04-20 | 四川川大智胜软件股份有限公司 | ATM (Automatic Teller Machine) cheat-proof device and system based on three-dimensional human face identification |
CN105825186A (en) * | 2016-03-16 | 2016-08-03 | 四川川大智胜软件股份有限公司 | Identity authentication method for identity card and card holder based on 3D face data |
-
2016
- 2016-08-31 CN CN201610798437.3A patent/CN106407914B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102622588A (en) * | 2012-03-08 | 2012-08-01 | 无锡数字奥森科技有限公司 | Dual-certification face anti-counterfeit method and device |
CN104598878A (en) * | 2015-01-07 | 2015-05-06 | 深圳市唯特视科技有限公司 | Multi-modal face recognition device and method based on multi-layer fusion of gray level and depth information |
CN104834901A (en) * | 2015-04-17 | 2015-08-12 | 北京海鑫科金高科技股份有限公司 | Binocular stereo vision-based human face detection method, device and system |
CN105022994A (en) * | 2015-06-30 | 2015-11-04 | 国网山东省电力公司日照供电公司 | Identity authentication method of network safety access of power system |
CN105138996A (en) * | 2015-09-01 | 2015-12-09 | 北京上古视觉科技有限公司 | Iris identification system with living body detecting function |
CN204944450U (en) * | 2015-09-18 | 2016-01-06 | 上海图漾信息科技有限公司 | Depth data measuring system |
CN105513221A (en) * | 2015-12-30 | 2016-04-20 | 四川川大智胜软件股份有限公司 | ATM (Automatic Teller Machine) cheat-proof device and system based on three-dimensional human face identification |
CN105825186A (en) * | 2016-03-16 | 2016-08-03 | 四川川大智胜软件股份有限公司 | Identity authentication method for identity card and card holder based on 3D face data |
Cited By (51)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10796178B2 (en) | 2016-12-15 | 2020-10-06 | Beijing Kuangshi Technology Co., Ltd. | Method and device for face liveness detection |
CN108573203A (en) * | 2017-03-17 | 2018-09-25 | 北京旷视科技有限公司 | Identity identifying method and device and storage medium |
CN112651348A (en) * | 2017-03-17 | 2021-04-13 | 北京旷视科技有限公司 | Identity authentication method and device and storage medium |
CN108573203B (en) * | 2017-03-17 | 2021-01-26 | 北京旷视科技有限公司 | Identity authentication method and device and storage medium |
CN108629259A (en) * | 2017-03-17 | 2018-10-09 | 北京旷视科技有限公司 | Identity identifying method and device and storage medium |
CN108629260A (en) * | 2017-03-17 | 2018-10-09 | 北京旷视科技有限公司 | Live body verification method and device and storage medium |
CN108694357A (en) * | 2017-04-10 | 2018-10-23 | 北京旷视科技有限公司 | Method, apparatus and computer storage media for In vivo detection |
CN108734057A (en) * | 2017-04-18 | 2018-11-02 | 北京旷视科技有限公司 | The method, apparatus and computer storage media of In vivo detection |
CN108875452A (en) * | 2017-05-11 | 2018-11-23 | 北京旷视科技有限公司 | Face identification method, device, system and computer-readable medium |
CN107392137B (en) * | 2017-07-18 | 2020-09-08 | 艾普柯微电子(上海)有限公司 | Face recognition method and device |
CN107392137A (en) * | 2017-07-18 | 2017-11-24 | 艾普柯微电子(上海)有限公司 | Face identification method and device |
US10699103B2 (en) | 2017-07-26 | 2020-06-30 | Baidu Online Network Technology (Beijing) Co., Ltd. | Living body detecting method and apparatus, device and storage medium |
CN107590430A (en) * | 2017-07-26 | 2018-01-16 | 百度在线网络技术(北京)有限公司 | Biopsy method, device, equipment and storage medium |
CN107392874A (en) * | 2017-07-31 | 2017-11-24 | 广东欧珀移动通信有限公司 | U.S. face processing method, device and mobile device |
CN108875331A (en) * | 2017-08-01 | 2018-11-23 | 北京旷视科技有限公司 | Face unlocking method, device and system and storage medium |
CN107609515A (en) * | 2017-09-13 | 2018-01-19 | 天津麒麟信息技术有限公司 | A kind of face alignment system and method for the double verification based on platform of soaring |
CN107832712A (en) * | 2017-11-13 | 2018-03-23 | 深圳前海微众银行股份有限公司 | Biopsy method, device and computer-readable recording medium |
CN107944378A (en) * | 2017-11-20 | 2018-04-20 | 广东金赋科技股份有限公司 | The personal identification method and self-help serving system of a kind of Self-Service |
CN108875508A (en) * | 2017-11-23 | 2018-11-23 | 北京旷视科技有限公司 | In vivo detection algorithm update method, device, client, server and system |
CN108875508B (en) * | 2017-11-23 | 2021-06-29 | 北京旷视科技有限公司 | Living body detection algorithm updating method, device, client, server and system |
CN108171113A (en) * | 2017-12-01 | 2018-06-15 | 国政通科技股份有限公司 | A kind of identity authentication method and system |
CN108509868B (en) * | 2018-03-12 | 2020-08-04 | 杭州软库科技有限公司 | Face recognition system and method based on light field camera |
CN108509868A (en) * | 2018-03-12 | 2018-09-07 | 杭州软库科技有限公司 | A kind of face identification system and method based on light-field camera |
CN108335394A (en) * | 2018-03-16 | 2018-07-27 | 东莞市华睿电子科技有限公司 | A kind of long-range control method of intelligent door lock |
CN108596061A (en) * | 2018-04-12 | 2018-09-28 | Oppo广东移动通信有限公司 | Face identification method, device and mobile terminal, storage medium |
US11256903B2 (en) | 2018-04-12 | 2022-02-22 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Image processing method, image processing device, computer readable storage medium and electronic device |
US11410458B2 (en) | 2018-04-12 | 2022-08-09 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Face identification method and apparatus, mobile terminal and storage medium |
CN108875546A (en) * | 2018-04-13 | 2018-11-23 | 北京旷视科技有限公司 | Face auth method, system and storage medium |
TWI736883B (en) * | 2018-04-28 | 2021-08-21 | 大陸商Oppo廣東移動通信有限公司 | Method for image processing and electronic device |
WO2019205742A1 (en) * | 2018-04-28 | 2019-10-31 | Oppo广东移动通信有限公司 | Image processing method, apparatus, computer-readable storage medium, and electronic device |
US10771689B2 (en) | 2018-04-28 | 2020-09-08 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Image processing method and device, computer-readable storage medium and electronic device |
CN108776786A (en) * | 2018-06-04 | 2018-11-09 | 北京京东金融科技控股有限公司 | Method and apparatus for generating user's truth identification model |
CN109147116A (en) * | 2018-07-25 | 2019-01-04 | 深圳市飞瑞斯科技有限公司 | The method that smart lock and control smart lock are opened |
US11869255B2 (en) | 2018-10-12 | 2024-01-09 | Hangzhou Hikvision Digital Technology Co., Ltd. | Anti-counterfeiting face detection method, device and multi-lens camera |
WO2020073993A1 (en) * | 2018-10-12 | 2020-04-16 | 杭州海康威视数字技术股份有限公司 | Face anti-spoof detection method, device and multi-view camera |
CN109635539A (en) * | 2018-10-30 | 2019-04-16 | 华为技术有限公司 | A kind of face identification method and electronic equipment |
EP3872658A4 (en) * | 2018-10-30 | 2021-12-15 | Honor Device Co., Ltd. | Face recognition method and electronic device |
WO2020134238A1 (en) * | 2018-12-29 | 2020-07-02 | 北京市商汤科技开发有限公司 | Living body detection method and apparatus, and storage medium |
CN111444744A (en) * | 2018-12-29 | 2020-07-24 | 北京市商汤科技开发有限公司 | Living body detection method, living body detection device, and storage medium |
US11393256B2 (en) | 2018-12-29 | 2022-07-19 | Beijing Sensetime Technology Development Co., Ltd. | Method and device for liveness detection, and storage medium |
CN111382639A (en) * | 2018-12-30 | 2020-07-07 | 深圳市光鉴科技有限公司 | Living body face detection method and device |
CN110222486A (en) * | 2019-05-18 | 2019-09-10 | 王�锋 | User ID authentication method, device, equipment and computer readable storage medium |
WO2020232889A1 (en) * | 2019-05-23 | 2020-11-26 | 平安科技(深圳)有限公司 | Check encashment method, apparatus and device, and computer-readable storage medium |
CN110443237A (en) * | 2019-08-06 | 2019-11-12 | 北京旷视科技有限公司 | Certificate recognition methods, device, electronic equipment and computer readable storage medium |
CN110720105A (en) * | 2019-09-11 | 2020-01-21 | 深圳市汇顶科技股份有限公司 | Face anti-counterfeiting detection method, device, chip, electronic equipment and computer readable medium |
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 |
CN111311792A (en) * | 2020-02-12 | 2020-06-19 | 德施曼机电(中国)有限公司 | Intelligent lock verification system and method |
CN111611843A (en) * | 2020-03-30 | 2020-09-01 | 北京爱接力科技发展有限公司 | Face detection preprocessing method, device, equipment and storage medium |
CN113066237A (en) * | 2021-03-26 | 2021-07-02 | 中国工商银行股份有限公司 | Face living body detection and identification method for automatic teller machine and automatic teller machine |
WO2023156319A1 (en) * | 2022-02-15 | 2023-08-24 | Trinamix Gmbh | Image manipulation for material information determination |
WO2023156315A1 (en) * | 2022-02-15 | 2023-08-24 | Trinamix Gmbh | Face authentication including material data extracted from image |
Also Published As
Publication number | Publication date |
---|---|
CN106407914B (en) | 2019-12-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106407914A (en) | Method for detecting human faces, device and remote teller machine system | |
CN109711243B (en) | Static three-dimensional face in-vivo detection method based on deep learning | |
CN108875452A (en) | Face identification method, device, system and computer-readable medium | |
CN107609383B (en) | 3D face identity authentication method and device | |
KR101356358B1 (en) | Computer-implemented method and apparatus for biometric authentication based on images of an eye | |
CN108876833A (en) | Image processing method, image processing apparatus and computer readable storage medium | |
CN104834901B (en) | A kind of method for detecting human face, apparatus and system based on binocular stereo vision | |
CN106778525A (en) | Identity identifying method and device | |
CN106599772A (en) | Living body authentication method, identity authentication method and device | |
CN108734057A (en) | The method, apparatus and computer storage media of In vivo detection | |
CN108573202A (en) | Identity identifying method, device and system and terminal, server and storage medium | |
JP7262884B2 (en) | Biometric face detection method, device, equipment and computer program | |
CN111597938B (en) | Living body detection and model training method and device | |
JP2019506694A (en) | Biometric analysis system and method | |
CN108573203A (en) | Identity identifying method and device and storage medium | |
CN105989263A (en) | Method for authenticating identities, method for opening accounts, devices and systems | |
CN113205057B (en) | Face living body detection method, device, equipment and storage medium | |
CN108875469A (en) | In vivo detection and identity authentication method, device and computer storage medium | |
CN108875338A (en) | unlocking method, device and system and storage medium | |
CN107609462A (en) | Measurement information generation to be checked and biopsy method, device, equipment and storage medium | |
US9501719B1 (en) | System and method for verification of three-dimensional (3D) object | |
CN111382592B (en) | Living body detection method and apparatus | |
CN108875468A (en) | Biopsy method, In vivo detection system and storage medium | |
CN108140114A (en) | Iris recognition | |
CN108875544A (en) | Face identification method, device, system and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
CB02 | Change of applicant information |
Address after: 100190 Beijing, Haidian District Academy of Sciences, South Road, No. 2, block A, No. 313 Applicant after: MEGVII INC. Applicant after: Beijing maigewei Technology Co., Ltd. Address before: 100190 Beijing, Haidian District Academy of Sciences, South Road, No. 2, block A, No. 313 Applicant before: MEGVII INC. Applicant before: Beijing aperture Science and Technology Ltd. |
|
CB02 | Change of applicant information | ||
GR01 | Patent grant | ||
GR01 | Patent grant |