CN106778559A - The method and device of In vivo detection - Google Patents
The method and device of In vivo detection Download PDFInfo
- Publication number
- CN106778559A CN106778559A CN201611093551.2A CN201611093551A CN106778559A CN 106778559 A CN106778559 A CN 106778559A CN 201611093551 A CN201611093551 A CN 201611093551A CN 106778559 A CN106778559 A CN 106778559A
- Authority
- CN
- China
- Prior art keywords
- sound wave
- face
- detected
- sub
- facial image
- 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
A kind of method of In vivo detection is the embodiment of the invention provides, including：Determine the face of object to be detected；The first sound wave is sent to the face of the object to be detected；Receive the second sound wave that first sound wave is obtained after the face of the object to be detected reflects；And according to first sound wave and second sound wave, judge whether the object to be detected is live body.The embodiment of the present invention is based on live body face with other prosthese materials in difference physically, strength retrogression between the sound wave obtained after calculating the sound wave for sending and reflection, and then determine whether object to be detected is live body, so it is prevented from the attack that attacker uses non-living body.
Description
Technical field
The present invention relates to field of face identification, relate more specifically to a kind of method and device of In vivo detection.
Background technology
Recognition of face, is that the facial feature information based on people carries out a kind of biological identification technology of identification.Face is known
The multiple technologies such as other integrated use digital picture, Video processing, pattern-recognition, computer vision.Currently, face identification system
Scene on the line during security protection, finance, social security etc. need the field of authentication more and more is applied to, such as bank remotely opens
Family, online trading operation demonstration, unattended gate control system, social security is handled and got, long-range medical insurance is handled etc. on line.
In the application field of these high safety ranks, except the human face similarity degree that need to ensure authenticatee meets database
The bottom storehouse of middle storage, in addition it is also necessary to verify that subject is a legal biological living.That is, face identification system needs energy
Enough security from attacks persons are attacked using modes such as photo, video, 3D faceforms or masks.Therefore, being badly in need of one kind is carried out
The technology of In vivo detection.
The content of the invention
The present invention is proposed in view of above mentioned problem.The invention provides a kind of method of In vivo detection, can interpolate that
Whether object to be detected is live body, so as to prevent attacker from using the attack of non-living body.
According to the first aspect of the invention, there is provided a kind of method of In vivo detection, including：
Determine the face of object to be detected；
The first sound wave is sent to the face of the object to be detected；
Receive the second sound wave that first sound wave is obtained after the face of the object to be detected reflects；And
According to first sound wave and second sound wave, judge whether the object to be detected is live body.
Exemplarily, the first sound wave is sent to the face of the object to be detected, including：Sound by intelligent terminal is defeated
Go out device and send first sound wave to the face of the object to be detected.
Exemplarily, it is described to receive first sound wave is obtained after the face of the object to be detected reflects second
Sound wave, including：Sound wave collection is received by the sound receiver of intelligent terminal；The sound wave collection is filtered, obtains described
Second sound wave that first sound wave is obtained after the face of the object to be detected reflects.
Exemplarily, the sound wave collection is filtered, obtains face of first sound wave by the object to be detected
Second sound wave obtained after portion's reflection, including：The sound wave is concentrated into the sound wave in preset time period, is defined as described
Second sound wave.
Exemplarily, the face for determining object to be detected, including：
By the image acquisition device video flowing of intelligent terminal；
Face datection is carried out to the video flowing, to obtain the facial image for detecting；
Whether the facial image detected described in judging is effective；And
Will determine that the face in the locus corresponding to the face in effective facial image is defined as described to be detected
The face of object.
Exemplarily, whether the facial image for being detected described in the judgement is effective, including：
If it is determined that the facial image for detecting includes the face in a face, and the facial image for detecting
The distance between face in corresponding locus and described intelligent terminal meet default requirement, it is determined that the detection
The facial image for arriving is effective.
Exemplarily, before whether the facial image detected described in the judgement is effective, also include：
The face in the locus corresponding to face in the facial image detected described in calculating is with the intelligence eventually
The distance between end.
Exemplarily, the face in the locus corresponding to face in the facial image for being detected described in the calculating
The distance between with the intelligent terminal, including：
The interpupillary distance of the face in the facial image for detecting and the image collecting device of the intelligent terminal
Machine parameter calculate the distance.
Exemplarily, first sound wave includes the multiple first sub- sound waves with different frequency, and the rising tone
Ripple includes the multiple second sub- sound waves with corresponding different frequency.
Exemplarily, it is described according to first sound wave and second sound wave, judge the object to be detected whether be
Live body, including：
It is the multiple second sub- sound wave by the rising tone Wave Decomposition, wherein, each second sub- sound wave has corresponding
Different frequency；
According to the multiple first sub- sound wave and the multiple second sub- sound wave, judge whether the object to be detected is living
Body.
Exemplarily, it is described according to the multiple first sub- sound wave and the multiple second sub- sound wave, judge described to be checked
Survey whether object is live body, including：
Calculate the intensity of the second sub- sound wave of each frequency；
The intensity of the intensity of the second sub- sound wave according to each frequency and the first sub- sound wave of respective frequencies, calculates
The strength difference of first sound wave and second sound wave；And
According to the strength difference, judge whether the object to be detected is live body.
According to the second aspect of the invention, there is provided a kind of device of In vivo detection, including：
Determining module, the face for obtaining object to be detected；
Sending module, the face of the object described to be detected for determining to the determining module sends the first sound wave；
Receiver module, for receiving what first sound wave that the sending module sends determined by the determining module
The second sound wave obtained after face's reflection of the object to be detected；And
Judge module, for the institute that first sound wave sent according to the sending module and the receiver module are received
The second sound wave is stated, judges whether the object to be detected is live body.
Exemplarily, the sending module, specifically for：By the voice output of intelligent terminal to described to be detected
The face of object sends first sound wave.
Exemplarily, the receiver module, including：Sound wave collection receiving unit, receives for the sound by intelligent terminal
Device receives sound wave collection；Second sound wave acquiring unit, for being filtered to the sound wave collection, obtains first sound wave and passes through
Second sound wave obtained after face's reflection of the object to be detected.
Exemplarily, the second sound wave acquiring unit includes the second sound wave determination subelement, for by the sound wave collection
In in preset time period sound wave, be defined as second sound wave.
Exemplarily, the determining module, including：
Video acquisition module, for the image acquisition device video flowing by intelligent terminal；
Face detection module, for carrying out Face datection to the video flowing, to obtain the facial image for detecting；
Whether face quality analysis module is effective for judging the facial image for detecting；And
Subject face determining module to be detected, for will determine that the space bit corresponding to the face in effective facial image
Face in putting is defined as the face of the object to be detected.
Exemplarily, the face quality analysis module includes effective facial image determining unit, for if it is determined that described
The facial image for detecting is included in the locus corresponding to the face in a face, and the facial image for detecting
The distance between face and the intelligent terminal meet default requirement, it is determined that the facial image for detecting is effective.
Exemplarily, described device also includes computing module, is used for：Whether have in the facial image detected described in judgement
Before effect, face and the intelligent terminal in the locus corresponding to face in the facial image detected described in calculating
The distance between.
Exemplarily, the computing module, the interpupillary distance of the face in the facial image for detecting and described
The machine parameter of the image collecting device of intelligent terminal calculates the distance.
Exemplarily, first sound wave includes the multiple first sub- sound waves with different frequency, and the rising tone
Ripple includes the multiple second sub- sound waves with corresponding different frequency.
Exemplarily, the judge module, including：
Sound wave resolving cell, for being the multiple second sub- sound wave by the rising tone Wave Decomposition, wherein, each second
Sub- sound wave has corresponding different frequency；And
Live body judging unit, for according to the multiple first sub- sound wave and the multiple second sub- sound wave, judging described
Whether object to be detected is live body.
Exemplarily, the live body judging unit includes：Strength co-mputation subelement, the second son for calculating each frequency
The intensity of sound wave；Strength difference computation subunit, for the intensity and correspondence of the second sub- sound wave according to each frequency
The intensity of the first sub- sound wave of frequency, calculates the strength difference of first sound wave and second sound wave；And live body judges
Subelement, for according to the strength difference, judging whether the object to be detected is live body.
Exemplarily, described device is the intelligent terminal with image collecting device.
The method that the device described in second aspect is implemented for the In vivo detection of aforementioned first aspect.
According to the third aspect of the invention we, there is provided a kind of computer chip, the computer chip includes processor and deposits
Reservoir.The memory storage has instruction code, and the processor is used to perform the instruction code, and when the processor is held
During row instruction code, the method that the In vivo detection described in aforementioned first aspect can be realized.
The embodiment of the present invention is based on live body face with other prosthese materials in difference physically, is sent by calculating
Sound wave and reflection after strength retrogression between the sound wave that obtains, and then determine whether object to be detected is live body, so can
Prevent attacker from using the attack of non-living body.
Brief description of the drawings
The embodiment of the present invention is described in more detail by with reference to accompanying drawing, of the invention above-mentioned and other purposes,
Feature and advantage will be apparent.Accompanying drawing is used for providing further understanding the embodiment of the present invention, and constitutes explanation
A part for book, is used to explain the present invention together with the embodiment of the present invention, is not construed as limiting the invention.In the accompanying drawings,
Identical reference number typically represents same parts or step.
Fig. 1 is a schematic block diagram of the electronic equipment of the embodiment of the present invention；
Fig. 2 is an indicative flowchart of the method for the In vivo detection of the embodiment of the present invention；
Fig. 3 is another indicative flowchart of the method for the In vivo detection of the embodiment of the present invention；
Fig. 4 is a schematic block diagram of the device of the In vivo detection of the embodiment of the present invention；
Fig. 5 is another schematic block diagram of the device of the In vivo detection of the embodiment of the present invention；
Fig. 6 is another schematic block diagram of the device of the In vivo detection of the embodiment of the present invention.
Specific embodiment
In order that obtain the object, technical solutions and advantages of the present invention becoming apparent, root is described in detail below with reference to accompanying drawings
According to example embodiment of the invention.Obviously, described embodiment is only a part of embodiment of the invention, rather than this hair
Bright whole embodiments, it should be appreciated that the present invention is not limited by example embodiment described herein.Described in the present invention
The embodiment of the present invention, those skilled in the art's all other embodiment resulting in the case where creative work is not paid
Should all fall under the scope of the present invention.
The embodiment of the present invention can apply to electronic equipment, and Fig. 1 show of the electronic equipment of the embodiment of the present invention
Schematic block diagram.Electronic equipment 10 shown in Fig. 1 include one or more processors 102, one or more storage devices 104,
Input unit 106, output device 108, imageing sensor 110 and one or more non-image sensors 114, these components lead to
Cross bus system 112 and/or other forms interconnection.It should be noted that the component and structure of electronic equipment 10 shown in Fig. 1 are to show
Example property, and it is nonrestrictive, and as needed, the electronic equipment can also have other assemblies and structure.
The processor 102 can include CPU 1021 and GPU 1022 or with data-handling capacity and/or instruction
The processing unit of the other forms of executive capability, and other components in the electronic equipment 10 can be controlled to perform expectation
Function.
The storage device 104 can include one or more computer program products, and the computer program product can
With including various forms of computer-readable recording mediums, such as volatile memory 1041 and/or nonvolatile memory
1042.The volatile memory 1041 can for example include random access memory (Random Access Memory, RAM)
And/or cache memory (cache) etc..The nonvolatile memory 1042 can for example include read-only storage
(Read-Only Memory, ROM), hard disk, flash memory etc..One or many can be stored on the computer-readable recording medium
Individual computer program instructions, processor 102 can run described program instruction, to realize various desired functions.In the meter
Various application programs and various data can also be stored in calculation machine readable storage medium storing program for executing, such as application program use and/or
Various data for producing etc..
The input unit 106 can be device of the user for input instruction, and can include keyboard, mouse, listen
One or more in cylinder and touch-screen etc..
The output device 108 can export various information (such as image or sound) to outside (such as user), and
Can be including one or more in display, loudspeaker etc..
Described image sensor 110 can shoot the desired image of user (such as photo, video etc.), and will be captured
Image store in the storage device 104 so that other components are used.
Exemplarily, the electronic equipment 10 is referred to as intelligent terminal etc., may be implemented as such as smart mobile phone, puts down
Plate computer, IMAQ end of gate control system etc..
Method shown in the embodiment of the present invention can be performed by intelligent terminal, the intelligent terminal have voice output,
Sound receiver, image collecting device etc..For example, voice output can be loudspeaker, sound receiver can be
Receiver, image collecting device can be front camera etc..Subsequent embodiment of the present invention is illustrated by taking mobile phone as an example.Due to
The limitation of existing cell phone platform hardware, the existing In vivo detection towards cell phone platform mainly uses the skill with user mutual
Art is taken precautions against prosthese and is attacked.But more perfect 3D faceforms are currently existed, being attacked in this, as prosthese has breakthrough current
The possibility that In vivo detection is taken precautions against.
In order to solve the defence imperfection of the existing In vivo detection technology towards cell phone platform, the embodiment of the present invention is provided
A kind of In vivo detection technology based on sound wave, by the material for distinguishing object judges whether destination object is live body.Namely
Say the invention provides a kind of In vivo detection scheme of use sonic wave region partial objectives for object material.This scheme is raised by cell phone platform
Sound device sends the sound of different frequency, and the sound being reflected back is received using receiver.Because face and other prosthese materials are in thing
Reason structure has significantly different, and after fixed other conditions, the strength retrogression of the sound of withdrawal has some differences.As principle,
The decay of signal is received by calculating receiver, live body and prosthese is effectively distinguished.The technical scheme that the present invention is provided can effectively take precautions against
Prosthese is attacked.
Fig. 2 is an indicative flowchart of the method for the In vivo detection of the embodiment of the present invention, the method bag shown in Fig. 2
Include：
S101, determines the face of object to be detected.
Alternatively, the face of object to be detected can be face to be detected.It is understood that the face of object to be detected can also
It is the face of other objects, face of such as particular animals etc., the present invention is not limited this.For example, in rare animal
During (such as panda) searches and rescues, the face of object to be detected can be face of the rare animal etc..But it is of the invention follow-up real
Example is applied mainly to be illustrated by taking face to be detected as an example.
Alternatively, as shown in figure 3, S101 can include：
S1011, by the image acquisition device video flowing of intelligent terminal.
S1012, Face datection is carried out to the video flowing, to obtain the facial image for detecting.
S1013, judge described in the facial image that detects it is whether effective.
S1014, will determine that the face in the locus corresponding to the face in effective facial image is defined as described
The face of face object to be detected.
Can be realized using existing Face datection algorithm in the Face datection of S1012.For example, can search in advance
Collect a large amount of facial images (such as N=10000), the rectangular window of representative's face position is manually marked out in every facial image.
It is trained using machine learning algorithm, so as to obtain Face datection algorithm.Wherein machine learning algorithm can be deep learning
Algorithm, or be regression algorithm based on local feature etc., the present invention is not limited this.
S1013 can include：If it is determined that the facial image that detects includes a face, and the face figure that detects
The distance between face in the locus corresponding to face as in and intelligent terminal meet default requirement, then can be true
The fixed facial image that this is detected is effective.That is, ensureing that and if only if in the presence of one in the facial image for detecting first
Face, and limit that the size of face in the facial image that this detects is not too much also too small must not to ensure the people for detecting
The face in the locus corresponding to face in face image is in relatively-stationary distance with intelligent terminal.
Wherein, as a kind of implementation, the space bit corresponding to the face in the facial image for detecting can be calculated
The distance between face and intelligent terminal in putting.For example, can be by image collecting device (such as preposition shooting of intelligent terminal
Head) obtain the facial image that detects, measure the interpupillary distance of the face in the facial image that this detects, and according to the interpupillary distance and
The machine parameter of the image collecting device of intelligent terminal calculates the distance.Assuming that the distance being calculated is d, default requirement is
Distance is interval [d1, d2], if meeting d1≤d≤d2, shows the space corresponding to the face in the facial image for detecting
The distance between face and intelligent terminal in position meet default requirement.
Wherein, as another implementation, it can be determined that detecting acquired in the image collecting device of intelligent terminal
Facial image in face whether be located at intelligent terminal display screen particular range within, so that it is determined that the face figure for detecting
Whether the distance between face in the locus corresponding to face as in and intelligent terminal meet default requirement.Example
Such as, a prompting frame for predefined size can be presented on the display screen of intelligent terminal, with so that in the facial image for detecting
Face alignd with the prompting frame.If the face in the facial image for detecting is located within the prompting frame, show the inspection
The distance between face in the locus corresponding to face in the facial image for measuring and intelligent terminal meet default
It is required that.
It can be seen that, if determining the face for detecting in S1013 effectively, the face that can be detected this in S1014
The face in the locus corresponding to face in image is defined as the face of object to be detected.
S102, the first sound wave is sent to the face of the object to be detected.
Specifically, the first sound can be sent to the face of the object to be detected by the voice output of intelligent terminal
Ripple.If for example, intelligent terminal is mobile phone, can be sent by the loudspeaker of cell phone platform.
Alternatively, first sound wave can have a frequency.
Alternatively, first sound wave can include multiple first sub- sound waves, and the first different sub- sound waves have it is different
Frequency.That is, the first sound wave can the sound of multiple different frequencies be composited.Alternatively, first sound wave can
There is fixed time interval between cycle periodically to send and different.For example, the cycle of transmission can be 0.5 second
S (), fixed time interval can be 1s.The duration that i ＆ lt sends the first sound wave can be expressed as [ti, ti+0.5], and
And t (i+1)=ti+1.5.In such manner, it is possible to the interference of the reflection sound wave in preventing environment such that it is able to increase the reliability of result
Property.
In the embodiment of the present invention, the first sound wave is properly termed as the voice output (such as loudspeaker of mobile phone) of intelligent terminal
The specified sound for sending, the specified sound can be the letter synthesized by the sound multiplexing of the various different frequencies for setting
Number.And the resource of the specified sound can be by the Software Create for the treatment of audio.In order to prevent sound wave from directly propagating or through background objects
The sound wave interference result of body reflection, tune is regularly interval sounding, such as, at interval of 1 second sounding 0.5 second, continue one
The section time.So repeatedly inspection can increase the reliability of result.
S103, receives the second sound wave that first sound wave is obtained after the face of the object to be detected reflects.
Specifically, sound wave collection can be received by the sound receiver of intelligent terminal；And the sound wave collection was carried out
Filter, obtains second sound wave that first sound wave is obtained after the face of the object to be detected reflects.Wherein it is possible to
The sound wave is concentrated into the sound wave in preset time period, is defined as second sound wave.Wherein, sound receiver can be such as
It is receiver.
For example, the sound receiver of intelligent terminal can be opened, and the whole lower sound to be received of record, i.e. sound wave
Collection.Here filtering is to only retain the sound wave obtained after destination object (face of object i.e. to be detected) reflection as far as possible.
Specific filter method to retain the sound wave of [ti+ (2d/c)-e, ti+ (2d/c)+e] time period, will sound wave concentrate the time of being in
The sound wave of section [ti+ (2d/c)-e, ti+ (2d/c)+e] is defined as the second sound wave.Wherein ti is rising for the first sound wave i ＆ lt sounding
Begin the moment, d is the face of object to be detected to the distance of intelligent terminal, c is the speed that sound is propagated in atmosphere, and e is one
The value of very little, represents error range.For example, c=340m/s, e=10-6.Wherein d can be the face in facial image
What the machine parameter of the image collecting device of interpupillary distance and intelligent terminal was calculated, circular may refer to foregoing
The description of S1013 parts, to avoid repeating, repeats no more here.
S104, according to first sound wave and second sound wave, judges whether the object to be detected is live body.
Specifically, if the difference of the intensity of the intensity of the first sound wave and the second sound wave meets default threshold value, it is determined that should
Object to be detected is live body.Wherein, the difference of the intensity of the intensity of the first sound wave and the second sound wave is properly termed as the pad value of intensity.
S104 can include：According to the strength difference between the second sound wave and the first sound wave, the object to be detected is judged
Whether it is live body.If the difference of the intensity meets default threshold value, it is determined that the object to be detected is live body.
It is alternatively possible to passing through below equation calculates intensity：
Ldb=20 × log (A1/A0), formula 1
Wherein, A1 represents the peak swing of sound wave.A0 is an a reference value, can be a constant.It is understood that intensity
Pad value can be the reduction amount of decibel.
Wherein, default threshold value can be directed to what is obtained after multiple (or substantial amounts of) live bodies are tested, or, can be with
It is that, by being calculated by way of numerical simulation, the present invention is not limited this.
If the first sound wave includes the multiple first sub- sound waves with different frequency, then, it is appreciated that corresponding the
Two sound waves can also include the multiple second sub- sound waves with corresponding different frequency.The second sound wave for receiving is entered first now
Row is decomposed.That is, the second sound wave is split as multiple second sub- sound waves, wherein, each second sub- sound wave has corresponding different frequencies
Rate, then calculates intensity respectively for each second sub- sound wave again.
That is, S104 can include：It is the multiple second sub- sound wave by the rising tone Wave Decomposition, wherein, each second
Sub- sound wave has corresponding different frequency；And according to the multiple first sub- sound wave and the multiple second sub- sound wave, judge
Whether the object to be detected is live body.
Specifically, it is described according to the multiple first sub- sound wave and the multiple second sub- sound wave, judge described to be detected
Whether object is live body, including：Calculate the intensity of the second sub- sound wave of each frequency；The second sub- sound according to each frequency
The intensity of the intensity of ripple and the first of respective frequencies the sub- sound wave, calculates the intensity difference of first sound wave and second sound wave
Value；And according to the strength difference, judge whether the object to be detected is live body.
Where it is assumed that the first sound wave is synthesized by m the first of different frequency the sub- sound wave, then accordingly, the second sound wave can be with
It is broken down into m the second sub- sound wave of corresponding different frequency, it is possible to use formula 1：Ldb=20 × log (A1/A0) calculates every
The intensity L of the second sub- sound wave of individual frequencydb1... ..Ldbm.The intensity of the second sub- sound wave according to each frequency and right
The intensity of the first sub- sound wave of frequency is answered, the strength difference Δ L of first sound wave and second sound wave is calculateddb1... ..
ΔLdbm.According to the strength difference, judge whether the object to be detected is live body.For example, each intensity that will can be obtained
Difference is compared with corresponding threshold value, obtains the relation of each strength difference and corresponding threshold value, and according to default condition
(for example, a certain proportion of strength difference meets the threshold value), judges whether the object to be detected is live body.
The physical principle of the embodiment of the present invention is：Sound wave is different by the strength retrogression after different material reflections.Also
It is to say, the sound of same frequency, the strength retrogression of the sound returned after being reflected through live body and prosthese is different.
In order to ensure the reliability of result, the embodiment of the present invention can be used the sound of different frequency repeatedly to test, you can with
S102 to S104 is repeated, wherein, the first sound wave has a certain frequency and each frequency is different.Or, the present invention is implemented
The sound wave of multiple different frequencies can be combined and detected again by example, i.e., as described in above-mentioned S102, the first sound wave includes
Multiple first sub- sound waves with different frequency.Time that transmission is received etc. can be so reduced, so as to improve efficiency.
The embodiment of the present invention is based on live body face with other prosthese materials in difference physically, is sent by calculating
Sound wave and reflection after strength retrogression between the sound wave that obtains, and then determine whether object to be detected is live body, so can
Prevent attacker from using the attack of non-living body.In addition, the sound wave for being sent can be the compound of the sound of multiple frequencies, so will
The sound wave of multiple frequencies sends together, while result reliability is ensured, can improve the efficiency of detection.
In addition, the description based on the method above with respect to the In vivo detection understands, the method is based on the first sound wave for sending
The second sound wave with reflection carries out In vivo detection, and influence of other background sounds to the method is larger, therefore when performing the method
Should be at a more quiet environment, it is preferable that user may be at quietly and more spacious scene, can so avoiding the back of the body
The influence of the reflection sound of scape sound and other barriers.At the same time, the method that this method can use gap sounding, and it is right
The sound wave for receiving is filtered, so as to the interference that reflection of the background object to sound wave is produced can be excluded.
Fig. 4 is a schematic block diagram of the device of the In vivo detection of the embodiment of the present invention.Device 40 shown in Fig. 4 is wrapped
Include：Determining module 401, sending module 402, receiver module 403 and judge module 404.
Determining module 401, the face for determining object to be detected；
Sending module 402, the face of the object described to be detected for determining to determining module 401 sends the first sound wave；
Receiver module 403, for receiving first sound wave of the transmission of sending module 402 by the object to be detected
The second sound wave obtained after face's reflection；
Judge module 404, what first sound wave and receiver module 403 for being sent according to sending module 402 were received
Second sound wave, judges whether the object to be detected is live body.
Exemplarily, the sending module 402, specifically for：Treated to described by the voice output of intelligent terminal
The face of detection object sends first sound wave.In the embodiment of the present invention, sending module 402 be referred to as transmitter module or
Person's acoustic emission module.
Exemplarily, the receiver module 403, can include：Sound wave collection receiving unit, for the sound by intelligent terminal
Sound reception device receives sound wave collection；And the second sound wave acquiring unit, for being filtered to the sound wave collection, obtain described
Second sound wave that one sound wave is obtained after the face of the object to be detected reflects.In the embodiment of the present invention, mould is received
Block 403 is referred to as acoustic receiver module.
Wherein, the second sound wave acquiring unit includes the second sound wave determination subelement, for by the sound wave concentration
In the sound wave of preset time period, it is defined as second sound wave.
Exemplarily, judge module 404 is referred to as live body judge module, can be used for：According to the second sound wave and
The pad value of the intensity between one sound wave, judges whether the object to be detected is live body.If the pad value of the intensity meets pre-
If threshold value, it is determined that the object to be detected be live body.
Exemplarily, as shown in figure 5, determining module 401 can include video acquisition module 4011, face detection module
4012nd, face quality analysis module 4013 and subject face determining module 4014 to be detected.
Video acquisition module 4011, for the image acquisition device video flowing by intelligent terminal；Face datection mould
Block 4012, for carrying out Face datection to the video flowing, to obtain the facial image for detecting；Face quality analysis module
4013, it is whether effective for judging the facial image for detecting；Subject face determining module 4014 to be detected, for that will sentence
The face in the locus corresponding to face in disconnected effective facial image is defined as the face of the object to be detected.
Wherein, the video stream that video acquisition module 4011 will be gathered is to face detection module 4012.Face datection mould
Block 4012 is referred to as face character analysis module, and the facial image that will be detected is sent to face quality analysis module
4013.Face quality analysis module 4013 is referred to as face quality detection module, and face quality analysis module 4013 can be with
Including effective facial image determining unit, it is used for：If it is determined that the facial image for detecting includes a face, and the inspection
The distance between face in the locus corresponding to face in the facial image for measuring and described intelligent terminal meet pre-
If requirement, it is determined that the facial image for detecting is effective.Subject face determining module 4014 to be detected can be used specifically
In：If the facial image for detecting is confirmed as effectively, the sky corresponding to face in the facial image that this is detected
Between face in position be defined as the face of object to be detected.
Exemplarily, as shown in fig. 6, computing module 4015 can also be included, it is used for：In the face detected described in judgement
Image whether effectively before, calculate described in face in locus corresponding to face in the facial image that detects and institute
State the distance between intelligent terminal.
Exemplarily, computing module 4015 can be according to the interpupillary distance of the face in the facial image for detecting and institute
The machine parameter for stating the image collecting device of intelligent terminal calculates the distance.
Exemplarily, first sound wave includes the multiple first sub- sound waves with different frequency, and the rising tone
Ripple includes the multiple second sub- sound waves with corresponding different frequency.
Exemplarily, judge module 404 can include：Sound wave resolving cell, for being institute by the rising tone Wave Decomposition
Multiple second sub- sound waves are stated, wherein, each second sub- sound wave has corresponding different frequency；And live body judging unit, it is used for
According to the multiple first sub- sound wave and the multiple second sub- sound wave, judge whether the object to be detected is live body.
Specifically, live body judging unit includes：Strength co-mputation subelement, the second sub- sound wave for calculating each frequency
Intensity；Strength difference computation subunit, intensity and respective frequencies for the second sub- sound wave according to each frequency
The intensity of the first sub- sound wave, calculates the strength difference of first sound wave and second sound wave；And live body judgment sub-unit,
For according to the strength difference, judging whether the object to be detected is live body.
Exemplarily, device 40 can be the intelligent terminal with image collecting device.For example, can be to be taken the photograph with preposition
As the mobile phone of head.
The method that device 40 shown in Fig. 4-Fig. 6 is implemented for the In vivo detection shown in earlier figures 2- Fig. 3.
In addition, the embodiment of the present invention additionally provides a kind of electronic equipment, the electronic equipment includes device 40.
Alternatively, the device 40 can include processor and memory, wherein, memory is used for store instruction code, place
When reason device performs the instruction code, it is possible to achieve the method for the In vivo detection shown in earlier figures 2 or Fig. 3.
Example of the invention provides a kind of In vivo detection scheme of use sonic wave region partial objectives for object material.This scheme passes through
The loudspeaker of the voice output of intelligent terminal, such as cell phone platform, sends the sound of different frequency, and uses intelligent terminal
Sound receiver, such as receiver, the sound that is reflected back of reception.Because live body face and other prosthese materials are in physical arrangement
Have significantly different, after fixed other conditions, the strength retrogression of the sound being reflected back has some differences.As principle, pass through
The decay for receiving signal is calculated, live body and prosthese is effectively distinguished.
Although the example embodiment by reference to Description of Drawings here, it should be understood that above-mentioned example embodiment is merely exemplary
, and be not intended to limit the scope of the invention to this.Those of ordinary skill in the art can wherein carry out various changes
And modification, it is made without departing from the scope of the present invention and spirit.All such changes and modifications are intended to be included in appended claims
Within required the scope of the present invention.
Those of ordinary skill in the art are it is to be appreciated that the list of each example described with reference to the embodiments described herein
Unit and algorithm steps, can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
Performed with hardware or software mode, depending on the application-specific and design constraint of technical scheme.Professional and technical personnel
Described function, but this realization can be realized it is not considered that exceeding using distinct methods to each specific application
The scope of the present invention.
In several embodiments provided herein, it should be understood that disclosed apparatus and method, can be by it
Its mode is realized.For example, apparatus embodiments described above are only schematical, for example, the division of the unit, only
Only a kind of division of logic function, can there is other dividing mode when actually realizing, such as multiple units or component can be tied
Another equipment is closed or is desirably integrated into, or some features can be ignored, or do not perform.
In specification mentioned herein, numerous specific details are set forth.It is to be appreciated, however, that implementation of the invention
Example can be put into practice in the case of without these details.In some instances, known method, structure is not been shown in detail
And technology, so as not to obscure the understanding of this description.
Similarly, it will be appreciated that in order to simplify the present invention and help to understand one or more in each inventive aspect, exist
In to the description of exemplary embodiment of the invention, each feature of the invention be grouped together into sometimes single embodiment, figure,
Or in descriptions thereof.However, the method for the present invention should be construed to reflect following intention：It is i.e. required for protection
Application claims features more more than the feature being expressly recited in each claim.More precisely, such as corresponding power
As sharp claim reflects, its inventive point is that can use the spy of all features less than certain disclosed single embodiment
Levy to solve corresponding technical problem.Therefore, it then follows it is specific that thus claims of specific embodiment are expressly incorporated in this
Implementation method, wherein each claim are in itself as separate embodiments of the invention.
It will be understood to those skilled in the art that in addition to mutually exclusive between feature, any combinations pair can be used
All features and so disclosed any method disclosed in this specification (including adjoint claim, summary and accompanying drawing)
Or all processes or unit of equipment are combined.Unless expressly stated otherwise, this specification (including adjoint right will
Ask, make a summary and accompanying drawing) disclosed in each feature can the alternative features of or similar purpose identical, equivalent by offer replace.
Although additionally, it will be appreciated by those of skill in the art that some embodiments described herein include other embodiments
In included some features rather than further feature, but the combination of the feature of different embodiments means in of the invention
Within the scope of and form different embodiments.For example, in detail in the claims, embodiment required for protection it is one of any
Mode can use in any combination.
All parts embodiment of the invention can be realized with hardware, or be run with one or more processor
Software module realize, or with combinations thereof realize.It will be understood by those of skill in the art that can use in practice
Microprocessor or digital signal processor (DSP) realize some moulds in article analytical equipment according to embodiments of the present invention
The some or all functions of block.The present invention is also implemented as the part or complete for performing method as described herein
The program of device (for example, computer program and computer program product) in portion.It is such to realize that program of the invention be stored
On a computer-readable medium, or can have one or more signal form.Such signal can be from internet
Downloaded on website and obtained, or provided on carrier signal, or provided in any other form.
It should be noted that above-described embodiment the present invention will be described rather than limiting the invention, and ability
Field technique personnel can design alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference symbol being located between bracket should not be configured to limitations on claims.Word "comprising" is not excluded the presence of not
Element listed in the claims or step.Word "a" or "an" before element is not excluded the presence of as multiple
Element.The present invention can come real by means of the hardware for including some different elements and by means of properly programmed computer
It is existing.If in the unit claim for listing equipment for drying, several in these devices can be by same hardware branch
To embody.The use of word first, second, and third does not indicate that any order.These words can be explained and run after fame
Claim.
The above, specific embodiment only of the invention or the explanation to specific embodiment, protection of the invention
Scope is not limited thereto, any one skilled in the art the invention discloses technical scope in, can be easily
Expect change or replacement, should all be included within the scope of the present invention.Protection scope of the present invention should be with claim
Protection domain is defined.
Claims (23)
1. a kind of method of In vivo detection, it is characterised in that including：
Determine the face of object to be detected；
The first sound wave is sent to the face of the object to be detected；
Receive the second sound wave that first sound wave is obtained after the face of the object to be detected reflects；And
According to first sound wave and second sound wave, judge whether the object to be detected is live body.
2. the method for claim 1, it is characterised in that send the first sound wave, bag to the face of the object to be detected
Include：
First sound wave is sent to the face of the object to be detected by the voice output of intelligent terminal.
3. the method for claim 1, it is characterised in that reception first sound wave is by the object to be detected
Face's reflection after the second sound wave for obtaining, including：
Sound wave collection is received by the sound receiver of intelligent terminal；And
The sound wave collection is filtered, obtains what first sound wave was obtained after the face of the object to be detected reflects
Second sound wave.
4. method as claimed in claim 3, it is characterised in that filtered to the sound wave collection, obtain first sound wave
By second sound wave obtained after face's reflection of the object to be detected, including：
The sound wave is concentrated into the sound wave in preset time period, is defined as second sound wave.
5. the method for claim 1, it is characterised in that the face of the determination object to be detected, including：
By the image acquisition device video flowing of intelligent terminal；
Face datection is carried out to the video flowing, to obtain the facial image for detecting；
Whether the facial image detected described in judging is effective；And
Will determine that the face in the locus corresponding to the face in effective facial image is defined as the object to be detected
Face.
6. method as claimed in claim 5, it is characterised in that the facial image detected described in the judgement whether effectively,
Including：
If it is determined that the facial image for detecting includes that the face institute in a face, and the facial image for detecting is right
The distance between face in the locus answered and described intelligent terminal meet default requirement, it is determined that described to detect
Facial image is effective.
7. method as claimed in claim 6, it is characterised in that whether effective in the facial image detected described in the judgement
Before, also include：
Face and the intelligent terminal in the locus corresponding to face in the facial image that detects described in calculating it
Between distance.
8. method as claimed in claim 7, it is characterised in that the face institute in the facial image detected described in the calculating
The distance between face in corresponding locus and described intelligent terminal, including：
The machine of the interpupillary distance of the face in the facial image for detecting and the image collecting device of the intelligent terminal
Device parameter calculates the distance.
9. the method as described in any one of claim 1 to 8, it is characterised in that first sound wave includes thering is different frequency
Multiple first sub- sound waves, and second sound wave includes the multiple second sub- sound waves with corresponding different frequency.
10. method as claimed in claim 9, it is characterised in that described according to first sound wave and second sound wave, sentences
Whether the object to be detected that breaks is live body, including：
It is the multiple second sub- sound wave by the rising tone Wave Decomposition, wherein, each second sub- sound wave has corresponding difference
Frequency；And
According to the multiple first sub- sound wave and the multiple second sub- sound wave, judge whether the object to be detected is live body.
11. methods as claimed in claim 10, it is characterised in that described according to the multiple first sub- sound wave and the multiple
Second sub- sound wave, judges whether the object to be detected is live body, including：
Calculate the intensity of the second sub- sound wave of each frequency；
The intensity of the intensity of the second sub- sound wave according to each frequency and the first sub- sound wave of respective frequencies, calculates described
The strength difference of the first sound wave and second sound wave；And
According to the strength difference, judge whether the object to be detected is live body.
A kind of 12. devices of In vivo detection, it is characterised in that including：
Determining module, the face for determining object to be detected；
Sending module, the face of the object described to be detected for determining to the determining module sends the first sound wave；
Receiver module, for receiving first sound wave of the sending module transmission by described in determining module determination
The second sound wave obtained after face's reflection of object to be detected；And
Judge module, described the received for first sound wave sent according to the sending module and the receiver module
Two sound waves, judge whether the object to be detected is live body.
13. devices as claimed in claim 12, it is characterised in that the sending module, specifically for：
First sound wave is sent to the face of the object to be detected by the voice output of intelligent terminal.
14. devices as claimed in claim 12, it is characterised in that the receiver module, including：
Sound wave collection receiving unit, sound wave collection is received for the sound receiver by intelligent terminal；And
Second sound wave acquiring unit, for being filtered to the sound wave collection, obtains first sound wave by described to be detected
Second sound wave obtained after face's reflection of object.
15. devices as claimed in claim 14, it is characterised in that the second sound wave acquiring unit determines including the second sound wave
Subelement, for the sound wave to be concentrated into the sound wave in preset time period, is defined as second sound wave.
16. devices as claimed in claim 12, it is characterised in that the determining module, including：
Video acquisition module, for the image acquisition device video flowing by intelligent terminal；
Face detection module, for carrying out Face datection to the video flowing, to obtain the facial image for detecting；
Whether face quality analysis module is effective for judging the facial image for detecting；And
Subject face determining module to be detected, for will determine that the locus corresponding to the face in effective facial image in
Face be defined as the face of the object to be detected.
17. devices as claimed in claim 16, it is characterised in that the face quality analysis module, including effective face figure
As determining unit, for if it is determined that the facial image for detecting includes a face, and the facial image for detecting
In face corresponding to locus in the distance between face and the intelligent terminal meet default requirement, it is determined that
The facial image for detecting is effective.
18. devices as claimed in claim 17, it is characterised in that also including computing module, be used for：
Before whether the facial image detected described in judging is effective, the face institute in the facial image detected described in calculating
The distance between face in corresponding locus and described intelligent terminal.
19. devices as claimed in claim 18, it is characterised in that the facial image that the computing module is detected according to
In the machine parameter of image collecting device of interpupillary distance and the intelligent terminal of face calculate the distance.
20. device as described in any one of claim 12 to 19, it is characterised in that first sound wave includes thering is different frequencies
Multiple first sub- sound waves of rate, and second sound wave includes the multiple second sub- sound waves with corresponding different frequency.
21. devices as claimed in claim 20, it is characterised in that the judge module, including：
Sound wave resolving cell, for being the multiple second sub- sound wave by the rising tone Wave Decomposition, wherein, each second sub- sound
Ripple has corresponding different frequency；And
Live body judging unit, for according to the multiple first sub- sound wave and the multiple second sub- sound wave, judging described to be checked
Survey whether object is live body.
22. devices as claimed in claim 21, it is characterised in that the live body judging unit includes：
Strength co-mputation subelement, the intensity of the second sub- sound wave for calculating each frequency；
Strength difference computation subunit, the of intensity and respective frequencies for the second sub- sound wave according to each frequency
The intensity of one sub- sound wave, calculates the strength difference of first sound wave and second sound wave；And
Live body judgment sub-unit, for according to the strength difference, judging whether the object to be detected is live body.
23. device as described in any one of claim 12 to 19, it is characterised in that described device is with image collecting device
Intelligent terminal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611093551.2A CN106778559A (en) | 2016-12-01 | 2016-12-01 | The method and device of In vivo detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611093551.2A CN106778559A (en) | 2016-12-01 | 2016-12-01 | The method and device of In vivo detection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106778559A true CN106778559A (en) | 2017-05-31 |
Family
ID=58882700
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611093551.2A Pending CN106778559A (en) | 2016-12-01 | 2016-12-01 | The method and device of In vivo detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106778559A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107273875A (en) * | 2017-07-18 | 2017-10-20 | 广东欧珀移动通信有限公司 | Human face in-vivo detection method and Related product |
| CN108921080A (en) * | 2018-06-27 | 2018-11-30 | 北京旷视科技有限公司 | Image-recognizing method, device and electronic equipment |
| CN110020520A (en) * | 2019-03-26 | 2019-07-16 | 华中科技大学 | A kind of recognition of face assistant authentification method and system based on voice signal |
| CN110321756A (en) * | 2018-03-28 | 2019-10-11 | 北京语智科技有限公司 | In vivo detection system and method |
| CN110688957A (en) * | 2019-09-27 | 2020-01-14 | 腾讯科技（深圳）有限公司 | Living body detection method and device applied to face recognition and storage medium |
| CN111639519A (en) * | 2020-04-07 | 2020-09-08 | 北京海关技术中心 | Living body detection method and device |
| CN112001240A (en) * | 2020-07-15 | 2020-11-27 | 浙江大华技术股份有限公司 | Living body detection method, living body detection device, computer equipment and storage medium |
| CN112449053A (en) * | 2019-09-04 | 2021-03-05 | 北京小米移动软件有限公司 | Control method and device for prompt signal of mobile terminal and storage medium |
| CN112507798A (en) * | 2020-11-12 | 2021-03-16 | 上海优扬新媒信息技术有限公司 | Living body detection method, electronic device, and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101541238A (en) * | 2007-01-24 | 2009-09-23 | 松下电器产业株式会社 | Biological information measurement device and method of controlling the same |
| CN101751551A (en) * | 2008-12-05 | 2010-06-23 | 比亚迪股份有限公司 | Method, device, system and device for identifying face based on image |
| CN102622588A (en) * | 2012-03-08 | 2012-08-01 | 无锡数字奥森科技有限公司 | Dual-certification face anti-counterfeit method and device |
| WO2014171983A1 (en) * | 2013-04-18 | 2014-10-23 | Wichita State University | Non-invasive biofeedback system |
| CN104915649A (en) * | 2015-06-04 | 2015-09-16 | 南京理工大学 | Living person detection method applied to face recognition |
| CN105912986A (en) * | 2016-04-01 | 2016-08-31 | 北京旷视科技有限公司 | In vivo detection method, in vivo detection system and computer program product |
-
2016
- 2016-12-01 CN CN201611093551.2A patent/CN106778559A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101541238A (en) * | 2007-01-24 | 2009-09-23 | 松下电器产业株式会社 | Biological information measurement device and method of controlling the same |
| CN101751551A (en) * | 2008-12-05 | 2010-06-23 | 比亚迪股份有限公司 | Method, device, system and device for identifying face based on image |
| CN102622588A (en) * | 2012-03-08 | 2012-08-01 | 无锡数字奥森科技有限公司 | Dual-certification face anti-counterfeit method and device |
| WO2014171983A1 (en) * | 2013-04-18 | 2014-10-23 | Wichita State University | Non-invasive biofeedback system |
| CN104915649A (en) * | 2015-06-04 | 2015-09-16 | 南京理工大学 | Living person detection method applied to face recognition |
| CN105912986A (en) * | 2016-04-01 | 2016-08-31 | 北京旷视科技有限公司 | In vivo detection method, in vivo detection system and computer program product |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107273875A (en) * | 2017-07-18 | 2017-10-20 | 广东欧珀移动通信有限公司 | Human face in-vivo detection method and Related product |
| CN110321756A (en) * | 2018-03-28 | 2019-10-11 | 北京语智科技有限公司 | In vivo detection system and method |
| CN108921080A (en) * | 2018-06-27 | 2018-11-30 | 北京旷视科技有限公司 | Image-recognizing method, device and electronic equipment |
| CN110020520B (en) * | 2019-03-26 | 2021-03-26 | 华中科技大学 | Face recognition auxiliary authentication method and system based on sound signals |
| CN110020520A (en) * | 2019-03-26 | 2019-07-16 | 华中科技大学 | A kind of recognition of face assistant authentification method and system based on voice signal |
| CN112449053A (en) * | 2019-09-04 | 2021-03-05 | 北京小米移动软件有限公司 | Control method and device for prompt signal of mobile terminal and storage medium |
| CN110688957A (en) * | 2019-09-27 | 2020-01-14 | 腾讯科技（深圳）有限公司 | Living body detection method and device applied to face recognition and storage medium |
| CN110688957B (en) * | 2019-09-27 | 2023-06-30 | 腾讯科技（深圳）有限公司 | Living body detection method, device and storage medium applied to face recognition |
| CN111639519A (en) * | 2020-04-07 | 2020-09-08 | 北京海关技术中心 | Living body detection method and device |
| CN111639519B (en) * | 2020-04-07 | 2023-06-20 | 北京海关技术中心 | Living body detection method and living body detection device |
| CN112001240A (en) * | 2020-07-15 | 2020-11-27 | 浙江大华技术股份有限公司 | Living body detection method, living body detection device, computer equipment and storage medium |
| CN112507798A (en) * | 2020-11-12 | 2021-03-16 | 上海优扬新媒信息技术有限公司 | Living body detection method, electronic device, and storage medium |
| CN112507798B (en) * | 2020-11-12 | 2024-02-23 | 度小满科技(北京)有限公司 | Living body detection method, electronic device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106778559A (en) | The method and device of In vivo detection | |
| RU2725413C2 (en) | Systems and methods for detecting fraudulent objects and analyzing vitality | |
| CN105912986B (en) | A kind of biopsy method and system | |
| CN106407914A (en) | Method for detecting human faces, device and remote teller machine system | |
| CN106778525A (en) | Identity identifying method and device | |
| CN106952303A (en) | Vehicle distance detecting method, device and system | |
| Zhu et al. | Magnitude estimation for earthquake early warning using a deep convolutional neural network | |
| CN106265004A (en) | Multi-sensor intelligent blind person's guiding method and device | |
| CN106646587B (en) | Object detection and recognition method and system based on acoustic vibration signal | |
| CN107077550A (en) | Biology contact for user's checking | |
| CN107942335A (en) | A kind of object identification method and equipment | |
| CN108875333A (en) | Terminal unlock method, terminal and computer readable storage medium | |
| CN103324918A (en) | Identity authentication method with face identification and lip identification matched | |
| CN107358699A (en) | A kind of safe verification method and system | |
| JP2019532387A (en) | Infant detection for electronic gate environments | |
| CN106951833A (en) | Human face image collecting device and man face image acquiring method | |
| Aravind et al. | Audio spoofing verification using deep convolutional neural networks by transfer learning | |
| CN111444788B (en) | Behavior recognition method, apparatus and computer storage medium | |
| CN107038784A (en) | Safe verification method and device | |
| KR20160142095A (en) | Apparatus and method of detection stress and classification stress using of chicken sound | |
| CN109922311A (en) | Monitoring method, device, terminal and storage medium based on audio/video linkage | |
| CN106940904A (en) | Attendance checking system based on recognition of face and speech recognition | |
| DE502004007690D1 (en) | METHOD OF ACCEPTANCE OF FACILITIES, APPLICABLE ARRANGEMENT AND EQUIPMENT | |
| CN107221338A (en) | Sound wave extraction element and extracting method | |
| CN107894837A (en) | Dynamic sentiment analysis model sample processing method and processing device |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 100190 Beijing, Haidian District Academy of Sciences, South Road, No. 2, block A, No. 313 Applicant after: MEGVII INC. Applicant after: Beijing maigewei Technology Co., Ltd. Address before: 100190 Beijing, Haidian District Academy of Sciences, South Road, No. 2, block A, No. 313 Applicant before: MEGVII INC. Applicant before: Beijing aperture Science and Technology Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170531 |