CN107437067A - Human face in-vivo detection method and Related product - Google Patents
Human face in-vivo detection method and Related product Download PDFInfo
- Publication number
- CN107437067A CN107437067A CN201710560789.XA CN201710560789A CN107437067A CN 107437067 A CN107437067 A CN 107437067A CN 201710560789 A CN201710560789 A CN 201710560789A CN 107437067 A CN107437067 A CN 107437067A
- Authority
- CN
- China
- Prior art keywords
- reference picture
- user
- multiframe
- mentioned
- coverage
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical 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
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- 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
- G06V40/18—Eye characteristics, e.g. of the iris
-
- 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
Abstract
The embodiment of the invention discloses a kind of human face in-vivo detection method and Related product.Method includes：Mobile terminal is when detecting that including integrity degree in the range of current shooting is more than the pre-set image of predetermined threshold value, the reference picture of the multiframe in the range of continuous acquisition current shooting；Pre-process the reference picture of the multiframe；Obtain the pretreated set of characteristic points per frame reference picture；Determine whether the user in the coverage is real user according to the set of characteristic points of the acquisition.The embodiment of the present invention is advantageous to improve security, reliability and the accuracy of mobile terminal bio-identification.
Description
Technical field
The present invention relates to technical field of mobile terminals, and in particular to human face in-vivo detection method and Related product.
Background technology
With society progress and the reach of science, information exchange is more and more frequent, for ensure information safety, need to
Family identity is verified, therefore, can usually use bio-identification, such as：Fingerprint recognition, recognition of face, iris recognition, vein are known
Not, the biological identification technology such as personal recognition.
At present, face recognition technology is widely used and continues to be used more widely, and increasing mobile terminal is matched somebody with somebody
Face identification device is had, facial image is shot such as by front camera, face recognition technology has accuracy rate high, conveniently
The features such as quick,
The content of the invention
The embodiments of the invention provide human face in-vivo detection method and Related product, can improve mobile terminal bio-identification
Security, reliability and accuracy..
In a first aspect, the embodiment of the present invention provides a kind of mobile terminal, including biological information acquisition device, processor, on
State biological information acquisition device and connect above-mentioned processor, wherein,
Above-mentioned processor, for detecting the pre-set image for being more than predetermined threshold value in the range of current shooting comprising integrity degree
When, pass through the reference picture of the multiframe in the range of above-mentioned biological information acquisition device continuous acquisition current shooting；
Above-mentioned processor, it is additionally operable to pre-process the reference picture of above-mentioned multiframe；
Above-mentioned processor, it is additionally operable to obtain the above-mentioned pretreated set of characteristic points per frame reference picture；
Above-mentioned processor, it is additionally operable to determine whether is user in above-mentioned coverage according to the set of characteristic points of above-mentioned acquisition
For real user.
Second aspect, the embodiment of the present invention provide a kind of human face in-vivo detection method, including：
Detecting that continuous acquisition is current when being more than the pre-set image of predetermined threshold value comprising integrity degree in the range of current shooting
The reference picture of multiframe in coverage；
Pre-process the reference picture of above-mentioned multiframe；
Obtain the above-mentioned pretreated set of characteristic points per frame reference picture；
Determine whether the user in above-mentioned coverage is real user according to the set of characteristic points of above-mentioned acquisition.
The third aspect, the embodiment of the present invention provide a kind of mobile terminal, including processing unit and collecting unit,
Above-mentioned processing unit, for detecting the default figure for being more than predetermined threshold value in the range of current shooting comprising integrity degree
During picture, pass through the reference picture of the multiframe in the range of above-mentioned collecting unit continuous acquisition current shooting；
Above-mentioned processing unit, it is additionally operable to pre-process the reference picture of above-mentioned multiframe；
Above-mentioned processing unit, it is additionally operable to obtain the above-mentioned pretreated set of characteristic points per frame reference picture；
Above-mentioned processing unit, it is additionally operable to determine that the user in above-mentioned coverage is according to the set of characteristic points of above-mentioned acquisition
No is real user.
Fourth aspect, the embodiment of the present invention provide a kind of mobile terminal, including processor, memory, communication interface and
One or more programs, wherein, said one or multiple programs are stored in above-mentioned memory, and are configured by above-mentioned
Manage device to perform, said procedure includes being used for the instruction for performing the step in first aspect either method of the embodiment of the present invention.
5th aspect, the embodiments of the invention provide a kind of computer-readable recording medium, wherein, above computer is readable
Storage medium stores the computer program for electronic data interchange, wherein, above computer program causes computer to perform such as
Part or all of step described in first aspect either method of the embodiment of the present invention, above computer include mobile terminal.
6th aspect, the embodiments of the invention provide a kind of computer program product, wherein, above computer program product
Non-transient computer-readable recording medium including storing computer program, above computer program are operable to make calculating
Machine is performed such as the part or all of step described in first aspect either method of the embodiment of the present invention.The computer program product
Can be a software installation bag, above computer includes mobile terminal.
As can be seen that in the embodiment of the present invention, mobile terminal includes integrity degree detecting first in the range of current shooting
More than predetermined threshold value pre-set image when, the reference picture of the multiframe in the range of continuous acquisition current shooting, secondly, in pretreatment
The reference picture of multiframe is stated, then, the above-mentioned pretreated set of characteristic points per frame reference picture is obtained, finally, according to upper
The set of characteristic points for stating acquisition determines whether the user in above-mentioned coverage is real user.It can be seen that mobile terminal is being carried out
Before bio-identification, first changed according to the countenance of user, whether identification current face is face live body, be efficiently avoid
Situations such as false photo, be advantageous to improve security, reliability and the accuracy of bio-identification.
Brief description of the drawings
The accompanying drawing involved by the embodiment of the present invention will be briefly described below.
Fig. 1 is a kind of structural representation of mobile terminal provided in an embodiment of the present invention；
Fig. 2A is a kind of schematic flow sheet of human face in-vivo detection method provided in an embodiment of the present invention；
Fig. 2 B are a kind of exemplary plots of reference picture provided in an embodiment of the present invention；
Fig. 2 C are a kind of exemplary plots of reference picture provided in an embodiment of the present invention；
A kind of structural representation of mobile terminal disclosed in Fig. 3 inventive embodiments；
Fig. 4 is a kind of functional unit composition block diagram of mobile terminal disclosed in the embodiment of the present invention.
Embodiment
In order that those skilled in the art more fully understand the present invention program, below in conjunction with the embodiment of the present invention
Accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is only
Part of the embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art
The every other embodiment obtained under the premise of creative work is not made, belongs to the scope of protection of the invention.
Term " first ", " second " in description and claims of this specification and above-mentioned accompanying drawing etc. are to be used to distinguish
Different objects, rather than for describing particular order.In addition, term " comprising " and " having " and their any deformations, it is intended that
It is to cover non-exclusive include.Such as process, method, system, product or the equipment for containing series of steps or unit do not have
The step of being defined in the step of having listed or unit, but alternatively also including not listing or unit, or alternatively also wrap
Include for other intrinsic steps of these processes, method, product or equipment or unit.
Referenced herein " embodiment " is it is meant that the special characteristic, structure or the characteristic that describe can wrap in conjunction with the embodiments
In at least one embodiment of the present invention.Each position in the description occur the phrase might not each mean it is identical
Embodiment, nor the independent or alternative embodiment with other embodiments mutual exclusion.Those skilled in the art explicitly and
Implicitly understand, embodiment described herein can be combined with other embodiments.
Mobile terminal involved by the embodiment of the present invention can include the various handheld devices with radio communication function,
Mobile unit, wearable device, computing device or other processing equipments for being connected to radio modem, and various forms
User equipment (User Equipment, UE), mobile station (Mobile Station, MS), terminal device (terminal
Device) etc..For convenience of description, apparatus mentioned above is referred to as mobile terminal.
Mobile terminal described by the embodiment of the present invention is provided with biological information acquisition device, the biological information acquisition device
Finger print information harvester, iris information harvester and facial information harvester are specifically included, wherein, finger print information collection
Device can be that fingerprint sensor module, iris information harvester can include infrared light supply and iris camera, face letter
Breath harvester can be universal camera shooting head mould group, such as front camera.The embodiment of the present invention is situated between below in conjunction with the accompanying drawings
Continue.
Referring to Fig. 1, Fig. 1 is that the embodiments of the invention provide a kind of structural representation of mobile terminal 100, above-mentioned movement
Terminal 100 includes：Housing, touching display screen, mainboard, battery and subplate, infrared light supply 21, iris camera are provided with mainboard
22nd, front camera 23, processor 110, memory 120 and sim card slot etc., oscillator, integral sound chamber, VOOC are provided with subplate
Interface and fingerprint module 24 are filled in sudden strain of a muscle, and above-mentioned infrared light supply 21 and iris camera 22 form the iris information of the mobile terminal 100
Harvester, above-mentioned front camera 23 form the facial information harvester of the mobile terminal 100, above-mentioned fingerprint sensor mould
Group 24 forms the finger print information harvester of the mobile terminal 100, above-mentioned iris information harvester, facial information harvester
The biological information acquisition device of the mobile terminal 100 is referred to as with finger print information harvester, wherein,
Above-mentioned biological information acquisition device, for being more than predetermined threshold value comprising integrity degree in the range of current shooting detecting
Pre-set image when, the reference picture of the multiframe in the range of continuous acquisition current shooting.
Wherein, when biological information acquisition device is iris information harvester, infrared light supply 21 is used to launch infrared light
The iris for irradiating user forms reflection light, and iris camera 22 is used to gather reflection light formation iris image, processor 110
After obtaining the iris image, for the iris image perform iris image quality assess, localization of iris circle (comprising coarse positioning and
Fine positioning), Iris preprocessing, iris feature point extraction, iris templates generation etc. processing procedure, the iris templates of generation are above-mentioned
Biological information.
The specific implementation of collection biological information can be the biometric image of biological information acquisition device collection user.
Above-mentioned processor 110, for pre-processing the reference picture of above-mentioned multiframe.
Above-mentioned processor 110, it is additionally operable to obtain the above-mentioned pretreated set of characteristic points per frame reference picture.
Above-mentioned processor 110, it is additionally operable to determine the user in above-mentioned coverage according to the set of characteristic points of above-mentioned acquisition
Whether it is real user
As can be seen that in the embodiment of the present invention, mobile terminal includes integrity degree detecting first in the range of current shooting
More than predetermined threshold value pre-set image when, the reference picture of the multiframe in the range of continuous acquisition current shooting, secondly, in pretreatment
The reference picture of multiframe is stated, then, the above-mentioned pretreated set of characteristic points per frame reference picture is obtained, finally, according to upper
The set of characteristic points for stating acquisition determines whether the user in above-mentioned coverage is real user.It can be seen that mobile terminal is being carried out
Before bio-identification, first changed according to the countenance of user, whether identification current face is face live body, be efficiently avoid
Situations such as false photo, be advantageous to improve security, reliability and the accuracy of bio-identification.
In a possible example, in terms of the reference picture of the above-mentioned multiframe of above-mentioned pretreatment, above-mentioned processor 110 has
Body is used for：Detect whether big equal to preset area per the face size in frame reference picture in the reference picture of above-mentioned multiframe
It is small；And for when detecting that above-mentioned face size is not equal to preset area size, being contracted to above-mentioned reference picture
Put so that the face size in the above-mentioned reference picture per frame is equal to preset area size.
In a possible example, determined in the above-mentioned set of characteristic points according to above-mentioned acquisition in above-mentioned coverage
In terms of whether user is real user, above-mentioned processor 110 is specifically used for：Any two obtained in features described above point set is special
Sign point；And for determining the first relative reference value between above-mentioned any two characteristic point；And in above-mentioned first phase
When being more than the first predetermined threshold value to reference value, it is real user to determine the user in above-mentioned coverage.
In a possible example, determined in the above-mentioned set of characteristic points according to above-mentioned acquisition in above-mentioned coverage
In terms of whether user is real user, above-mentioned processor 110 is specifically used for：Obtain any two frame in the reference picture of above-mentioned multiframe
The set of characteristic points of reference picture；And corresponding feature in the set of characteristic points for determining above-mentioned any two frames reference picture
The second relative reference value between point；And for when the above-mentioned second relative reference value is more than the second predetermined threshold value, it is determined that on
It is real user to state the user in coverage.
In this possible example, when the above-mentioned second relative reference value is more than the second predetermined threshold value, above-mentioned shooting is determined
In the range of user in terms of real user, above-mentioned processor 110 is specifically used for：Determine that the above-mentioned second relative reference value is more than the
The feature point group number of two predetermined threshold values；And for when features described above point group number is more than three predetermined threshold values, determining above-mentioned bat
User in the range of taking the photograph is real user.
Refer to Fig. 2A, Fig. 2A be the embodiments of the invention provide a kind of schematic flow sheet of human face in-vivo detection method,
Applied to mobile terminal, as illustrated, this human face in-vivo detection method includes：
S201, mobile terminal are more than the pre-set image of predetermined threshold value detecting comprising integrity degree in the range of current shooting
When, the reference picture of the multiframe in the range of continuous acquisition current shooting.
Wherein, pre-set image can be facial image or iris image.
Wherein, the integrity degree of facial image or iris image should be greater than predetermined threshold value in pre-set image.For example, facial image
In face integrity degree need to be more than 90 percent, in this way, can avoid with the human face photo of different expressions disguise oneself as face live
Body identifies, because during photo is replaced, it is low or even shoot situation less than face to have a face integrity degree photographed,
And then it can effectively avoid the situation of false photo array.
Wherein, predetermined threshold value corresponding to facial image and iris image can differ.
Wherein, mobile terminal is more than the pre- of predetermined threshold value in the pre-set image in coverage is detected comprising integrity degree
If during image, the reference picture of the multiframe in the range of continuous acquisition current shooting, the reference picture of the multiframe is facial image.
S202, above-mentioned mobile terminal pre-process the reference picture of above-mentioned multiframe.
Wherein, the reference picture of multiframe is pre-processed, the multiple image can be carried out to brightness, contrast and smooth
The processing of degree, to facilitate the extraction of characteristic point and reduce the error between characteristic point.
Wherein,, can basis because the reference picture of this multiframe is continuous acquisition after the reference picture of multiframe is collected
The reference picture of the multiframe judges whether the expression of face converts, and determines whether as face live body.
S203, the above-mentioned above-mentioned pretreated set of characteristic points per frame reference picture of acquisition for mobile terminal.
Wherein, the pretreated set of characteristic points per frame reference picture is obtained, characteristic point can be eyes, nose, mouth
Bar, eyebrow etc..
Wherein, the selection of characteristic point can be configured by user, or, mobile terminal enters according to the use habit of user
Row intelligence learning, obtains set of characteristic points.For example, during user uses mobile terminal, detect user habitually
It can open one's mouth and either move eyes or dynamic eyebrow, can be using these elements as characteristic point.
S204, above-mentioned mobile terminal determine whether is user in above-mentioned coverage according to the set of characteristic points of above-mentioned acquisition
For real user.
Wherein, due to collect be Time Continuous multiframe reference picture, it is assumed that the user photographed expression hair
During changing, it can also be changed per the set of characteristic points in frame reference picture, therefore can be according to the feature point set arrived of acquisition
Close, can further determine that whether the expression of user changes, so as to, it is determined whether it is face In vivo detection.
As can be seen that in the embodiment of the present invention, mobile terminal includes integrity degree detecting first in the range of current shooting
More than predetermined threshold value pre-set image when, the reference picture of the multiframe in the range of continuous acquisition current shooting, secondly, in pretreatment
The reference picture of multiframe is stated, then, the above-mentioned pretreated set of characteristic points per frame reference picture is obtained, finally, according to upper
The set of characteristic points for stating acquisition determines whether the user in above-mentioned coverage is real user.It can be seen that mobile terminal is being carried out
Before bio-identification, first changed according to the countenance of user, whether identification current face is face live body, be efficiently avoid
Situations such as false photo, be advantageous to improve security, reliability and the accuracy of bio-identification.
In a possible example, the reference picture of the above-mentioned above-mentioned multiframe of pretreatment, including：Detect the ginseng of above-mentioned multiframe
Examine in image and whether be equal to preset area size per the face size in frame reference picture；Detecting above-mentioned face area
Differ in size when preset area size, above-mentioned reference picture is zoomed in and out so that the face in the above-mentioned reference picture per frame
Size is equal to preset area size.
Wherein, the reference picture of multiframe is pre-processed, whether the face size in the every frame reference picture of detection
Equal to default size, when face size is not equal to default size, the reference picture is zoomed in and out,
So that face size in the reference picture is equal to default size, and then so that in the reference picture of multiframe
It is all identical per the face size in frame reference picture, equal to default size
Wherein, preset area size should meet that clearly feature can be extracted from the facial image of the preset area size
Point set.
It can be seen that in this example, because user is when carrying out recognition of face, the distance between mobile terminal may have occurred
Change, and then so that the size of face area differs in the reference picture of obtained multiframe.To the people in every frame reference picture
Face size is detected, so as to which the face size in reference picture be normalized so that is referred to per frame
Face size in image is identical, is advantageous to when the reference picture to multiframe carries out feature point extraction so that phase
The characteristic point image area size answered is identical, so as to reduce the error of characteristic point.
In a possible example, the above-mentioned set of characteristic points according to above-mentioned acquisition determines the use in above-mentioned coverage
Whether family is real user, including：Obtain any two characteristic point in features described above point set；Determine that above-mentioned any two is special
The first relative reference value between sign point；When the above-mentioned first relative reference value is more than the first predetermined threshold value, above-mentioned shooting is determined
In the range of user be real user.
Wherein, in the set of characteristic points of any reference picture, two characteristic points is arbitrarily chosen, compare the two characteristic points
Between the first relative reference value, the first relative reference value can be relative distance, relative angle, the phase between two characteristic points
To direction, relative coordinate displacement etc., do not limit herein.
For example, the first relative reference value is relative distance, two characteristic points of selection are the corners of the mouth and nose, and user is smiling
When and when not smiling, the distance between the corners of the mouth and nose should differ.For example possible user is when smiling, the corners of the mouth and nose it
Between distance can be more than the distance between the corners of the mouth and nose when not smiling, according to the difference of smile degree, between the corners of the mouth and nose
Distance can also occur a certain degree of change, but the scope changed should such as exceed in rational transformation range within
This excursion, then it is not considered as normal face smile expression.
In another example the first relative reference value is relative coordinate, using nose as the origin of coordinates, user does not do any expression
When, the relative coordinate of the corners of the mouth is (X1, Y1), and when user does expression, the relative coordinate of the corners of the mouth is (X2, Y2), and first is relative
Displacement of the reference value between coordinate (X2, Y2) and coordinate (X1, Y1).Wherein, it is more than first in the first relative reference value to preset
During threshold value, i.e., when the displacement between (X2, Y2) and coordinate (X1, Y1) is more than the first predetermined threshold value, illustrating user, there occurs certain
The smile of degree, it is intentional smiling, it may be determined that active user is real user.
It can be seen that in this example, according to the first relative reference value between any two characteristic point in set of characteristic points, really
Determine whether the user in coverage is real user, user can be accurately identified whether there occurs expression shape change, so that it is determined that being
No is face live body, is advantageous to improve the accuracy and reliability of bio-identification.
In a possible example, the above-mentioned set of characteristic points according to above-mentioned acquisition determines the use in above-mentioned coverage
Whether family is real user, including：Obtain the set of characteristic points of any two frames reference picture in the reference picture of above-mentioned multiframe；Really
The second relative reference value in the set of characteristic points of fixed above-mentioned any two frames reference picture between corresponding characteristic point；Above-mentioned
When two relative reference values are more than the second predetermined threshold value, it is real user to determine the user in above-mentioned coverage.
Wherein, in the face reference picture of continuous acquisition multiframe, if the human face expression of user is changed, more
It is also what is differed per the same or multiple characteristic point in the set of characteristic points in frame reference picture in the reference picture of frame,
Have change to a certain extent.
Wherein, in the set of characteristic points of any two frames reference picture, one or more characteristic points, compare corresponding to selection
The second relative reference value between characteristic point.Second relative reference value can be that one or more character pairs o'clock refer in two frames
The distance change that occurs in image, change in displacement, angle change etc..
For example, two corners of the mouths in selected characteristic point are compared, changed in user's expression, when such as smiling, reference
The distance between two corners of the mouths may differ in the distance between two corners of the mouths and reference picture 2 in image 1, because reference picture 1
It is the two width reference pictures that collect different at the time of with reference picture 2, user is during expression changes, two mouths
The distance between angle can naturally also change.As shown in fig. 2 b and fig. 2 c, it is any two frame reference in multi-frame-reference image
Image, Fig. 2 B are reference picture 1, and the distance between the corners of the mouth 1 and the corners of the mouth 2 are d1 in reference picture 1, and Fig. 2 C are reference picture 2, ginseng
It is d2 to examine the distance between the corners of the mouth 1 and the corners of the mouth 2 in image 2, and the second reference value is the absolute value of d1 and d2 differences.As can be seen that
The distance between corners of the mouth d1 and d2 is differed in reference picture 1 and reference picture 2.
Wherein, the second relative reference value between the character pair point in two frame reference pictures, such as with reference to figure 1 and ginseng
Examine the distance between two corners of the mouths in image 2 d1 and d2, it may be determined that the second relative reference value, be more than the in the second relative reference value
During two predetermined threshold values, show that the expression of user in reference picture 1 and reference picture 2 is changed, it may be determined that current shooting model
User's face in enclosing is face live body.
It can be seen that in this example, due to the facial image that the reference picture of multiframe is continuous acquisition, and the He of reference picture 1
Reference picture 2 is any two reference pictures in the reference picture of multiframe, therefore, with the expression shape change according to face and change
Degree is defined as face live body.
It is above-mentioned when the above-mentioned second relative reference value is more than the second predetermined threshold value in this possible example, determine above-mentioned
User in coverage is real user, including：Determine that the above-mentioned second relative reference value is more than the feature of the second predetermined threshold value
Point group number；When features described above point group number is more than three predetermined threshold values, it is real user to determine the user in above-mentioned coverage.
Wherein, multiple characteristic points of user are included in set of characteristic points, the expression shape change of user can include multiple characteristic points
Change, for example, first characteristic point detected is the corners of the mouth, after it is determined that the corners of the mouth converts, and then, can detect user's
Whether eyes convert, and due to user, when smiling, eyes can also change, can be to the multigroup of any two frames reference picture
Characteristic point is compared, and determines that the second relative reference value between characteristic point is more than the group number of the second predetermined threshold value.
Wherein, when feature point group number is more than three predetermined threshold values, it may be determined that the user in coverage is real user.
For example, the 3rd predetermined threshold value be 2, if detecting, the corners of the mouth of only face is changed, can not judge current face or
Face live body, if detect face the corners of the mouth and eyes this two groups of characteristic points all there occurs a certain degree of change, can determine that
For face live body.
It can be seen that in this example, the feature point group number that the second predetermined threshold value is more than in the second relative reference value is pre- more than the 3rd
If during threshold value, just can determine that the user in coverage is real user.In this way, using user before bio-identification is carried out,
A certain degree of expression synthesis is first made, and during expression shape change, it is impossible to simply simple expression shape change, occur
The feature of change, which is counted out, need to be more than the 3rd predetermined threshold value, be advantageous to improve the accuracy and reliability of face In vivo detection.
It is consistent with the embodiment shown in above-mentioned Fig. 2A, referring to Fig. 3, Fig. 3 is a kind of shifting provided in an embodiment of the present invention
The structural representation of dynamic terminal, as illustrated, the mobile terminal includes processor, memory, communication interface and one or more
Individual program, wherein, said one or multiple programs are stored in above-mentioned memory, and are configured to be held by above-mentioned processor
OK, said procedure includes being used for the instruction for performing following steps；
Detecting that continuous acquisition is current when being more than the pre-set image of predetermined threshold value comprising integrity degree in the range of current shooting
The reference picture of multiframe in coverage；
Pre-process the reference picture of above-mentioned multiframe；
Obtain the above-mentioned pretreated set of characteristic points per frame reference picture；
Determine whether the user in above-mentioned coverage is real user according to the set of characteristic points of above-mentioned acquisition.
As can be seen that in the embodiment of the present invention, mobile terminal includes integrity degree detecting first in the range of current shooting
More than predetermined threshold value pre-set image when, the reference picture of the multiframe in the range of continuous acquisition current shooting, secondly, in pretreatment
The reference picture of multiframe is stated, then, the above-mentioned pretreated set of characteristic points per frame reference picture is obtained, finally, according to upper
The set of characteristic points for stating acquisition determines whether the user in above-mentioned coverage is real user.It can be seen that mobile terminal is being carried out
Before bio-identification, first changed according to the countenance of user, whether identification current face is face live body, be efficiently avoid
Situations such as false photo, be advantageous to improve security, reliability and the accuracy of bio-identification.
In a possible example, in terms of the reference picture of the above-mentioned multiframe of above-mentioned pretreatment, the finger in said procedure
Order is specifically used for performing following steps：Detect in the reference picture of above-mentioned multiframe is per the face size in frame reference picture
It is no to be equal to preset area size；When detecting that above-mentioned face size is not equal to preset area size, to above-mentioned reference chart
As zooming in and out so that the face size in the above-mentioned reference picture per frame is equal to preset area size.
In a possible example, determined in the above-mentioned set of characteristic points according to above-mentioned acquisition in above-mentioned coverage
In terms of whether user is real user, the instruction in said procedure is specifically used for performing following steps：Obtain features described above point set
Any two characteristic point in conjunction；Determine the first relative reference value between above-mentioned any two characteristic point；In above-mentioned first phase
When being more than the first predetermined threshold value to reference value, it is real user to determine the user in above-mentioned coverage.
In a possible example, determined in the above-mentioned set of characteristic points according to above-mentioned acquisition in above-mentioned coverage
In terms of whether user is real user, the instruction in said procedure is specifically used for performing following steps：Obtain the ginseng of above-mentioned multiframe
Examine the set of characteristic points of any two frames reference picture in image；It is right in the set of characteristic points of above-mentioned any two frames reference picture to determine
The second relative reference value between the characteristic point answered；When the above-mentioned second relative reference value is more than the second predetermined threshold value, it is determined that on
It is real user to state the user in coverage.
In a possible example, above-mentioned when above-mentioned second reference value is more than the second predetermined threshold value relatively, it is determined that
In terms of user in above-mentioned coverage is real user, the instruction in said procedure is specifically used for performing following steps：It is determined that
Above-mentioned second relative reference value is more than the feature point group number of the second predetermined threshold value；
When features described above point group number is more than three predetermined threshold values, determine that the user in above-mentioned coverage uses to be true
Family.
It is above-mentioned that mainly the scheme of the embodiment of the present invention is described from the angle of method side implementation procedure.It is appreciated that
, for mobile terminal in order to realize above-mentioned function, it comprises perform the corresponding hardware configuration of each function and/or software mould
Block.Those skilled in the art should be readily appreciated that, with reference to the unit of each example of the embodiments described herein description
And algorithm steps, the present invention can be realized with the combining form of hardware or hardware and computer software.Some function actually with
The mode of hardware or computer software driving hardware performs, application-specific and design constraint bar depending on technical scheme
Part.Professional and technical personnel can specifically realize described function to each using distinct methods, but this reality
Now it is not considered that beyond the scope of this invention.
The embodiment of the present invention can carry out the division of functional unit according to above method example to mobile terminal, for example, can
Each functional unit is divided with corresponding each function, two or more functions can also be integrated in a processing unit
In.Above-mentioned integrated unit can both be realized in the form of hardware, can also be realized in the form of SFU software functional unit.Need
It is noted that the division in the embodiment of the present invention to unit is schematical, only a kind of division of logic function is actual real
There can be other dividing mode now.
In the case of using integrated unit, Fig. 4 shows one kind of mobile terminal involved in above-described embodiment
Possible functional unit forms block diagram.Mobile terminal 400 includes：Processing unit 402 and collecting unit 403.Processing unit 402 is used
Management is controlled in the action to mobile terminal, for example, processing unit 402 is used to support mobile terminal to perform the step in Fig. 2A
Rapid S201-S203 and/or other processes for techniques described herein.Collecting unit 403 be used for support mobile terminal with
The communication of other equipment.Mobile terminal can also include memory cell 401, the program code sum for memory mobile terminal
According to.
Wherein, above-mentioned processing unit 402, for being more than predetermined threshold value comprising integrity degree in the range of current shooting detecting
Pre-set image when, pass through the reference picture of the multiframe in the range of the above-mentioned continuous acquisition current shooting of collecting unit 403；And use
In the reference picture for pre-processing above-mentioned multiframe；And for obtaining the above-mentioned pretreated feature point set per frame reference picture
Close；And for determining whether the user in above-mentioned coverage is real user according to the set of characteristic points of above-mentioned acquisition.
In a possible example, in terms of the reference picture of the above-mentioned multiframe of above-mentioned pretreatment, above-mentioned processing unit 402
It is specifically used for：Detect in the reference picture of above-mentioned multiframe and whether be equal to preset area per the face size in frame reference picture
Size；And for when detecting that above-mentioned face size is not equal to preset area size, being carried out to above-mentioned reference picture
Scaling so that the face size in the above-mentioned reference picture per frame is equal to preset area size.
In a possible example, determined in the above-mentioned set of characteristic points according to above-mentioned acquisition in above-mentioned coverage
In terms of whether user is real user, above-mentioned processing unit 402 is specifically used for：Obtain any two in features described above point set
Characteristic point；And for determining the first relative reference value between above-mentioned any two characteristic point；And for above-mentioned first
When being more than the first predetermined threshold value with respect to reference value, it is real user to determine the user in above-mentioned coverage.
In a possible example, determined in the above-mentioned set of characteristic points according to above-mentioned acquisition in above-mentioned coverage
In terms of whether user is real user, above-mentioned processing unit 402 is specifically used for：Obtain any two in the reference picture of above-mentioned multiframe
The set of characteristic points of frame reference picture；And corresponding spy in the set of characteristic points for determining above-mentioned any two frames reference picture
The second relative reference value between sign point；And for when the above-mentioned second relative reference value is more than the second predetermined threshold value, it is determined that
User in above-mentioned coverage is real user.
In a possible example, above-mentioned when above-mentioned second reference value is more than the second predetermined threshold value relatively, it is determined that
User in above-mentioned coverage is real user aspect, and above-mentioned processing unit 402 is specifically used for：Determine the above-mentioned second relative ginseng
Examine the feature point group number that value is more than the second predetermined threshold value；And for when features described above point group number is more than three predetermined threshold values,
It is real user to determine the user in above-mentioned coverage.
Wherein, processing unit 402 can be processor or controller, and collecting unit 403 can be biomedical information acquisition dress
Put, such as iris information harvester, facial information harvester, finger print information harvester, memory cell 401 can be deposited
Reservoir.
The embodiment of the present invention also provides a kind of computer-readable storage medium, wherein, the computer-readable storage medium is stored for electricity
The computer program that subdata exchanges, the computer program cause computer to perform any as described in above-mentioned embodiment of the method
The part or all of step of method, above computer include mobile terminal.
The embodiment of the present invention also provides a kind of computer program product, and above computer program product includes storing calculating
The non-transient computer-readable recording medium of machine program, above computer program are operable to make computer perform side as described above
The part or all of step of either method described in method embodiment.The computer program product can be a software installation
Bag, above computer include mobile terminal.
It should be noted that for foregoing each method embodiment, in order to be briefly described, therefore it is all expressed as a series of
Combination of actions, but those skilled in the art should know, the present invention is not limited by described sequence of movement because
According to the present invention, some steps can use other orders or carry out simultaneously.Secondly, those skilled in the art should also know
Know, embodiment described in this description belongs to preferred embodiment, and involved action and module are not necessarily of the invention
It is necessary.
In the above-described embodiments, the description to each embodiment all emphasizes particularly on different fields, and does not have the portion being described in detail in some embodiment
Point, it may refer to the associated description of other embodiment.
In several embodiments provided herein, it should be understood that disclosed device, can be by another way
Realize.For example, device embodiment described above is only schematical, such as the division of said units, it is only one kind
Division of logic function, can there is an other dividing mode when actually realizing, such as multiple units or component can combine or can
To be integrated into another system, or some features can be ignored, or not perform.Another, shown or discussed is mutual
Coupling direct-coupling or communication connection can be by some interfaces, the INDIRECT COUPLING or communication connection of device or unit,
Can be electrical or other forms.
The above-mentioned unit illustrated as separating component can be or may not be physically separate, show as unit
The part shown can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On NE.Some or all of unit therein can be selected to realize the mesh of this embodiment scheme according to the actual needs
's.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, can also
That unit is individually physically present, can also two or more units it is integrated in a unit.Above-mentioned integrated list
Member can both be realized in the form of hardware, can also be realized in the form of SFU software functional unit.
If above-mentioned integrated unit is realized in the form of SFU software functional unit and is used as independent production marketing or use
When, it can be stored in a computer-readable access to memory.Based on such understanding, technical scheme substantially or
Person say the part to be contributed to prior art or the technical scheme all or part can in the form of software product body
Reveal and, the computer software product is stored in a memory, including some instructions are causing a computer equipment
(can be personal computer, server or network equipment etc.) performs all or part of each embodiment above method of the present invention
Step.And foregoing memory includes：USB flash disk, read-only storage (ROM, Read-Only Memory), random access memory
(RAM, Random Access Memory), mobile hard disk, magnetic disc or CD etc. are various can be with the medium of store program codes.
One of ordinary skill in the art will appreciate that all or part of step in the various methods of above-described embodiment is can
To instruct the hardware of correlation to complete by program, the program can be stored in a computer-readable memory, memory
It can include：Flash disk, read-only storage (English：Read-Only Memory, referred to as：ROM), random access device (English：
Random Access Memory, referred to as：RAM), disk or CD etc..
The embodiment of the present invention is described in detail above, specific case used herein to the principle of the present invention and
Embodiment is set forth, and the explanation of above example is only intended to help the method and its core concept for understanding the present invention；
Meanwhile for those of ordinary skill in the art, according to the thought of the present invention, can in specific embodiments and applications
There is change part, in summary, this specification content should not be construed as limiting the invention.
Claims (14)
- A kind of 1. mobile terminal, it is characterised in that including biological information acquisition device, processor, the biomedical information acquisition dress The connection processor is put, wherein,The processor, for detect in the range of current shooting comprising integrity degree be more than predetermined threshold value pre-set image when, Pass through the reference picture of the multiframe in the range of the biological information acquisition device continuous acquisition current shooting；The processor, it is additionally operable to pre-process the reference picture of the multiframe；The processor, it is additionally operable to obtain the pretreated set of characteristic points per frame reference picture；The processor, it is additionally operable to determine whether the user in the coverage is true according to the set of characteristic points of the acquisition Real user.
- 2. mobile terminal according to claim 1, it is characterised in that in the reference chart image space of the pretreatment multiframe Face, the processor are specifically used for：Detect in the reference picture of the multiframe is per the face size in frame reference picture It is no to be equal to preset area size；And for when detecting that the face size is not equal to preset area size, to institute State reference picture to zoom in and out so that the face size in the reference picture per frame is equal to preset area size.
- 3. mobile terminal according to claim 1 or 2, it is characterised in that in the feature point set according to the acquisition Close whether the user determined in the coverage is real user aspect, the processor is specifically used for：Obtain the feature Any two characteristic point in point set；And for determining the first relative reference value between any two characteristic point； And for when the described first relative reference value is more than the first predetermined threshold value, it to be true to determine the user in the coverage User.
- 4. mobile terminal according to claim 1 or 2, it is characterised in that in the feature point set according to the acquisition Close whether the user determined in the coverage is real user aspect, the processor is specifically used for：Obtain the multiframe Reference picture in any two frames reference picture set of characteristic points；And for determining the spy of any two frames reference picture Levy the second relative reference value between corresponding characteristic point in point set；And for being more than the in the described second relative reference value During two predetermined threshold values, it is real user to determine the user in the coverage.
- 5. mobile terminal according to claim 4, it is characterised in that be more than the in the described second relative reference value described During two predetermined threshold values, in terms of determining the user in the coverage for real user, the processor is specifically used for：Determine institute State the feature point group number that the second relative reference value is more than the second predetermined threshold value；And for being more than the 3rd in the feature point group number During predetermined threshold value, it is real user to determine the user in the coverage.
- A kind of 6. human face in-vivo detection method, it is characterised in that including：When detecting that including integrity degree in the range of current shooting is more than the pre-set image of predetermined threshold value, continuous acquisition current shooting In the range of multiframe reference picture；Pre-process the reference picture of the multiframe；Obtain the pretreated set of characteristic points per frame reference picture；Determine whether the user in the coverage is real user according to the set of characteristic points of the acquisition.
- 7. according to the method for claim 6, it is characterised in that the reference picture of the pretreatment multiframe, including：Detect in the reference picture of the multiframe and whether be equal to preset area size per the face size in frame reference picture；When detecting that the face size is not equal to preset area size, the reference picture is zoomed in and out so that Face size in the reference picture per frame is equal to preset area size.
- 8. the method according to claim 6 or 7, it is characterised in that described to be determined according to the set of characteristic points of the acquisition Whether the user in the coverage is real user, including：Obtain any two characteristic point in the set of characteristic points；Determine the first relative reference value between any two characteristic point；When the described first relative reference value is more than the first predetermined threshold value, determine that the user in the coverage uses to be true Family.
- 9. the method according to claim 6 or 7, it is characterised in that described to be determined according to the set of characteristic points of the acquisition Whether the user in the coverage is real user, including：Obtain the set of characteristic points of any two frames reference picture in the reference picture of the multiframe；Determine the second relative reference value between corresponding characteristic point in the set of characteristic points of any two frames reference picture；When the described second relative reference value is more than the second predetermined threshold value, determine that the user in the coverage uses to be true Family.
- 10. according to the method for claim 9, it is characterised in that described pre- more than second in the described second relative reference value If during threshold value, it is real user to determine the user in the coverage, including：Determine that the described second relative reference value is more than the feature point group number of the second predetermined threshold value；When the feature point group number is more than three predetermined threshold values, it is real user to determine the user in the coverage.
- A kind of 11. mobile terminal, it is characterised in that including processing unit and collecting unit,The processing unit, for detecting the pre-set image for being more than predetermined threshold value in the range of current shooting comprising integrity degree When, pass through the reference picture of the multiframe in the range of the collecting unit continuous acquisition current shooting；The processing unit, it is additionally operable to pre-process the reference picture of the multiframe；The processing unit, it is additionally operable to obtain the pretreated set of characteristic points per frame reference picture；The processing unit, be additionally operable to according to the set of characteristic points of the acquisition determine user in the coverage whether be Real user.
- 12. mobile terminal according to claim 11, it is characterised in that in the reference picture of the pretreatment multiframe Aspect, the processing unit are specifically used for：Detect big per the face area in frame reference picture in the reference picture of the multiframe It is small whether to be equal to preset area size；And for when detecting that the face size is not equal to preset area size, The reference picture is zoomed in and out so that the face size in the reference picture per frame is equal to preset area size.
- A kind of 13. mobile terminal, it is characterised in that including processor, memory, communication interface and one or more programs, Wherein, one or more of programs are stored in the memory, and are configured by the computing device, the journey Sequence includes being used for the instruction that perform claim requires the step in any one of 6-10 method.
- A kind of 14. computer-readable recording medium, it is characterised in that it stores the computer program for electronic data interchange, Wherein, the computer program causes computer to perform the method as described in claim any one of 6-10, the computer bag Include mobile terminal.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710560789.XA CN107437067A (en) | 2017-07-11 | 2017-07-11 | Human face in-vivo detection method and Related product |
| PCT/CN2018/088896 WO2019011073A1 (en) | 2017-07-11 | 2018-05-29 | Human face live detection method and related product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710560789.XA CN107437067A (en) | 2017-07-11 | 2017-07-11 | Human face in-vivo detection method and Related product |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107437067A true CN107437067A (en) | 2017-12-05 |
Family
ID=60461267
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710560789.XA Pending CN107437067A (en) | 2017-07-11 | 2017-07-11 | Human face in-vivo detection method and Related product |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN107437067A (en) |
| WO (1) | WO2019011073A1 (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109086691A (en) * | 2018-07-16 | 2018-12-25 | 阿里巴巴集团控股有限公司 | A kind of three-dimensional face biopsy method, face's certification recognition methods and device |
| WO2019011073A1 (en) * | 2017-07-11 | 2019-01-17 | Oppo广东移动通信有限公司 | Human face live detection method and related product |
| CN109614910A (en) * | 2018-12-04 | 2019-04-12 | 青岛小鸟看看科技有限公司 | A kind of face identification method and device |
| CN110199296A (en) * | 2019-04-25 | 2019-09-03 | 深圳市汇顶科技股份有限公司 | Face identification method, processing chip and electronic equipment |
| WO2020007191A1 (en) * | 2018-07-06 | 2020-01-09 | 北京三快在线科技有限公司 | Method and apparatus for living body recognition and detection, and medium and electronic device |
| CN111432279A (en) * | 2019-01-10 | 2020-07-17 | 青岛海尔多媒体有限公司 | Method and device for controlling smart television and smart television |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111860057A (en) * | 2019-04-29 | 2020-10-30 | 北京眼神智能科技有限公司 | Face image blurring and living body detection method and device, storage medium and equipment |
| CN111179234B (en) * | 2019-12-20 | 2023-08-25 | 珠海格力智能装备有限公司 | Method and device for determining hole site information of compressor |
| CN113128288A (en) * | 2019-12-31 | 2021-07-16 | 深圳云天励飞技术有限公司 | Monitoring method and related product |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102654903A (en) * | 2011-03-04 | 2012-09-05 | 井维兰 | Face comparison method |
| CN104361326A (en) * | 2014-11-18 | 2015-02-18 | 新开普电子股份有限公司 | Method for distinguishing living human face |
| CN104751110A (en) * | 2013-12-31 | 2015-07-01 | 汉王科技股份有限公司 | Bio-assay detection method and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107437067A (en) * | 2017-07-11 | 2017-12-05 | 广东欧珀移动通信有限公司 | Human face in-vivo detection method and Related product |
-
2017
- 2017-07-11 CN CN201710560789.XA patent/CN107437067A/en active Pending
-
2018
- 2018-05-29 WO PCT/CN2018/088896 patent/WO2019011073A1/en active Application Filing
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102654903A (en) * | 2011-03-04 | 2012-09-05 | 井维兰 | Face comparison method |
| CN104751110A (en) * | 2013-12-31 | 2015-07-01 | 汉王科技股份有限公司 | Bio-assay detection method and device |
| CN104361326A (en) * | 2014-11-18 | 2015-02-18 | 新开普电子股份有限公司 | Method for distinguishing living human face |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019011073A1 (en) * | 2017-07-11 | 2019-01-17 | Oppo广东移动通信有限公司 | Human face live detection method and related product |
| WO2020007191A1 (en) * | 2018-07-06 | 2020-01-09 | 北京三快在线科技有限公司 | Method and apparatus for living body recognition and detection, and medium and electronic device |
| CN109086691A (en) * | 2018-07-16 | 2018-12-25 | 阿里巴巴集团控股有限公司 | A kind of three-dimensional face biopsy method, face's certification recognition methods and device |
| CN109614910A (en) * | 2018-12-04 | 2019-04-12 | 青岛小鸟看看科技有限公司 | A kind of face identification method and device |
| CN111432279A (en) * | 2019-01-10 | 2020-07-17 | 青岛海尔多媒体有限公司 | Method and device for controlling smart television and smart television |
| CN110199296A (en) * | 2019-04-25 | 2019-09-03 | 深圳市汇顶科技股份有限公司 | Face identification method, processing chip and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2019011073A1 (en) | 2019-01-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107437067A (en) | Human face in-vivo detection method and Related product | |
| CN109711243B (en) | Static three-dimensional face in-vivo detection method based on deep learning | |
| CN105184246B (en) | Living body detection method and living body detection system | |
| CN107370942B (en) | Photographing method, photographing device, storage medium and terminal | |
| CN109858371A (en) | The method and device of recognition of face | |
| US8866931B2 (en) | Apparatus and method for image recognition of facial areas in photographic images from a digital camera | |
| CN108229369A (en) | Image capturing method, device, storage medium and electronic equipment | |
| CN109558764A (en) | Face identification method and device, computer equipment | |
| CN107273875A (en) | Human face in-vivo detection method and Related product | |
| CN107527046A (en) | Solve lock control method and Related product | |
| KR101612605B1 (en) | Method for extracting face feature and apparatus for perforimg the method | |
| CN107977650B (en) | Method for detecting human face and device | |
| CN106161962B (en) | A kind of image processing method and terminal | |
| CN107622243B (en) | Unlocking control method and related product | |
| CN107657161A (en) | Method of mobile payment and Related product based on recognition of face | |
| WO2021003964A1 (en) | Method and apparatus for face shape recognition, electronic device and storage medium | |
| CN107590474A (en) | Solve lock control method and Related product | |
| EP3944188A1 (en) | Image processing device, image processing method, and recording medium in which program is stored | |
| CN109977846B (en) | Living body detection method and system based on near-infrared monocular photography | |
| CN110956691A (en) | Three-dimensional face reconstruction method, device, equipment and storage medium | |
| CN107330316A (en) | unlocking processing method and related product | |
| CN107622246A (en) | Face identification method and Related product | |
| CN107451453A (en) | Solve lock control method and Related product | |
| CN107277265A (en) | Solve lock control method and Related product | |
| CN107451543A (en) | Event-handling method and Related product |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171205 |