CN109766785A - A kind of biopsy method and device of face - Google Patents
A kind of biopsy method and device of face Download PDFInfo
- Publication number
- CN109766785A CN109766785A CN201811572285.0A CN201811572285A CN109766785A CN 109766785 A CN109766785 A CN 109766785A CN 201811572285 A CN201811572285 A CN 201811572285A CN 109766785 A CN109766785 A CN 109766785A
- Authority
- CN
- China
- Prior art keywords
- face
- detected
- different moments
- determined
- degree
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Abstract
The invention discloses a kind of biopsy method of face and devices.The described method includes: obtaining face to be detected in different moments corresponding feature vector and default key point in different moments corresponding location information, to according to different moments corresponding feature vector and different moments corresponding location information, it can determine the face change degree of face to be detected, and then after determining that face change degree is greater than preset threshold, it can determine that face to be detected passes through In vivo detection.In this way, can be by judging the default key point in face to be detected, with the presence or absence of the variation on position, can determine whether face to be detected is living body in different moments.In this way, due to criminal forge faceform be it is static, biopsy method provided in an embodiment of the present invention can effectively identify the faceform of forgery, to improve the safety of recognition of face, and then improve the reliability of face identification system.
Description
Technical field
The present invention relates to technical field of face recognition more particularly to the biopsy methods and device of a kind of face.
Background technique
Currently, biometrics identification technology is widely used in security fields, be authenticate user identity main means it
One.Biometrics identification technology, especially face recognition technology have been widely used in every field, such as financial payment neck
Domain, gate inhibition security fields etc..There is easy-to-use, user friendly, contactless etc. a little in view of face recognition technology, in recent years
To achieve the development advanced by leaps and bounds.
However, traditional face recognition technology is usually handled just for the image that video camera takes, it is not intended that
Whether taken image is true man, and the faceform so as to cause forgeries such as photo face, mask faces can pass through people
The detection of face identifying system is easy to cause the safety of recognition of face to be affected in turn.
Based on this, a kind of biopsy method of face is needed at present, for solving face recognition technology in the prior art
The faceform of forgery can not be identified, thus the problem of influencing the safety of recognition of face.
Summary of the invention
The embodiment of the present invention provides the biopsy method and device of a kind of face, to solve recognition of face in the prior art
Technology can not identify the faceform of forgery, thus the technical issues of influencing the safety of recognition of face.
The embodiment of the present invention provides a kind of biopsy method of face, which comprises
Face to be detected is obtained in different moments corresponding feature vector;
It obtains and presets key point in the face to be detected in the different moments corresponding location information, the position letter
Breath is position of the default key point in the face to be detected;The default key point is that can characterize the area of human face expression
Domain;
According to the different moments corresponding feature vector and the different moments corresponding location information, determine it is described to
Detect the face change degree of face;
If the face change degree of the face to be detected is greater than preset threshold, it is determined that the face to be detected passes through living body
Detection.
In this way, can be by judging the default key point in face to be detected in different moments with the presence or absence of the change on position
Change, can determine whether face to be detected is living body.In this way, since the faceform that criminal forges is static
, therefore, biopsy method provided in an embodiment of the present invention can effectively identify the faceform of forgery, to improve people
The safety of face identification, and then improve the reliability of face identification system.
In one possible implementation, according to the different moments corresponding feature vector and the different moments pair
The location information answered determines the face change degree of the face to be detected, comprising:
According to the different moments corresponding feature vector, characteristic similarity is determined;
According to the different moments corresponding location information, change in location degree is determined;
According to the characteristic similarity and the change in location degree, the face change degree of the face to be detected is determined.
In one possible implementation, face to be detected is obtained in different moments corresponding feature vector, comprising:
The segmentation area of the face to be detected is obtained in the different moments corresponding feature vector;Each segmentation
Region is determined according to the face position of face;
According to the different moments corresponding feature vector, characteristic similarity is determined, comprising:
According to each cut zone in the different moments corresponding feature vector, the feature phase of each cut zone is determined
Like degree;
According to the characteristic similarity and the change in location degree, the face change degree of the face to be detected is determined, wrap
It includes:
According to the characteristic similarity of each cut zone and the change in location degree, the face of the face to be detected is determined
Change degree.
By being split to face to be detected, the expression susceptibility of segmentation area can be comprehensively considered, to improve
The accuracy rate of In vivo detection.
In one possible implementation, according to the characteristic similarity of each cut zone and the change in location degree,
Determine the face change degree of the face to be detected, comprising:
For any default key point, cut zone belonging to the default key point is determined;
According to the characteristic similarity of affiliated cut zone and the change in location degree of the default key point, described point is determined
Cut the face change degree in region;
According to the face change degree of segmentation area, the face change degree of the face to be detected is determined.
In one possible implementation, the cut zone includes mouth region, nasal area, cheek region, eyebrow
Hair-fields domain, eye areas and forehead region.
In one possible implementation, it obtains in the face to be detected and presets key point in the different moments pair
The location information answered, comprising:
It is corresponding in the different moments that default key point in the face to be detected is obtained using flight time TOF technology
Location information;
Or
It is corresponding in the different moments that default key point in the face to be detected is obtained using 3D face reconstruction techniques
Location information.
The related data of face is obtained using TOF technology, can obtain user's face in the case where user's unaware
Related data, lower to the fitness requirement of user, the experience of user is more preferably.
In one possible implementation, after determining the face to be detected by In vivo detection, further includes:
According to the first eigenvector and the second feature vector, determine the corresponding feature of the face to be detected to
Amount;
According to the corresponding feature vector of the face to be detected and it is pre-stored at least one to have detected face corresponding
Feature vector, however, it is determined that it is described at least one detected in face that there are the similar faces of the face to be detected, it is determined that
The face to be detected passes through authentication.
The embodiment of the present invention provides a kind of living body detection device of face, and described device includes:
Acquiring unit, for obtaining face to be detected in different moments corresponding feature vector;And it obtains described to be checked
It surveys in face and presets key point in the different moments corresponding location information, the location information is that the default key point exists
Position in the face to be detected;The default key point is that can characterize the region of human face expression;
Processing unit, for being believed according to the different moments corresponding feature vector and the different moments corresponding position
Breath, determines the face change degree of the face to be detected;If the face change degree of the face to be detected is greater than preset threshold,
Determine that the face to be detected passes through In vivo detection.
In one possible implementation, the processing unit is specifically used for:
According to the different moments corresponding feature vector, characteristic similarity is determined;And it is corresponding according to the different moments
Location information, determine change in location degree;And it according to the characteristic similarity and the change in location degree, determines described to be checked
Survey the face change degree of face.
In one possible implementation, the acquiring unit is specifically used for:
The segmentation area of the face to be detected is obtained in the different moments corresponding feature vector;Each segmentation
Region is determined according to the face position of face;
The processing unit is specifically used for:
According to each cut zone in the different moments corresponding feature vector, the feature phase of each cut zone is determined
Like degree;
And characteristic similarity and the change in location degree according to each cut zone, determine the face to be detected
Face change degree.
In one possible implementation, the processing unit is specifically used for:
For any default key point, cut zone belonging to the default key point is determined;And according to affiliated segmentation
The change in location degree of the characteristic similarity in region and the default key point determines the face change degree of the cut zone;With
And the face change degree according to segmentation area, determine the face change degree of the face to be detected.
In one possible implementation, the cut zone includes mouth region, nasal area, cheek region, eyebrow
Hair-fields domain, eye areas and forehead region.
In one possible implementation, the acquiring unit is specifically used for:
It is corresponding in the different moments that default key point in the face to be detected is obtained using flight time TOF technology
Location information;
Or
It is corresponding in the different moments that default key point in the face to be detected is obtained using 3D face reconstruction techniques
Location information.
In one possible implementation, the processing unit determine the face to be detected by In vivo detection it
Afterwards, it is also used to:
According to the first eigenvector and the second feature vector, determine the corresponding feature of the face to be detected to
Amount;And according to the corresponding feature vector of the face to be detected and it is pre-stored at least one to have detected face corresponding
Feature vector, however, it is determined that it is described at least one detected in face that there are the similar faces of the face to be detected, it is determined that institute
It states face to be detected and passes through authentication.
The embodiment of the present application also provides a kind of device, which has the In vivo detection for realizing face as described above
The function of method.The function can execute corresponding software realization by hardware, in a kind of possible design, the device packet
It includes: processor, transceiver, memory;The memory is for storing computer executed instructions, and the transceiver is for realizing the device
It is communicated with other communication entities, which is connect with the memory by the bus, when the apparatus is operative, the processing
Device executes the computer executed instructions of memory storage, so that the device executes the In vivo detection of face as described above
Method.
The embodiment of the present invention also provides a kind of computer storage medium, stores software program in the storage medium, this is soft
Part program realizes people described in above-mentioned various possible implementations when being read and executed by one or more processors
The biopsy method of face.
The embodiment of the present invention also provides a kind of computer program product comprising instruction, when run on a computer,
So that computer executes the biopsy method of face described in above-mentioned various possible implementations.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly introduced.
Fig. 1 is flow diagram corresponding to a kind of biopsy method of face provided in an embodiment of the present invention;
Fig. 2 is a kind of schematic diagram of the cut zone of face provided in an embodiment of the present invention;
Fig. 3 a is a kind of schematic diagram of the corresponding default key point of eyes;
Fig. 3 b is a kind of schematic diagram of the corresponding default key point of mouth;
Fig. 4 is the schematic diagram of the belonging relation of default key point and cut zone;
Fig. 5 is the globality flow diagram of the In vivo detection of face involved in the embodiment of the present invention;
Fig. 6 is that use In vivo detection technology involved in the embodiment of the present invention carries out authentication process schematic diagram;
Fig. 7 is a kind of structural schematic diagram of the living body detection device of face provided in an embodiment of the present invention.
Specific embodiment
The application is specifically described with reference to the accompanying drawings of the specification, the concrete operation method in embodiment of the method can also
To be applied in Installation practice.
Fig. 1 illustrates process corresponding to a kind of biopsy method of face provided in an embodiment of the present invention and shows
It is intended to, as shown in Figure 1, including the following steps:
Step 101, face to be detected is obtained in different moments corresponding feature vector.
Step 102, it obtains and presets key point in face to be detected in different moments corresponding location information.
Step 103, it according to different moments corresponding feature vector and different moments corresponding location information, determines to be detected
The face change degree of face;
Step 104, if the face change degree of face to be detected is greater than preset threshold, it is determined that face to be detected passes through living body
Detection.
In this way, can be by judging the default key point in face to be detected in different moments with the presence or absence of the change on position
Change, can determine whether face to be detected is living body.In this way, since the faceform that criminal forges is static
, therefore, biopsy method provided in an embodiment of the present invention can effectively identify the faceform of forgery, to improve people
The safety of face identification, and then improve the reliability of face identification system.
Specifically, in step 101 and step 102, different moments can refer to two different moments, or be also possible to
At the time of referring to three differences, or it can also refer at the time of N number of difference (N be integer) greater than 1.For ease of description, with
Under be described by taking two different moments as an example, i.e., in a step 101, obtain face to be detected at the first moment and the second moment
Corresponding feature vector;In a step 102, it obtains and presets key point in face to be detected at the first moment and the second moment
Corresponding location information, wherein at the time of the first moment and the second moment are two differences.
Based on the above-mentioned explanation to different moments, in step 101, can by preset neural network model to it is any when
The corresponding feature of human face data for the face to be detected carved extracts, and obtains face to be certified according to the feature extracted and exist
The corresponding feature vector of any moment.
Further, preset neural network model can be a plurality of types of neural network models, for example, can be 2D
Deep neural network model, or it is also possible to 3D deep neural network model, specifically without limitation.
In view of the different zones of face to be detected are different the sensitivity of facial expression, such as eyes, mouth
The sensitivity in equal regions is relatively high, and the corresponding sensitivity in the regions such as cheek, forehead is relatively low, therefore, the present invention
Face to be detected can be divided into multiple cut zone by embodiment, to improve the accuracy rate of In vivo detection.Wherein, each segmentation
Region can be determining according to the face position of face.As shown in Fig. 2, for a kind of point of face provided in an embodiment of the present invention
Cut the schematic diagram in region.As shown in Fig. 2, face can be divided into multiple cut zone, such as cut zone can be mouth
Region, is perhaps also possible to nasal area and is perhaps also possible to cheek region to be perhaps also possible to brow region or can also
To be eye areas, or it is also possible to forehead region, specifically without limitation.
The signal of cut zone based on face shown in Fig. 2, in the embodiment of the present invention, also available face to be detected
Segmentation area corresponding feature vector at any one time.Specifically, can by preset neural network model to appoint
The corresponding feature of human face data of some cut zone of the face to be detected at one moment extracts, and according to the spy extracted
Sign obtains some cut zone of face to be certified corresponding feature vector at any one time.
In step 102, default key point can refer to the region that can characterize human face expression, for example, people is when laughing at, eye
Eyeball would generally be bent up, then, eyes can correspond to multiple default key points, be the corresponding default key of eyes as shown in Figure 3a
A kind of example of point, can be using canthus, eye tail, the central point in upper eyelid, the central point of palpebra inferior and eyeball center as eye
The corresponding default key point of eyeball;For another example, when crying, mouth would generally close lightly people, then, mouth can also correspond to multiple
Default key point is as shown in Figure 3b a kind of example of the corresponding default key point of mouth, can will be in the corners of the mouth, upper lip
Heart point, the central point of lower lip, front tooth are as the corresponding default key point of mouth.
In the embodiment of the present invention, the side that key point corresponding location information at any one time is preset in face to be detected is obtained
There are many formulas, a kind of possible implementation be can be obtained using flight time (Time Of Flight, TOF) technology to
It detects and presets key point corresponding location information at any one time in face.Specifically, TOF technology can be by connecting to target
Supervention send light pulse, and the light returned from object is then received with sensor, by detecting these transmittings and receiving flying for light pulse
Row (round-trip) time obtains object distance.In the embodiment of the present invention, can by TOF technical application to camera, thus
It obtains and presets key point corresponding location information (such as coordinate data) at any one time in face to be detected.Using TOF technology
The related data of face is obtained, the related data of user's face can be obtained in the case where user's unaware, user is matched
Right to require lower, the experience of user is more preferably.
During alternatively possible realization is sent, it can be obtained using face reconstruction techniques and preset key point in face to be detected
Corresponding location information at any one time.Specifically, for collected facial image (such as each frame in monitor video
Facial image), (Cascaded Regression, CR) method can be returned using based on cascade, generate one by multiple weak times
The strong recurrence for returning cascade to form, in conjunction with deep learning algorithm, realization is rebuild end to end, in this way, one facial image of input,
The 3D model of face can be directly exported, in turn, can be determined according to the 3D model of the face and preset key in face to be detected
Put corresponding location information (such as coordinate data) at any one time.
In other possible implementations, is also obtained using other methods and preset key point in face to be detected any
Moment corresponding location information, for example obtained in such a way that user to be certified is manually entered and preset key point in face to be detected
Corresponding location information at any one time, specifically without limitation.
It is also contemplated that difference of the different zones of face to be detected to the sensitivity of facial expression, Fig. 2 shows
On the basis of the segmentation area of face, in the embodiment of the present invention, default key point corresponding position at any one time is being got
After confidence breath, cut zone belonging to each default key point can be further determined that with the corresponding position of segmentation area.
For example, as shown in figure 4, the schematic diagram of the belonging relation for default key point and cut zone, it is assumed that face tool to be detected
There are 30 default key points that number is 1~30 shown in Fig. 4, also, face to be detected has before dotted line outlines in Fig. 4
Frontal region domain, brow region, eye areas, nasal area, mouth region and cheek region totally 6 cut zone, in conjunction with each default
The location information of key point and the position of segmentation area can determine cut zone belonging to each default key point.
In step 103, the face change degree of face to be detected can be according to different moments corresponding feature vector and difference
Moment presets the corresponding location information of key point to determine.There are many specific methods of determination, and a kind of possible implementation is,
According to face to be detected in different moments corresponding feature vector, characteristic similarity is determined, and pre- according to face to be detected
If key point determines change in location degree, and according to characteristic similarity and change in location in different moments corresponding location information
Degree, determines the face change degree of face to be detected.
That is, the face change degree of face to be detected can be determined according to formula (1):
Δ=λ1·S-λ2D formula (1)
In formula (1), Δ is the face change degree of face to be detected;S is characterized change degree;D change in location degree;λ1For spy
Levy the corresponding weight of change degree;λ2For the corresponding weight of change in location degree.
In view of in the embodiment of the present invention face to be detected can be obtained by the way of being split to face to be detected
Segmentation area in different moments corresponding feature vector.Based on this, if what is got is each cut section of face to be detected
It domain, then can be according to each cut zone in different moments corresponding feature vector, really in different moments corresponding feature vector
The characteristic similarity of fixed each cut zone;And it can be according to the change in location for the default key point for including in each cut zone
Degree, determines the change in location degree of each cut zone;In turn, can be become according to the characteristic similarity of each cut zone and position
Change degree determines the face change degree of each cut zone, and then determines the face change degree of face to be detected.
Further, the change in location degree of each cut zone can be determined according to formula (2):
In formula (2), DiFor the change in location degree of i-th of cut zone, 1≤i≤M, M are the segmentation in face to be detected
The quantity in region, M are the integer greater than 1;dijFor the Europe of j-th of default key point under different moments in i-th of cut zone
Formula distance, 1≤j≤n, n are the quantity of the default key point in i-th of cut zone, and n is the integer greater than 1.
It should be noted that formula (2) is only a kind of example, those skilled in the art can also be counted using other way
Calculate the change in location degree of each cut zone, for example calculate by the way of vector, specifically without limitation.
In turn, it according to the change in location degree of the changing features degree of each cut zone and each cut zone, can determine
The face change degree of each cut zone.The face change degree of each cut zone can be determined according to formula (3):
In formula (3), δiFor the face change degree of i-th of cut zone, 1≤i≤M, M are the segmentation in face to be detected
The quantity in region, M are the integer greater than 1;SiFor the changing features degree of i-th of cut zone;DiFor the position of i-th of cut zone
Set change degree;λ1It is characterized the corresponding weight of change degree;λ2For the corresponding weight of change in location degree.
In turn, the face change degree of face to be detected can be determined according to formula (4):
In formula (4), Δ is the face change degree of face to be detected;δiFor the face change degree of i-th of cut zone, 1
≤ i≤M, M are the quantity of the cut zone in face to be detected, and M is the integer greater than 1;ωiIt is corresponding for i-th of cut zone
Weight.
It should be noted that formula (4) is only a kind of example, those skilled in the art are obtaining the people of each cut zone
On the basis of face change degree, the face change degree of face to be detected can also be determined in other manners.For example, such as formula
(5) shown in, for the method for determination of the face change degree of another face to be detected.
In formula (5), Δ is the face change degree of face to be detected;If δi≤Thri, then (Thri-δi)+=1;Otherwise,
(Thri-δi)+=0.
It should be noted that being each segmentation according to different cut zone to the susceptibility of expression shape change in formula (5)
Region sets different threshold value (i.e. Thri), susceptibility is higher, and face variation is more significant, and similarity is smaller, therefore the threshold being arranged
It is worth smaller.In other words, if the similarity δ of a certain cut zonei≤Thri, then the expression for representing the cut zone becomes
Change;Otherwise, the expression for representing the cut zone does not change.
It, can also be by face to be detected in different moments corresponding feature vector and pre- in other possible implementations
If key point inputs trained similarity model in advance in different moments corresponding location information, so that it is determined that face to be detected
Face change degree, specifically without limitation.
In step 104, whether can be greater than preset threshold by judging the face change degree of face to be detected determine to
Whether detection face passes through In vivo detection, if more than can then determine that face to be detected passes through In vivo detection;It otherwise, can be true
Fixed face to be detected does not pass through In vivo detection.Wherein, preset threshold can be those skilled in the art rule of thumb with practical feelings
What condition determined, specifically without limitation.
For example, by taking the face change degree for the face to be detected being calculated using formula (4) as an example, if this is to be checked
The face change degree Δ for surveying face is greater than preset threshold, it is determined that face to be detected changes in different moments, it is believed that face
Expression shape change captures successfully, so that it is determined that personnel to be detected pass through In vivo detection;Otherwise, it determines face to be detected is in different moments
It does not change, it is believed that the failure of facial expression change capture, so that it is determined that personnel to be detected do not pass through In vivo detection.
By way of further example, by taking the face change degree for the face to be detected being calculated using formula (5) as an example, if Δ >=
M/2 is indicated in face to be detected in the quantity of different moments changed cut zone more than half, then it is assumed that facial table
Feelings change capture success, so that it is determined that personnel to be detected pass through In vivo detection;Otherwise, it indicates in face to be detected in different moments
The quantity of changed cut zone is less than half, then it is assumed that the failure of facial expression change capture, so that it is determined that be detected
Personnel do not pass through In vivo detection.
In order to more clearly introduce the biopsy method of above-mentioned face, below with reference to Fig. 5, to institute in the embodiment of the present invention
The In vivo detection process for the face being related to carries out globality explanation.The content shown in Fig. 5 can be specifically participated in, herein no longer in detail
It introduces.
In the embodiment of the present invention, after step 104 is performed, recognition of face can also be carried out, so that it is determined that people to be detected
Whether face passes through authentication.Specifically, the mode of recognition of face can be according to first eigenvector and second feature to
Amount, determines the corresponding feature vector of face to be detected;In turn, can according to the corresponding feature vector of face to be detected and in advance
At least one of storage has detected the corresponding feature vector of face, however, it is determined that at least one has been detected in face, and there are people to be detected
The similar face of face can then determine that face to be detected passes through authentication.
It may be that the mode of recognition of face is also possible to using existing based on depth nerve net in implementation other
Network model identifies face to be detected, specifically without limitation.
Below by taking In vivo detection technology carries out authentication as an example, in conjunction with Fig. 6, to involved in the embodiment of the present invention
Authentication process is carried out using In vivo detection technology and does globality explanation.The content shown in Fig. 6 can be specifically participated in, herein no longer
It is discussed in detail.
Based on same inventive concept, Fig. 7 illustrates a kind of living body inspection of face provided in an embodiment of the present invention
The structural schematic diagram for surveying device, as shown in fig. 7, the device includes acquiring unit 201 and processing unit 202;Wherein,
Acquiring unit 201, for obtaining face to be detected in different moments corresponding feature vector;And obtain it is described to
It detects and presets key point in face in the different moments corresponding location information, the location information is the default key point
Position in the face to be detected;The default key point is that can characterize the region of human face expression;
Processing unit 202, for according to the different moments corresponding feature vector and the different moments corresponding position
Confidence breath, determines the face change degree of the face to be detected;If the face change degree of the face to be detected is greater than default threshold
Value, it is determined that the face to be detected passes through In vivo detection.
In one possible implementation, the processing unit 202 is specifically used for:
According to the different moments corresponding feature vector, characteristic similarity is determined;And it is corresponding according to the different moments
Location information, determine change in location degree;And it according to the characteristic similarity and the change in location degree, determines described to be checked
Survey the face change degree of face.
In one possible implementation, the acquiring unit 201 is specifically used for:
The segmentation area of the face to be detected is obtained in the different moments corresponding feature vector;Each segmentation
Region is determined according to the face position of face;
The processing unit 202 is specifically used for:
According to each cut zone in the different moments corresponding feature vector, the feature phase of each cut zone is determined
Like degree;
And characteristic similarity and the change in location degree according to each cut zone, determine the face to be detected
Face change degree.
In one possible implementation, the processing unit 202 is specifically used for:
For any default key point, cut zone belonging to the default key point is determined;And according to affiliated segmentation
The change in location degree of the characteristic similarity in region and the default key point determines the face change degree of the cut zone;With
And the face change degree according to segmentation area, determine the face change degree of the face to be detected.
In one possible implementation, the cut zone includes mouth region, nasal area, cheek region, eyebrow
Hair-fields domain, eye areas and forehead region.
In one possible implementation, the acquiring unit 201 is specifically used for:
It is corresponding in the different moments that default key point in the face to be detected is obtained using flight time TOF technology
Location information;
Or
It is corresponding in the different moments that default key point in the face to be detected is obtained using 3D face reconstruction techniques
Location information.
In one possible implementation, the processing unit 202 determine the face to be detected pass through living body examine
After survey, it is also used to:
According to the first eigenvector and the second feature vector, determine the corresponding feature of the face to be detected to
Amount;And according to the corresponding feature vector of the face to be detected and it is pre-stored at least one to have detected face corresponding
Feature vector, however, it is determined that it is described at least one detected in face that there are the similar faces of the face to be detected, it is determined that institute
It states face to be detected and passes through authentication.
The embodiment of the present application also provides a kind of device, which has the In vivo detection for realizing face as described above
The function of method.The function can execute corresponding software realization by hardware, in a kind of possible design, the device packet
It includes: processor, transceiver, memory;The memory is for storing computer executed instructions, and the transceiver is for realizing the device
It is communicated with other communication entities, which is connect with the memory by the bus, when the apparatus is operative, the processing
Device executes the computer executed instructions of memory storage, so that the device executes the In vivo detection of face as described above
Method.
The embodiment of the present invention also provides a kind of computer storage medium, stores software program in the storage medium, this is soft
Part program realizes people described in above-mentioned various possible implementations when being read and executed by one or more processors
The biopsy method of face.
The embodiment of the present invention also provides a kind of computer program product comprising instruction, when run on a computer,
So that computer executes the biopsy method of face described in above-mentioned various possible implementations.
It should be understood by those skilled in the art that, the embodiment of the present invention can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the present invention
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the present invention, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Although preferred embodiments of the present invention have been described, it is created once a person skilled in the art knows basic
Property concept, then additional changes and modifications may be made to these embodiments.So it includes excellent that the following claims are intended to be interpreted as
It selects embodiment and falls into all change and modification of the scope of the invention.
Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art
Mind and range.In this way, if these modifications and changes of the present invention belongs to the range of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to include these modifications and variations.
Claims (16)
1. a kind of biopsy method of face, which is characterized in that the described method includes:
Face to be detected is obtained in different moments corresponding feature vector;
It obtains and presets key point in the face to be detected in the different moments corresponding location information, the location information is
Position of the default key point in the face to be detected;The default key point is that can characterize the region of human face expression;
According to the different moments corresponding feature vector and the different moments corresponding location information, determine described to be detected
The face change degree of face;
If the face change degree of the face to be detected is greater than preset threshold, it is determined that the face to be detected is examined by living body
It surveys.
2. the method according to claim 1, wherein according to the different moments corresponding feature vector and described
Different moments corresponding location information determines the face change degree of the face to be detected, comprising:
According to the different moments corresponding feature vector, characteristic similarity is determined;
According to the different moments corresponding location information, change in location degree is determined;
According to the characteristic similarity and the change in location degree, the face change degree of the face to be detected is determined.
3. the method according to claim 1, wherein obtain face to be detected different moments corresponding feature to
Amount, comprising:
The segmentation area of the face to be detected is obtained in the different moments corresponding feature vector;The segmentation area
It is to be determined according to the face position of face;
According to the different moments corresponding feature vector, characteristic similarity is determined, comprising:
According to each cut zone in the different moments corresponding feature vector, determine that the feature of each cut zone is similar
Degree;
According to the characteristic similarity and the change in location degree, the face change degree of the face to be detected is determined, comprising:
According to the characteristic similarity of each cut zone and the change in location degree, the face variation of the face to be detected is determined
Degree.
4. according to the method described in claim 3, it is characterized in that, according to the characteristic similarity of each cut zone and institute's rheme
Change degree is set, determines the face change degree of the face to be detected, comprising:
For any default key point, cut zone belonging to the default key point is determined;
According to the characteristic similarity of affiliated cut zone and the change in location degree of the default key point, the cut section is determined
The face change degree in domain;
According to the face change degree of segmentation area, the face change degree of the face to be detected is determined.
5. according to the method described in claim 3, it is characterized in that, the cut zone includes mouth region, nasal area, face
Buccal region domain, brow region, eye areas and forehead region.
6. presetting key point in the face to be detected described the method according to claim 1, wherein obtaining
Different moments corresponding location information, comprising:
It is obtained using flight time TOF technology and presets key point in the face to be detected in the different moments corresponding position
Information;
Or
It is obtained using 3D face reconstruction techniques and presets key point in the face to be detected in the different moments corresponding position
Information.
7. method according to any one of claim 1 to 6, which is characterized in that determining that the face to be detected passes through
After In vivo detection, further includes:
According to the first eigenvector and the second feature vector, the corresponding feature vector of the face to be detected is determined;
According to the corresponding feature vector of the face to be detected and it is pre-stored at least one detected the corresponding spy of face
Levy vector, however, it is determined that it is described at least one detected in face that there are the similar faces of the face to be detected, it is determined that it is described
Face to be detected passes through authentication.
8. a kind of living body detection device of face, which is characterized in that described device includes:
Acquiring unit, for obtaining face to be detected in different moments corresponding feature vector;And obtain the people to be detected
Key point is preset in face in the different moments corresponding location information, the location information is the default key point described
Position in face to be detected;The default key point is that can characterize the region of human face expression;
Processing unit is used for according to the different moments corresponding feature vector and the different moments corresponding location information,
Determine the face change degree of the face to be detected;If the face change degree of the face to be detected is greater than preset threshold, really
The fixed face to be detected passes through In vivo detection.
9. device according to claim 8, which is characterized in that the processing unit is specifically used for:
According to the different moments corresponding feature vector, characteristic similarity is determined;And according to the different moments corresponding position
Confidence breath, determines change in location degree;And according to the characteristic similarity and the change in location degree, determine the people to be detected
The face change degree of face.
10. device according to claim 8, which is characterized in that the acquiring unit is specifically used for:
The segmentation area of the face to be detected is obtained in the different moments corresponding feature vector;The segmentation area
It is to be determined according to the face position of face;
The processing unit is specifically used for:
According to each cut zone in the different moments corresponding feature vector, determine that the feature of each cut zone is similar
Degree;
And characteristic similarity and the change in location degree according to each cut zone, determine the face of the face to be detected
Change degree.
11. device according to claim 10, which is characterized in that the processing unit is specifically used for:
For any default key point, cut zone belonging to the default key point is determined;And according to affiliated cut zone
Characteristic similarity and the default key point change in location degree, determine the face change degree of the cut zone;And root
According to the face change degree of segmentation area, the face change degree of the face to be detected is determined.
12. device according to claim 10, which is characterized in that the cut zone include mouth region, nasal area,
Cheek region, brow region, eye areas and forehead region.
13. device according to claim 8, which is characterized in that the acquiring unit is specifically used for:
It is obtained using flight time TOF technology and presets key point in the face to be detected in the different moments corresponding position
Information;
Or
It is obtained using 3D face reconstruction techniques and presets key point in the face to be detected in the different moments corresponding position
Information.
14. the device according to any one of claim 8 to 13, which is characterized in that the processing unit is described in the determination
After face to be detected passes through In vivo detection, it is also used to:
According to the first eigenvector and the second feature vector, the corresponding feature vector of the face to be detected is determined;
And according to the corresponding feature vector of the face to be detected and it is pre-stored at least one detected the corresponding spy of face
Levy vector, however, it is determined that it is described at least one detected in face that there are the similar faces of the face to be detected, it is determined that it is described
Face to be detected passes through authentication.
15. a kind of computer readable storage medium, which is characterized in that the storage medium is stored with instruction, when described instruction exists
When being run on computer, so that computer realizes method described in any one of perform claim requirement 1 to 7.
16. a kind of computer equipment characterized by comprising
Memory, for storing program instruction;
Processor, for calling the program instruction stored in the memory, according to acquisition program execute as claim 1 to
Method described in any claim in 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811572285.0A CN109766785B (en) | 2018-12-21 | 2018-12-21 | Living body detection method and device for human face |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811572285.0A CN109766785B (en) | 2018-12-21 | 2018-12-21 | Living body detection method and device for human face |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109766785A true CN109766785A (en) | 2019-05-17 |
CN109766785B CN109766785B (en) | 2023-09-01 |
Family
ID=66450831
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811572285.0A Active CN109766785B (en) | 2018-12-21 | 2018-12-21 | Living body detection method and device for human face |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109766785B (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110458098A (en) * | 2019-08-12 | 2019-11-15 | 上海天诚比集科技有限公司 | A kind of face comparison method of facial angle measurement |
CN110728215A (en) * | 2019-09-26 | 2020-01-24 | 杭州艾芯智能科技有限公司 | Face living body detection method and device based on infrared image |
CN111274879A (en) * | 2020-01-10 | 2020-06-12 | 北京百度网讯科技有限公司 | Method and device for detecting reliability of in-vivo examination model |
CN111783644A (en) * | 2020-06-30 | 2020-10-16 | 百度在线网络技术(北京)有限公司 | Detection method, device, equipment and computer storage medium |
CN112132996A (en) * | 2019-06-05 | 2020-12-25 | Tcl集团股份有限公司 | Door lock control method, mobile terminal, door control terminal and storage medium |
CN112395902A (en) * | 2019-08-12 | 2021-02-23 | 北京旷视科技有限公司 | Face living body detection method, image classification method, device, equipment and medium |
CN112819986A (en) * | 2021-02-03 | 2021-05-18 | 广东共德信息科技有限公司 | Attendance system and method |
CN112927383A (en) * | 2021-02-03 | 2021-06-08 | 广东共德信息科技有限公司 | Cross-regional labor worker face recognition system and method based on building industry |
CN112927382A (en) * | 2021-02-03 | 2021-06-08 | 广东共德信息科技有限公司 | Face recognition attendance system and method based on GIS service |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104348778A (en) * | 2013-07-25 | 2015-02-11 | 信帧电子技术(北京)有限公司 | Remote identity authentication system, terminal and method carrying out initial face identification at handset terminal |
CN104361326A (en) * | 2014-11-18 | 2015-02-18 | 新开普电子股份有限公司 | Method for distinguishing living human face |
CN105389554A (en) * | 2015-11-06 | 2016-03-09 | 北京汉王智远科技有限公司 | Face-identification-based living body determination method and equipment |
CN105447432A (en) * | 2014-08-27 | 2016-03-30 | 北京千搜科技有限公司 | Face anti-fake method based on local motion pattern |
CN106850648A (en) * | 2015-02-13 | 2017-06-13 | 腾讯科技(深圳)有限公司 | Auth method, client and service platform |
CN107220590A (en) * | 2017-04-24 | 2017-09-29 | 广东数相智能科技有限公司 | A kind of anti-cheating network research method based on In vivo detection, apparatus and system |
CN107330914A (en) * | 2017-06-02 | 2017-11-07 | 广州视源电子科技股份有限公司 | Face position method for testing motion and device and vivo identification method and system |
CN107346422A (en) * | 2017-06-30 | 2017-11-14 | 成都大学 | A kind of living body faces recognition methods based on blink detection |
US20170345146A1 (en) * | 2016-05-30 | 2017-11-30 | Beijing Kuangshi Technology Co., Ltd. | Liveness detection method and liveness detection system |
CN107886070A (en) * | 2017-11-10 | 2018-04-06 | 北京小米移动软件有限公司 | Verification method, device and the equipment of facial image |
CN107992842A (en) * | 2017-12-13 | 2018-05-04 | 深圳云天励飞技术有限公司 | Biopsy method, computer installation and computer-readable recording medium |
CN108805047A (en) * | 2018-05-25 | 2018-11-13 | 北京旷视科技有限公司 | A kind of biopsy method, device, electronic equipment and computer-readable medium |
-
2018
- 2018-12-21 CN CN201811572285.0A patent/CN109766785B/en active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104348778A (en) * | 2013-07-25 | 2015-02-11 | 信帧电子技术(北京)有限公司 | Remote identity authentication system, terminal and method carrying out initial face identification at handset terminal |
CN105447432A (en) * | 2014-08-27 | 2016-03-30 | 北京千搜科技有限公司 | Face anti-fake method based on local motion pattern |
CN104361326A (en) * | 2014-11-18 | 2015-02-18 | 新开普电子股份有限公司 | Method for distinguishing living human face |
CN106850648A (en) * | 2015-02-13 | 2017-06-13 | 腾讯科技(深圳)有限公司 | Auth method, client and service platform |
CN105389554A (en) * | 2015-11-06 | 2016-03-09 | 北京汉王智远科技有限公司 | Face-identification-based living body determination method and equipment |
US20170345146A1 (en) * | 2016-05-30 | 2017-11-30 | Beijing Kuangshi Technology Co., Ltd. | Liveness detection method and liveness detection system |
CN107220590A (en) * | 2017-04-24 | 2017-09-29 | 广东数相智能科技有限公司 | A kind of anti-cheating network research method based on In vivo detection, apparatus and system |
CN107330914A (en) * | 2017-06-02 | 2017-11-07 | 广州视源电子科技股份有限公司 | Face position method for testing motion and device and vivo identification method and system |
CN107346422A (en) * | 2017-06-30 | 2017-11-14 | 成都大学 | A kind of living body faces recognition methods based on blink detection |
CN107886070A (en) * | 2017-11-10 | 2018-04-06 | 北京小米移动软件有限公司 | Verification method, device and the equipment of facial image |
CN107992842A (en) * | 2017-12-13 | 2018-05-04 | 深圳云天励飞技术有限公司 | Biopsy method, computer installation and computer-readable recording medium |
CN108805047A (en) * | 2018-05-25 | 2018-11-13 | 北京旷视科技有限公司 | A kind of biopsy method, device, electronic equipment and computer-readable medium |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112132996A (en) * | 2019-06-05 | 2020-12-25 | Tcl集团股份有限公司 | Door lock control method, mobile terminal, door control terminal and storage medium |
CN110458098A (en) * | 2019-08-12 | 2019-11-15 | 上海天诚比集科技有限公司 | A kind of face comparison method of facial angle measurement |
CN112395902A (en) * | 2019-08-12 | 2021-02-23 | 北京旷视科技有限公司 | Face living body detection method, image classification method, device, equipment and medium |
CN110728215A (en) * | 2019-09-26 | 2020-01-24 | 杭州艾芯智能科技有限公司 | Face living body detection method and device based on infrared image |
CN111274879A (en) * | 2020-01-10 | 2020-06-12 | 北京百度网讯科技有限公司 | Method and device for detecting reliability of in-vivo examination model |
CN111274879B (en) * | 2020-01-10 | 2023-04-25 | 北京百度网讯科技有限公司 | Method and device for detecting reliability of living body detection model |
CN111783644A (en) * | 2020-06-30 | 2020-10-16 | 百度在线网络技术(北京)有限公司 | Detection method, device, equipment and computer storage medium |
CN112819986A (en) * | 2021-02-03 | 2021-05-18 | 广东共德信息科技有限公司 | Attendance system and method |
CN112927383A (en) * | 2021-02-03 | 2021-06-08 | 广东共德信息科技有限公司 | Cross-regional labor worker face recognition system and method based on building industry |
CN112927382A (en) * | 2021-02-03 | 2021-06-08 | 广东共德信息科技有限公司 | Face recognition attendance system and method based on GIS service |
CN112927382B (en) * | 2021-02-03 | 2023-01-10 | 广东共德信息科技有限公司 | Face recognition attendance system and method based on GIS service |
Also Published As
Publication number | Publication date |
---|---|
CN109766785B (en) | 2023-09-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109766785A (en) | A kind of biopsy method and device of face | |
CN105518711B (en) | Biopsy method, In vivo detection system and computer program product | |
CN105612533B (en) | Living body detection method, living body detection system, and computer program product | |
CN108985134B (en) | Face living body detection and face brushing transaction method and system based on binocular camera | |
EP2546782B1 (en) | Liveness detection | |
CN108124486A (en) | Face living body detection method based on cloud, electronic device and program product | |
CN102945366B (en) | A kind of method and device of recognition of face | |
CN104966070B (en) | Biopsy method and device based on recognition of face | |
CN108140123A (en) | Face living body detection method, electronic device and computer program product | |
CN107590430A (en) | Biopsy method, device, equipment and storage medium | |
CN106570489A (en) | Living body determination method and apparatus, and identity authentication method and device | |
CN105518708A (en) | Method and equipment for verifying living human face, and computer program product | |
CN105160318A (en) | Facial expression based lie detection method and system | |
US11682236B2 (en) | Iris authentication device, iris authentication method and recording medium | |
US11756338B2 (en) | Authentication device, authentication method, and recording medium | |
CN106682473A (en) | Method and device for identifying identity information of users | |
US20230306792A1 (en) | Spoof Detection Based on Challenge Response Analysis | |
CN108932774A (en) | information detecting method and device | |
CN111178233A (en) | Identity authentication method and device based on living body authentication | |
US20220277311A1 (en) | A transaction processing system and a transaction method based on facial recognition | |
KR102530141B1 (en) | Method and apparatus for face authentication using face matching rate calculation based on artificial intelligence | |
US11961329B2 (en) | Iris authentication device, iris authentication method and recording medium | |
KR102616230B1 (en) | Method for determining user's concentration based on user's image and operating server performing the same | |
Lakshmi et al. | Efficient log-based iris detection and image sharpness enhancement (l-IDISE) using artificial neural network | |
Jagadeesh et al. | Software implementation procedure of the development of an iris-biometric identification system using image processing techniques |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |