CN107491775A - Human face in-vivo detection method, device, storage medium and equipment - Google Patents
Human face in-vivo detection method, device, storage medium and equipment Download PDFInfo
- Publication number
- CN107491775A CN107491775A CN201710950180.3A CN201710950180A CN107491775A CN 107491775 A CN107491775 A CN 107491775A CN 201710950180 A CN201710950180 A CN 201710950180A CN 107491775 A CN107491775 A CN 107491775A
- Authority
- CN
- China
- Prior art keywords
- face
- focal length
- facial image
- definition
- camera
- 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
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- 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 present invention discloses a kind of human face in-vivo detection method, device, storage medium and equipment, and this method includes：Acquisition step, image is gathered to face by camera, wherein, the first facial image is gathered in the first focal length, the second facial image is gathered in the second focal length, first focal length is less than the focusing focal length of the face, and second focal length is more than the focusing focal length of the face；Step is contrasted, contrasts the difference between the definition of first facial image and the definition of second facial image；First judgment step, if the result of the contrast exceedes threshold value set in advance, the face is judged for live body, otherwise, it is determined that the face is non-living body.This method has the advantages of speed is fast, and detection accuracy is high, low to hardware configuration demand.
Description
Technical field
The present invention relates to field of face identification, and in particular to a kind of human face in-vivo detection method, device, storage medium and sets
It is standby.
Background technology
At present, recognition of face has become one of technology conventional during certification user identity.However, face identification system
Easily attacked by some disabled users, wherein, due to the prevalence of the small type mobile devices such as mobile phone, tablet personal computer, lead to
Cross these portable mobile devices and play face synthesized video, to carry out the attack pattern that video attack is current more main flow.
Attacked for video, the In vivo detection scheme that industry is taken at present is divided into following a few classes substantially：
First kind scheme utilizes multiple cameras, obtains face multi-angle image, by 3D synthesize checking face whether be
Live body.Program system constructing is relative complex and amount of calculation is very big, and multiple cameras need to take larger space.
Second class scheme verifies whether face is live body using ultrasonic image, infrared image.The program is except common shooting
Configuration ultrasound, infrared camera are also needed to outside head, equipment cost is very high.
3rd class scheme be using emerging SVM (Support Vector Machine, SVMs) or other
Depth learning technology, trained by true human image and video image, it is final to distinguish live body and video.But because video playback is set
Standby otherness, the actually detected accuracy rate of the program is relatively low and unstable at present.
As can be seen that above technical scheme is all to be intended to realize that live body is examined by the way that the face for proving collection is live body
Survey, therefore these schemes are complex, the implementation cost and condition of scheme are higher, it is impossible to apply the letter in only single camera
On single gate, access control equipment, it can not more apply in configuration and such as Android (Android) of limited capacity and iOS movement
Equipment.
The content of the invention
In order to solve the above problems and the defects of prior art, realize that face live body is examined the embodiments of the invention provide one kind
Method, apparatus, storage medium and the equipment of survey.Technical scheme looks for another way, by proving that camera does not pass through
Face video gathers face, and so as to quickly and reliably detect face live body, and technical scheme only needs one
Common camera can be implemented, and hardware configuration requires low, and cost is cheap, have compatible with property and portability, especially suitable
Mobile device is closed to use.
In a first aspect, the embodiments of the invention provide a kind of method for realizing face In vivo detection, this method includes：Collection
Step, image is gathered to face by camera, wherein, the first facial image is gathered in the first focal length, is gathered in the second focal length
Second facial image, first focal length are less than the focusing focal length of the face, and second focal length is more than pair of the face
Focal length；Step is contrasted, is contrasted between the definition of first facial image and the definition of second facial image
Difference；First judgment step, if the result of the contrast exceedes threshold value set in advance, the face is judged for live body, otherwise,
Judge the face for non-living body.
With reference in a first aspect, the method for the face In vivo detection of the embodiment of the present invention also includes, the second judgment step, judge
Whether the ratio of face occupied area in the view-finder of camera is more than predetermined value, if being more than the predetermined value, performs collection
Step.
Second aspect, the embodiments of the invention provide a kind of device for realizing face In vivo detection, the device includes：Collection
Module, for gathering image to face by camera, wherein, the first facial image is gathered in the first focal length, in the second focal length
The second facial image is gathered, first focal length is less than the focusing focal length of the face, and second focal length is more than the face
Focusing focal length；Contrast module, for contrast first facial image definition and second facial image it is clear
Difference between degree；First judge module, if the result for the contrast exceedes threshold value set in advance, judge the face
For live body, otherwise, it is determined that the face is non-living body.
With reference to second aspect, the device of the face In vivo detection of the embodiment of the present invention also includes, the second judge module, judges
Whether the ratio of face occupied area in the view-finder of camera is more than predetermined value, if being more than the predetermined value, enters collection
Module.
The third aspect, the embodiments of the invention provide a kind of non-volatile memory medium, non-volatile memory medium tool
There is the instruction being stored therein, when the instruction is performed so that computing device human face in-vivo detection method, specifically, should
Instruction includes：Acquisition instructions, image is gathered to face by camera, wherein, the first facial image is gathered in the first focal length,
Second focal length gathers the second facial image, and first focal length is less than the focusing focal length of the face, and second focal length is more than
The focusing focal length of the face；Contrast instruction, contrast the definition of first facial image and second facial image
Difference between definition；First decision instruction, if the result of the contrast exceedes threshold value set in advance, judge the face
For live body, otherwise, it is determined that the face is non-living body.
With reference to the third aspect, the non-volatile memory medium can also include the second decision instruction, judge that face is imaging
Whether the ratio of occupied area is more than predetermined value in the view-finder of head, if being more than the predetermined value, performs acquisition instructions.
Fourth aspect, the embodiments of the invention provide a kind of equipment, including memory, is stored with the executable finger of computer
Order, processor, processor are configured as execute instruction to implement the process of face In vivo detection, and the process includes：Acquisition step,
Image is gathered to face by camera, wherein, the first facial image is gathered in the first focal length, the second people is gathered in the second focal length
Face image, first focal length are less than the focusing focal length of the face, and second focal length is more than the focusing focal length of the face；
Step is contrasted, contrasts the difference between the definition of first facial image and the definition of second facial image；The
One judgment step, if the result of the contrast exceedes threshold value set in advance, the face is judged for live body, otherwise, it is determined that institute
It is non-living body to state face.
With reference to fourth aspect, said process can also include the second judgment step, judge view-finder of the face in camera
Whether the ratio of middle occupied area is more than predetermined value, if being more than the predetermined value, performs acquisition step.
Based on such scheme, embodiments of the invention are fast with speed in terms of face In vivo detection, detection accuracy
Height, it is low to hardware configuration demand the advantages of, wherein, under some special scenes, embodiments of the invention 100% can detect
The face video of attacker；In addition, the human face in-vivo detection method of the present invention can be real in common gate inhibition, gate equipment
Apply, and be particularly suitable for disposing on the mobile apparatus, there is compatibility well to mobile device.
Brief description of the drawings
Fig. 1 is the indicative flowchart of human face in-vivo detection method according to an embodiment of the invention.
Fig. 2 is the indicative flowchart of human face in-vivo detection method in accordance with another embodiment of the present invention.
Fig. 3 is the schematic block diagram of face living body detection device according to an embodiment of the invention.
The schematic block diagram of face living body detection device in accordance with another embodiment of the present invention during Fig. 4.
Embodiment
To make the purpose of the embodiment of the present invention and technical scheme clearer, below in conjunction with the attached of the embodiment of the present invention
Figure, the technical scheme of the embodiment of the present invention is clearly and completely described.Obviously, described embodiment is of the invention
Part of the embodiment, rather than whole embodiments.Based on described embodiments of the invention, those of ordinary skill in the art
The every other embodiment obtained on the premise of without creative work, belongs to the scope of protection of the invention.
The technical scheme of the embodiment of the present invention can be deployed in Android, the face recognition application of iOS device, can also portion
Affix one's name to and be equipped with the gate inhibition of camera, in gate equipment.In above scene, the present invention can be passed through before recognition of face
Technical scheme, promptly carry out In vivo detection, and obtain reliably testing result.
Human face in-vivo detection method according to embodiments of the present invention is described in detail below in conjunction with Fig. 1.
Fig. 1 is the flow chart of human face in-vivo detection method 100 according to embodiments of the present invention.Method shown in Fig. 1 can be with
Performed by face living body detection device.
Specifically, as shown in figure 1, this method comprises the following steps：
Step S110, image is gathered to face by camera, wherein, the first facial image is gathered in the first focal length,
Second focal length gathers the second facial image, and the first focal length is less than the focusing focal length of face, and the focusing that the second focal length is more than face is burnt
Away from.
It should be understood that camera can be both integrated on face living body detection device, such as mobile phone, tablet personal computer, integral type
Gate inhibition and gate equipment, can also by the communication interface of face living body detection device, via mode wiredly and/or wirelessly with
Face living body detection device connects, and this is not limited by the present invention.
It is appreciated that the video attack meanses that face authentication equipment typically faces are more from compact, portable small-sized movable
Equipment, especially for the face authentication equipment of deployment in public places, only using the small-sized of mobile phone, tablet personal computer etc.
Mobile device is possible to carry out video spoofing attack to face authentication equipment on the premise of other people vigilance are not caused.Due to this
A little small type mobile devices are compact, portable, therefore their display screen plays the face meeting of video all without very greatly in screen
Face than reality is small.Therefore, small type mobile devices usually require just gather camera closer to face authentication equipment
To clearly facial image.
In S110, face living body detection device can switch the focal length of camera to switch focal plane, make when shooting face
Facial image of the camera under different focal planes, remote, the nearly two kinds of focal lengths of acquisition.It is appreciated that the focusing focal length of face is to take the photograph
Focal length during face most picture rich in detail can be gathered as head, the nearly focal length of above-mentioned camera switching is Jiao smaller than focusing focal length
Away from, and the remote focal length of camera switching is more than the focusing focal length.As an example, in order that the testing result of the present invention is more
Accurately, the nearly focal length could be arranged to the minimum focus of camera, or minimum focus is in minimum focus+10mm burnt segment limit
Arbitrary value, similarly, the remote focal length can be the maximum focal length of camera, or maximum focal length is to maximum focal length -10mm burnt section
In the range of arbitrary value.
Next, in the clear of step S120, the definition of contrast first facial image and second facial image
Difference between clear degree.
As described above, small type mobile devices generally with the distance between camera relative between real human face and camera
Distance it is smaller.According to focal plane imaging principle, for the face nearer apart from camera, nearly burnt collection facial image and
The image of remote burnt collection is compared, and the difference between both definition is smaller, i.e. the contrast of the definition of two images may not
There is significant difference, or, obscure or clearly amplitude of variation very little.Conversely, for the face apart from camera farther out,
The facial image of nearly burnt collection is compared with the image of remote burnt collection, differing greatly between both definition.
Specifically, face living body detection device can use such as edge sharpness algorithm (Edge Acutance Value,
Referred to as " EAV ") including image definition algorithm, respectively calculate near focus and a far focus image definition, then by the clear of acquisition
Clear degree calculated value subtracts each other, and obtains the comparing result of the definition difference of two kinds of images.
It is appreciated that the calculating of the definition for the embodiment of the present invention, using low as such as edge sharpness algorithm
The definition algorithm of operation strength, it is possible to obtain preferable operation result, which greatly enhances face In vivo detection of the present invention
The execution efficiency of method, also reduce the hardware configuration requirement of face living body detection device.
Next, if the result in step S130, contrast exceedes threshold value set in advance, judge that face is live body, otherwise,
Judge that face is non-living body.
As an example, setting is above-mentioned can be required to the different of detection accuracy according in the case where actually using scene
Threshold value, for example, when above-mentioned near focus and a far focus image definition difference more than 50% when, it is possible to determine that what camera was gathered
Face is live body, conversely, when the difference of the definition of above-mentioned near focus and a far focus image is not more than 50%, it is possible to determine that camera
The face gathered is non-living body.In this manner it is possible to detect that mobile device carries out the behavior of video human face attack.
Hereafter, this flow is terminated.
Therefore, the human face in-vivo detection method of the above embodiment of the present invention has that speed is fast, and detection accuracy is high, to hard
It the advantages of part configuration needs are low, can implement in common gate inhibition, gate equipment, and be particularly suitable for portion on the mobile apparatus
Administration, there is compatibility well to mobile device.
Second embodiment of the present invention discloses a kind of human face in-vivo detection method.
The human face in-vivo detection method 200 is described in detail with reference to Fig. 2.
Second embodiment is improved on the basis of first embodiment, is mainly theed improvement is that：
As shown in Fig. 2 step S210, judge face occupied area in the view-finder of camera ratio whether be more than it is pre-
Definite value, if being more than the predetermined value, perform step S220.
It is appreciated that face living body detection device can make the small-sized movable that execution video is attacked by some compulsive means
Equipment is more close to camera.
As an example, face living body detection device is before remote, the nearly burnt facial image of collection, it can be determined that face exists
The ratio of occupied area in the whole view-finder of camera, according to image-forming principle, the ratio of face occupied area is higher, illustrates people
Face is nearer apart from camera.Therefore, in order that face is closer to camera, can pre-set face should be in the whole of camera
The lower limit of the ratio of occupied area in individual view-finder, it can thus reach the mesh of distance between control face and camera
's.In addition, in other instances, distance between face and camera, example can also be judged by other distance sensing devices
Such as, above-mentioned Distance Judgment is performed by infrared induction unit integrated on mobile phone front panel etc., the present invention does not limit herein
System.
Specifically, exemplified by the method for the ratio of occupied area, people is worked as in the whole view-finder of camera to judge face
When face is appeared in the view finder of camera, face living body detection device can pass through computer conventional in face identification method
Vision storehouse OpenCV calculates face ratio shared in view-finder, if the ratio is more than or equal to face living body detection device
In ratio value set in advance, then continue executing with S220, gather the facial image of different focal；If the ratio is less than in device
Ratio value set in advance, then user can be guided close to camera by modes such as display reminding information or voice messages.This
Outside, as another example, when face is appeared in the view finder of camera, can be connected with face living body detection device
Display device on while show the real-time pictures of camera, a schematic block is shown, when profile and the schematic block of face
When sideline essentially coincides, judge that face ratio shared in view-finder meets ratio value set in advance, subsequently into next
Step.Such a mode more can intuitively guide user close to camera.
It is appreciated that for needing ratio value set in advance, can be set according to the optical parametric of camera.Citing comes
Say, wide-angle lens is generally possible to clearly be imaged interior in a big way, in order that the playback equipment of attacker is closer to taking the photograph
Can be 30%-50% by the range set of ratio value, it is preferable to set in 40%- for different wide-angle lens as head
Between 45%.Further, it is also possible to the ratio value is set according to the size of camera view-finder, before In vivo detection is not influenceed
Put, face at least will occupy 1/3rd in camera view-finder.
In method 200, step S220, S230 and S240 and step S110, S120 and S130 phase with method 100 respectively
Together, will not be repeated here.
In an embodiment of the present invention, by using above-mentioned human face in-vivo detection method, can force using attack equipment
Attacker must closer to the position of camera play face video.In such manner, it is possible to significantly increase face In vivo detection
The accuracy of method, under some special scenes, the human face in-vivo detection method 100% can detect that the face of attacker regards
Frequently.
The each method embodiment of the present invention can be realized in a manner of software, hardware, firmware etc..No matter the present invention be with
Software, hardware or firmware mode realize that instruction code may be stored in the addressable memory of any kind of computer
In (it is such as permanent or revisable, it is volatibility or non-volatile, it is solid-state or non-solid, it is fixed or
Replaceable medium of person etc.).Equally, memory may, for example, be programmable logic array (Programmable Array
Logic, referred to as " PAL "), random access memory (Random Access Memory, referred to as " RAM "), programmable read-only deposit
Reservoir (Programmable Read Only Memory, referred to as " PROM "), read-only storage (Read-Only Memory, letter
Claim " ROM "), Electrically Erasable Read Only Memory (Electrically Erasable Programmable ROM, referred to as
" EEPROM "), disk, CD, digital versatile disc (Digital Versatile Disc, referred to as " DVD ") etc..
Human face in-vivo detection method according to embodiments of the present invention is described in detail above in association with Fig. 1 to Fig. 2, below will knot
Close Fig. 3 and Fig. 4 and describe face living body detection device according to embodiments of the present invention.
Fig. 3 is the schematic block diagram of face living body detection device 300 according to embodiments of the present invention.As shown in figure 3, the people
Face living body detection device 300 includes：
Acquisition module 310, for gathering image to face by camera, wherein, gather the first face in the first focal length
Image, the second facial image is gathered in the second focal length, the first focal length is less than the focusing focal length of face, and the second focal length is more than face
Focusing focal length；
Contrast module 320, for contrast first facial image definition and second facial image it is clear
Difference between degree；
First judge module 320, if the result for contrasting exceedes threshold value set in advance, judge that face is live body, it is no
Then, judge that face is non-living body.
It is to be appreciated that the above-mentioned function of modules in the face living body detection device 300 of the embodiment of the present invention and/
Or other operations are described in detail to realize the corresponding flow of Fig. 1 method for sake of simplicity, suitably omitting herein.
Therefore, the face living body detection device 300 of the embodiment of the present invention has speed fast, and detection accuracy is high, to hardware
The advantages of configuration needs are low, it can affix one's name in common gate inhibition, gate its upper side, and be particularly suitable for portion on the mobile apparatus
Administration, there is compatibility well to mobile device.
Fig. 4 shows the schematic block diagram of face living body detection device 400 according to embodiments of the present invention.As shown in figure 4,
The face living body detection device 400 further comprises compared with device 300：
Second judge module 410, for judging whether the ratio of face occupied area in the view-finder of camera is more than
Predetermined value, if being more than the predetermined value, into next module.
It should be understood that other modules 420,430 and 440 and the respective modules phase of device 300 of face living body detection device 400
Together, in order to reduce repetition, repeat no more here.
It is to be appreciated that the above-mentioned function of modules in the face living body detection device 400 of the embodiment of the present invention and/
Or other operations are described in detail to realize the corresponding flow of method in Fig. 2 for sake of simplicity, omitting herein.
Therefore, the face living body detection device 400 of the embodiment of the present invention, further improve to the accurate of face video detection
Rate.
Further, according to an embodiment of the invention, a kind of non-volatile memory medium is also provided, the non-volatile memories
Medium has the instruction being stored therein, when the instruction is performed so that computing device human face in-vivo detection method, specifically
, the instruction includes：
Acquisition instructions, image is gathered to face by camera, wherein, the first facial image is gathered in the first focal length,
Second focal length gathers the second facial image, and first focal length is less than the focusing focal length of the face, and second focal length is more than
The focusing focal length of the face；
Contrast instruction, is contrasted between the definition of first facial image and the definition of second facial image
Difference；
First decision instruction, if the result of the contrast exceedes threshold value set in advance, the face is judged for live body, it is no
Then, judge the face for non-living body.
Alternatively, the non-volatile memory medium can also include the second decision instruction, judge face taking in camera
Whether the ratio of occupied area is more than predetermined value in scape frame, if being more than the predetermined value, performs acquisition instructions.
Further, according to another embodiment of the present invention, a kind of equipment, including memory are also provided, are stored with calculating
Machine executable instruction, processor, processor are configured as execute instruction to implement the process of face In vivo detection, the process bag
Include：
Acquisition step, image is gathered to face by camera, wherein, the first facial image is gathered in the first focal length,
Second focal length gathers the second facial image, and first focal length is less than the focusing focal length of the face, and second focal length is more than
The focusing focal length of the face；
Step is contrasted, is contrasted between the definition of first facial image and the definition of second facial image
Difference；
First judgment step, if the result of the contrast exceedes threshold value set in advance, the face is judged for live body, it is no
Then, judge the face for non-living body.
Alternatively, said process can also include the second judgment step, judge that face is shared in the view-finder of camera
Whether the ratio of area is more than predetermined value, if being more than the predetermined value, performs acquisition step.
Further, memory and processor are interconnected by bus in the said equipment.
Intelligible, processor can be central processing unit (CPU), image processor (English full name：graphics
Processing unit, abbreviation：GPU), digital signal processor (English full name：Digital signal processor, contracting
Write：DSP) or other forms integrated circuit.
Bus can use wired connected mode or use wireless communication modes, and the application is limited not to this
It is fixed.Bus can also be connected with input/output interface, additional storage (English：Secondary storage) and communication connect
Mouthful.
Input/output interface is connected with input-output apparatus, for receiving the information of input, exports operating result.It is defeated
Enter/output equipment can be mouse, keyboard, display or CD-ROM drive etc..
The storage medium of additional storage can be magnetic medium, (for example, floppy disk, hard disk, tape), optical medium (such as
CD) or semiconductor medium (such as solid state hard disc (English full name：Solid state disk, abbreviation：SSD)) etc..
Communication interface is using a kind of R-T unit of such as, but not limited to transceiver, to realize and other equipment or communication network
Communication between network, communication interface can pass through wired or wireless form and interconnection of telecommunication network.The communication network can be with
It is internet, Intranet is (English:Intranet), LAN (English full name：Local area network, abbreviation：LAN),
Wide Area Network (English full name：Wide area network, abbreviation：WAN), storage area network (English full name：storage
Area network, abbreviation：SAN) etc., or any combination of above network.
The human face in-vivo detection method of the embodiment of the present invention can be by the software code in computing device memory Lai complete
Into/support.Memory can include some softwares, for example, operating system (such as Darwin, RTXC, LINUX, UNIX, OS X,
WINDOWS or embedded OS (such as Vxworks), Android, iOS), application program and data processing module.
It should be noted that each unit mentioned in each equipment embodiment of the present invention is all logic unit, physically,
One logic unit can be a part for a physical location or a physical location, can also be with multiple physics
The combination of unit realizes that the Physical realization of these logic units in itself is not most important, and these logic units institute is real
The combination of existing function is only the key for solving technical problem proposed by the invention.In addition, in order to protrude the innovation of the present invention
Part, the above-mentioned each equipment embodiment of the present invention do not have the technical problem relation proposed by the invention with solution is less close
Unit introduce, this is not intended that the said equipment embodiment and other units is not present.
It should be noted that in the claim and specification of this patent, such as first and second or the like relation
Term is used merely to make a distinction an entity or operation with another entity or operation, and not necessarily requires or imply
Any this actual relation or order be present between these entities or operation.Moreover, term " comprising ", "comprising" or its
Any other variant is intended to including for nonexcludability so that process, method, article including a series of elements or
Equipment not only includes those key elements, but also the other element including being not expressly set out, or also include for this process,
Method, article or the intrinsic key element of equipment.In the absence of more restrictions, wanted by what sentence " including one " limited
Element, it is not excluded that other identical element in the process including the key element, method, article or equipment also be present.
Although disclosed herein various aspects and embodiment, other side and embodiment are for those skilled in the art
For will be apparent.Various aspects and embodiment disclosed herein are for illustrative purposes, and are not intended to be limited, very
The four corner instruction for the equivalent that real scope should be authorized to by appended claims and such claim.Also
It is appreciated that term used herein is merely to describe the purpose of specific embodiment, and be not intended to be limited.
Because many modifications, the changes and modifications in details can be made to described example, but before being intended to
All items shown in the description in face and accompanying drawing are interpreted the meaning that is illustrative, rather than limiting.
Claims (8)
- A kind of 1. human face in-vivo detection method, it is characterised in that including：Acquisition step, image is gathered to face by camera, wherein, the first facial image is gathered in the first focal length, second Focal length gathers the second facial image, and first focal length is less than the focusing focal length of the face, and second focal length is more than described The focusing focal length of face；Step is contrasted, contrasts the difference between the definition of first facial image and the definition of second facial image It is different；First judgment step, if the result of the contrast exceedes threshold value set in advance, the face is judged for live body, otherwise, Judge the face for non-living body.
- 2. according to the method for claim 1, it is characterised in that before the acquisition step, further comprise：Second judgment step, judge whether the ratio of face occupied area in the view-finder of the camera is more than and make a reservation for Value, if being more than the predetermined value, performs the acquisition step.
- 3. according to the method for claim 2, it is characterised in that the definition passes through respectively to first, second people Face image carries out edge sharpness and calculates acquisition.
- A kind of 4. face living body detection device, it is characterised in that including：Acquisition module, for gathering image to face by camera, wherein, the first facial image is gathered in the first focal length, Second focal length gathers the second facial image, and first focal length is less than the focusing focal length of the face, and second focal length is more than The focusing focal length of the face；Contrast module, for contrasting between the definition of first facial image and the definition of second facial image Difference；First judge module, if the result for the contrast exceedes threshold value set in advance, the face is judged for live body, it is no Then, judge the face for non-living body.
- 5. device according to claim 4, it is characterised in that before the acquisition module, further comprise：Second judge module, judge whether the ratio of face occupied area in the view-finder of the camera is more than and make a reservation for Value, if being more than the predetermined value, performs the acquisition module.
- 6. device according to claim 5, it is characterised in that the definition passes through respectively to first, second people Face image carries out edge sharpness and calculates acquisition.
- 7. a kind of non-volatile memory medium, the non-volatile memory medium has the instruction being stored therein, when the instruction When being performed so that computing device human face in-vivo detection method, the instruction include：Acquisition instructions, image is gathered to face by camera, wherein, the first facial image is gathered in the first focal length, second Focal length gathers the second facial image, and first focal length is less than the focusing focal length of the face, and second focal length is more than described The focusing focal length of face；Contrast instruction, contrasts the difference between the definition of first facial image and the definition of second facial image It is different；First decision instruction, if the result of the contrast exceedes threshold value set in advance, the face is judged for live body, otherwise, Judge the face for non-living body.
- 8. a kind of equipment, including memory, are stored with computer executable instructions, processor, the processor is configured as holding To implement the process of face In vivo detection, the process includes for the row instruction：Acquisition step, image is gathered to face by camera, wherein, the first facial image is gathered in the first focal length, second Focal length gathers the second facial image, and first focal length is less than the focusing focal length of the face, and second focal length is more than described The focusing focal length of face；Step is contrasted, contrasts the difference between the definition of first facial image and the definition of second facial image It is different；First judgment step, if the result of the contrast exceedes threshold value set in advance, the face is judged for live body, otherwise, Judge the face for non-living body.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710950180.3A CN107491775A (en) | 2017-10-13 | 2017-10-13 | Human face in-vivo detection method, device, storage medium and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710950180.3A CN107491775A (en) | 2017-10-13 | 2017-10-13 | Human face in-vivo detection method, device, storage medium and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107491775A true CN107491775A (en) | 2017-12-19 |
Family
ID=60653360
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710950180.3A Pending CN107491775A (en) | 2017-10-13 | 2017-10-13 | Human face in-vivo detection method, device, storage medium and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107491775A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108171204A (en) * | 2018-01-17 | 2018-06-15 | 百度在线网络技术（北京）有限公司 | Detection method and device |
| CN108182412A (en) * | 2017-12-29 | 2018-06-19 | 百度在线网络技术（北京）有限公司 | For the method and device of detection image type |
| CN108288056A (en) * | 2018-04-09 | 2018-07-17 | 王雅钲 | Object features extraction based on large-scale image data, identification device |
| CN108304708A (en) * | 2018-01-31 | 2018-07-20 | 广东欧珀移动通信有限公司 | Mobile terminal, face unlocking method and related product |
| CN109685018A (en) * | 2018-12-26 | 2019-04-26 | 深圳市捷顺科技实业股份有限公司 | A kind of testimony of a witness method of calibration, system and relevant device |
| CN110991356A (en) * | 2019-12-06 | 2020-04-10 | 中科智云科技有限公司 | Mobile phone playback living attack identification method based on screen edge |
| CN111144365A (en) * | 2019-12-31 | 2020-05-12 | 北京三快在线科技有限公司 | Living body detection method, living body detection device, computer equipment and storage medium |
| CN114170690A (en) * | 2022-02-14 | 2022-03-11 | 中国科学院自动化研究所 | Method and device for living body identification and construction of living body identification model |
| WO2023060756A1 (en) * | 2021-10-13 | 2023-04-20 | 深圳前海微众银行股份有限公司 | Face anti-spoofing detection method and device, and readable storage medium and computer program product |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103383723A (en) * | 2012-08-10 | 2013-11-06 | 眼验有限责任公司 | Method and system for spoof detection for biometric authentication |
| CN107135348A (en) * | 2016-02-26 | 2017-09-05 | 阿里巴巴集团控股有限公司 | Recognition methods, device, mobile terminal and the camera of reference object |
-
2017
- 2017-10-13 CN CN201710950180.3A patent/CN107491775A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103383723A (en) * | 2012-08-10 | 2013-11-06 | 眼验有限责任公司 | Method and system for spoof detection for biometric authentication |
| US20140044318A1 (en) * | 2012-08-10 | 2014-02-13 | EyeVerify LLC | Spoof Detection for Biometric Authentication |
| CN107135348A (en) * | 2016-02-26 | 2017-09-05 | 阿里巴巴集团控股有限公司 | Recognition methods, device, mobile terminal and the camera of reference object |
Non-Patent Citations (4)
| Title |
|---|
| LIBIN YANG: "Face Liveness Detection by Focusing on Frontal Faces and Image Backgrounds", 《PROCEEDINGS OF THE 2014 INTERNATIONAL CONFERENCE ON WAVELET ANALYSIS AND PATTERN RECOGNITION》 * |
| SOOYEON KIM 等: "Face Liveness Detection Using Defocus", 《SENSOR 2015》 * |
| SOOYEON KIM 等: "Face Liveness Detection using Variable Focusing", 《2013 INTERNATIONAL CONFERENCE ON BIOMETRICS（ICB）》 * |
| 郭惠楠 等: "基于色彩相关性的彩色图像清晰度评价算法", 《红外与激光工程》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108182412A (en) * | 2017-12-29 | 2018-06-19 | 百度在线网络技术（北京）有限公司 | For the method and device of detection image type |
| CN108171204A (en) * | 2018-01-17 | 2018-06-15 | 百度在线网络技术（北京）有限公司 | Detection method and device |
| CN108171204B (en) * | 2018-01-17 | 2019-09-17 | 百度在线网络技术（北京）有限公司 | Detection method and device |
| CN108304708A (en) * | 2018-01-31 | 2018-07-20 | 广东欧珀移动通信有限公司 | Mobile terminal, face unlocking method and related product |
| WO2019148968A1 (en) * | 2018-01-31 | 2019-08-08 | Oppo广东移动通信有限公司 | Mobile terminal, facial unlocking method, and related product |
| CN108288056A (en) * | 2018-04-09 | 2018-07-17 | 王雅钲 | Object features extraction based on large-scale image data, identification device |
| CN109685018A (en) * | 2018-12-26 | 2019-04-26 | 深圳市捷顺科技实业股份有限公司 | A kind of testimony of a witness method of calibration, system and relevant device |
| CN110991356A (en) * | 2019-12-06 | 2020-04-10 | 中科智云科技有限公司 | Mobile phone playback living attack identification method based on screen edge |
| CN111144365A (en) * | 2019-12-31 | 2020-05-12 | 北京三快在线科技有限公司 | Living body detection method, living body detection device, computer equipment and storage medium |
| WO2023060756A1 (en) * | 2021-10-13 | 2023-04-20 | 深圳前海微众银行股份有限公司 | Face anti-spoofing detection method and device, and readable storage medium and computer program product |
| CN114170690A (en) * | 2022-02-14 | 2022-03-11 | 中国科学院自动化研究所 | Method and device for living body identification and construction of living body identification model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107491775A (en) | Human face in-vivo detection method, device, storage medium and equipment | |
| US10455141B2 (en) | Auto-focus method and apparatus and electronic device | |
| CN109086645B (en) | Face recognition method and device and false user recognition method and device | |
| WO2020088588A1 (en) | Deep learning-based static three-dimensional method for detecting whether face belongs to living body | |
| EP3872689B1 (en) | Liveness detection method and device, electronic apparatus, storage medium and related system using the liveness detection method | |
| CN105391910B (en) | Multiple-camera laser scanner | |
| JP4912117B2 (en) | Imaging device with tracking function | |
| KR101560866B1 (en) | Viewpoint detector based on skin color area and face area | |
| EP2993894B1 (en) | Image capturing method and electronic apparatus | |
| JP6052399B2 (en) | Image processing program, image processing method, and information terminal | |
| WO2020019760A1 (en) | Living body detection method, apparatus and system, and electronic device and storage medium | |
| KR101530255B1 (en) | Cctv system having auto tracking function of moving target | |
| CN115457664A (en) | Living body face detection method and device | |
| EP3979065A1 (en) | Screen projection method and system | |
| KR20220123218A (en) | Target positioning method, apparatus, electronic device, storage medium and program | |
| CN109068118B (en) | Baseline distance adjusting method and device of double-camera module and double-camera module | |
| KR101648786B1 (en) | Method of object recognition | |
| CN109858319A (en) | Image processing equipment and control method and non-transitory computer-readable storage media | |
| CN111246116B (en) | Method for intelligent framing display on screen and mobile terminal | |
| JP2018197945A (en) | Obstacle detection apparatus and obstacle detection method | |
| TW201411565A (en) | Method for searching eyes, and eyes condition determining device and eyes searching device using the method | |
| KR20190079503A (en) | Apparatus and method for registering face posture for face recognition | |
| JP2008211534A (en) | Face detecting device | |
| JP2014085845A (en) | Moving picture processing device, moving picture processing method, program and integrated circuit | |
| CN106101539A (en) | A kind of self-shooting bar angle regulation method and self-shooting bar |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20171219 |
|
| WD01 | Invention patent application deemed withdrawn after publication |