Face anti-counterfeiting detection method and system based on coordinated constraints of binocular spatiotemporal data

Abstract

The present invention discloses a face anti-counterfeiting detection method and system based on binocular spatiotemporal data collaborative constraints. The method includes the following steps: obtaining the original video stream data of the left and right cameras; performing stereo calibration on the left and right cameras to obtain the internal parameter matrix and the external parameter matrix; correcting the original video stream to obtain the image video stream of distortion-free front view; performing face detection on the image video stream using the RetinaFace network model to obtain a feature point set; reconstructing the face feature point cloud set using the binocular triangulation method, and constructing an evaluation function of spatial correlation constraints; constructing a constraint evaluation function under the time dimension based on the monocular projection error correlation function and the binocular projection correlation function under the time series; constructing a face anti-counterfeiting detection model with binocular spatiotemporal data collaborative constraints to achieve real-time judgment and recognition of face detection.

Description

Technical Field

[0001] The present invention relates to a face anti-counterfeiting detection method based on binocular spatiotemporal data collaborative constraint, and also relates to a corresponding face anti-counterfeiting detection system, belonging to the technical field of face recognition. Background Art

[0002] With the rapid development of information technology, traditional identity authentication methods based on passwords or certificates can no longer meet the security and convenience requirements of actual applications. Biometric identification methods have been increasingly widely used due to their good adaptability and security. Compared with other biometric technologies, such as fingerprints or irises, face recognition, as a convenient, friendly and low-cost biometric identification technology, has been widely used in many fields such as security, finance and transportation.

[0003] In the prior art, the accuracy of face anti-counterfeiting detection and adaptability to the detection environment are two important performance indicators of non-cooperative face recognition systems. Usually, the face recognition system detects face video streams acquired in an open environment, and the face targets to be identified often have problems such as large angle changes, occlusions, and uneven lighting, which will greatly affect the accuracy and effect of face detection. At the same time, the face recognition system also needs to accurately identify fake face attacks, such as video attacks, photo attacks, etc. Therefore, how to improve the accuracy of face detection and adaptability to the detection environment to meet the needs of practical applications has always been a very important technical research topic in this field.

[0004] In the Chinese invention patent with patent number ZL 202010748989.X, a face detection and recognition method based on binocular vision is disclosed. The method includes the following steps: (1) obtaining two left and right face images through a binocular camera; (2) detecting the two images through the hog feature, and finding the corresponding two face images from the two images; (3) extracting face features from the two acquired pictures containing faces; (4) obtaining the depth information of face feature points through the binocular vision ranging method, thereby solving the three-dimensional face model; (5) using the statistical method to classify the three-dimensional face model through the support vector machine of the solved result, thereby realizing face recognition. Summary of the invention

[0005] The primary technical problem to be solved by the present invention is to provide a face anti-counterfeiting detection method based on the collaborative constraint of binocular spatiotemporal data.

[0006] Another technical problem to be solved by the present invention is to provide a face anti-counterfeiting detection system based on binocular spatiotemporal data collaborative constraints.

[0007] In order to achieve the above object, the present invention adopts the following technical solutions:

[0008] According to a first aspect of an embodiment of the present invention, a face anti-counterfeiting detection method based on binocular spatiotemporal data collaborative constraint is provided, comprising the following steps:

[0009] (1) Obtain the original video stream data of the left and right cameras in the application scenario;

[0010] (2) Perform stereo calibration on the left and right cameras to obtain the intrinsic parameter matrices of the left and right cameras and the extrinsic parameter matrix between the two cameras;

[0011] (3) performing distortion correction and stereo correction on the original video streams of the left and right cameras according to the intrinsic parameter matrix and the extrinsic parameter matrix to obtain a distortion-free front-view image video stream;

[0012] (4) performing face detection on the image video streams of the left and right cameras using the RetinaFace network model, and inferring feature point sets for face detection of the left and right cameras respectively;

[0013] (5) Based on the feature point sets of the left and right cameras and the correspondence between the feature points with the same name on the left and right cameras, as well as the intrinsic parameter matrices and the extrinsic parameter matrices of the left and right cameras, a binocular triangulation method is used to reconstruct a face feature point cloud set;

[0014] (6) Based on the face feature point cloud set, a face spatial topological structure information representation vector is established, the spatial topological similarity is obtained by calculation, and an evaluation function of the spatial association constraint is constructed;

[0015] (7) Using the grayscale consistency assumption of the key features corresponding to consecutive facial image frames, a tracking mathematical model based on the temporal correlation of facial features is constructed. The homography transformation matrix between adjacent facial image frames is obtained by calculation, and the monocular projection error correlation function under the facial feature time series is constructed.

[0016] (8) Based on the intrinsic parameter matrix and the extrinsic parameter matrix of the left and right cameras, the basic matrix between the left and right cameras is constructed by initializing the optical flow of the binocular face recognition system to obtain the corresponding binocular projection correlation function;

[0017] (9) constructing a constraint evaluation function in the time dimension based on the monocular projection error correlation function and the binocular projection correlation function in the face feature time series;

[0018] (10) Based on the constraint evaluation function under the time dimension and the evaluation function of the spatial correlation constraint and their mutual matching relationship, a face anti-counterfeiting detection model with coordinated constraints of binocular spatiotemporal data is constructed to achieve real-time judgment and recognition of face detection.

[0019] Preferably, in step (4), the feature points used for face detection include the left eye, the right eye, the tip of the nose, the left corner of the mouth and the right corner of the mouth.

[0020] Preferably, in step (5), the face feature point cloud set P 3d Satisfies the following formula:

[0021] P 3d =f(A1,A2,R,T,M1,M2)

[0022] Among them, A1 and A2 are the intrinsic parameter matrices of the left camera and the right camera respectively; R is the extrinsic parameter rotation matrix, T is the extrinsic parameter translation matrix; M1 and M2 are the feature point sets of the left camera and the right camera respectively.

[0023] Preferably, in step (6), the spatial topological similarity S satisfies the following formula:

[0024] S=cos <N1,N s >

[0025] Among them, N1 is the representation vector of the face space topological structure information, N s is the spatial topological structure information representation vector of a standard face, <N1,N s > represents the angle between two vectors.

[0026] Preferably, in step (7), the tracking mathematical model based on the time correlation of facial features satisfies the following formula:

[0027] I(x,y,t)=I(x+Δx,y+Δy,t+Δt)

[0028] Among them, I(x,y,t) represents the grayscale value of the facial feature coordinate point (x,y) at the t-th time; I(x+Δx,y+Δy,t+Δt) represents the grayscale value of the facial feature coordinate point (x+Δx,y+Δy) at the (t+Δt)-th time; Δt represents the interval time between image frames, and Δx and Δy represent the changes in the coordinates respectively.

[0029] The homography transformation matrix H between adjacent face image frames t Satisfies the following formula:

[0030] X t+1 =H t X t

[0031] Among them, X t and X t+1 are the sets of facial feature points at time t and time (t+1), respectively. Time t and time (t+1) are the times of adjacent facial image frames, and the interval between them is Δt.

[0032] Preferably, in step (8), the basic matrix F t Satisfies the following formula:

[0033] I L (x,y)=F t *I R (x,y)

[0034] Among them, I L (x, y) is the optical flow feature point of the left camera face, I R (x,y) is the optical flow feature point of the face of the right camera.

[0035] Preferably, in step (9), the constraint evaluation function T(t) in the time dimension satisfies the following formula:

[0036] T(t)=h(H t )+μ(F t )

[0037] Among them, h(H t ) is the monocular projection error correlation function; μ(F t ) is the binocular projection correlation function.

[0038] Preferably, in step (10), the output value F of the face anti-counterfeiting detection model with binocular spatiotemporal data collaborative constraints satisfies the following formula:

[0039]

[0040] Among them, F is the output value of the detection model; T(t) is the constraint evaluation function in the time dimension; g(P 3d ,S) is the evaluation function of the spatial association constraint of facial features; α and β are the association parameters of the time series and space series respectively; min is the objective function; ‖·‖ is the modulo operation.

[0041] According to a second aspect of an embodiment of the present invention, there is provided a face anti-counterfeiting detection system based on binocular spatiotemporal data collaborative constraint, comprising a processor and a memory, wherein the processor and the memory are coupled; wherein:

[0042] The memory is used to store computer programs;

[0043] The processor is used to run the computer program stored in the memory to execute the above-mentioned face anti-counterfeiting detection method based on binocular spatiotemporal data collaborative constraints.

[0044] Compared with the prior art, the face anti-counterfeiting detection method based on binocular spatiotemporal data collaborative constraints provided by the present invention obtains the key features of the face on the image video stream of the binocular vision system and aligns the spatiotemporal features, adopts the spatial constraints between binocular multi-frame face feature images to prevent planar prosthesis attacks, and simultaneously adopts the optical flow constraints between continuous image frames in a time series to identify whether the prosthetic face has tiny dynamic features, constructs a face anti-counterfeiting detection model with binocular spatiotemporal data collaborative constraints, realizes real-time and accurate judgment and anti-counterfeiting recognition of face detection, and improves the detection accuracy and environmental adaptability of the binocular living face detection system. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 A flowchart of a face anti-counterfeiting detection method based on binocular spatiotemporal data collaborative constraint provided by an embodiment of the present invention;

[0046] Figure 2 A structural schematic diagram of a face anti-counterfeiting detection system based on binocular spatiotemporal data collaborative constraints provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0047] The technical content of the present invention is described in detail below with reference to the accompanying drawings and specific embodiments.

[0048] like Figure 1 As shown, an embodiment of the present invention provides a face anti-counterfeiting detection method based on binocular spatiotemporal data collaborative constraint, which at least includes the following steps:

[0049] S1: Obtain the original video stream data of the left and right cameras in the application scene.

[0050] Among them, the binocular cameras used in binocular stereo vision scenes are the left camera and the right camera. In actual applications, the two cameras simultaneously collect facial data information to form an original video stream.

[0051] S2: Perform stereo calibration on the left and right cameras to obtain the intrinsic parameter matrix A1 of the left camera, the intrinsic parameter matrix A2 of the right camera, and the extrinsic parameter matrix [R, T] between the two cameras, where R is the rotation matrix and T is the translation matrix.

[0052] S3: According to the intrinsic parameter matrix and the extrinsic parameter matrix, the original video streams of the left and right cameras are subjected to distortion correction and stereo correction to obtain a distortion-free orthographic image video stream.

[0053] The above steps S1-S3 are data acquisition and data processing for the original video stream of the binocular camera. The present invention will extract and characterize the spatial feature information of face recognition.

[0054] S4: Use the RetinaFace network model to perform face detection on the image video streams of the left and right cameras, and infer the feature point set M1 used for face detection by the left camera and the feature point set M2 used for face detection by the right camera.

[0055] In one embodiment of the present invention, key feature points used for face detection may include a left eye, a right eye, a nose tip, a left corner of the mouth, and a right corner of the mouth.

[0056] S5: Based on the feature point sets of the left and right cameras, the correspondence between the feature points of the same name on the left and right, and the intrinsic parameter matrices and extrinsic parameter matrices of the left and right cameras, the face feature point cloud set p is reconstructed using the binocular triangulation method. 3d .

[0057] Face feature point cloud set P 3d The expression is as follows:

[0058] P 3d =f(A1,A2,R,T,M1,M2) (1)

[0059] Among them, A1 and A2 are the intrinsic parameter matrices of the left camera and the right camera respectively; R is the extrinsic rotation matrix, T is the extrinsic translation matrix; M1 and M2 are the feature point sets of the left camera and the right camera respectively.

[0060] S6: Based on the face feature point cloud set P 3d , establish the face space topological structure information representation vector N1, obtain the spatial topological similarity S by calculation, and construct the evaluation function g(P 3d ,S).

[0061] The face spatial topological structure information representation vector N1 and the standard face spatial topological structure information representation vector N s The cosine value of the angle is calculated to obtain the spatial topological similarity S.

[0062] The calculation of spatial topological similarity S is as follows:

[0063] S=cos <N1,N s > (2)

[0064] By comparing the calculated spatial topological similarity S with the set similarity threshold, false face attacks such as videos or images can be identified.

[0065] Furthermore, based on the face feature point cloud set P 3d The evaluation function g(P 3d ,S), is used to prevent planar face prosthesis attacks.

[0066] The above steps S4-S6 are for extracting and characterizing the spatial feature information of face recognition. On the basis of the above face spatial recognition, in order to improve the recognition of attacks by objects such as fake head models, the present invention will perform real-time extraction and rapid tracking of key face features in a two-dimensional video stream time series to achieve face recognition and judgment in a time series.

[0067] S7: Using the gray consistency assumption of the key features corresponding to consecutive face image frames, a tracking mathematical model based on the temporal correlation of face features is constructed, and the homography transformation matrix H between adjacent face image frames is obtained by calculation. t , and construct the monocular projection error correlation function h(H t ).

[0068] The mathematical model for tracking based on the temporal correlation of facial features is as follows:

[0069] I(x,y,t)=I(x+Δx,y+Δy,t+Δt) (3)

[0070] Among them, I(x,y,t) represents the grayscale value of the facial feature coordinate point (x,y) at the t-th time; I(x+Δx,y+Δy,t+Δt) represents the grayscale value of the facial feature coordinate point (x+Δx,y+Δy) at the (t+Δt)-th time; Δt represents the interval time between image frames, and Δx and Δy represent the changes in the coordinates respectively.

[0071] Expand the term I(x+Δx,y+Δy,t+Δt) in formula (3) according to the first-order Taylor series to obtain the following expression:

[0072]

[0073] in, is the moving direction vector of the facial feature point at time t. By selecting the (2w+1)×(2w+1) neighborhood window around the feature point I(x,y), the moving direction vector of the facial feature point I(x,y) at time t can be obtained. Among them, (2w+1) is the neighborhood width, and w is a positive integer, which is a parameter representing the neighborhood width.

[0074] Based on the motion direction vector of the facial feature points and the interval time Δt between image frames, the facial feature coordinate points (x+Δx, y+Δy) corresponding to adjacent frames are obtained.

[0075] Then construct the facial feature point set X at time t and time (t+1) respectively t and X t+1 , solve and obtain the homography transformation matrix H between adjacent face image frames t :

[0076] X t+1 =H t X t (5)

[0077] Among them, time t and time (t+1) are the times of adjacent face image frames, and the interval time between them is Δt.

[0078] Through the above calculation, we can get the monocular projection error correlation function h(H) under the time series of facial features. t ).

[0079] S8: Based on the intrinsic parameter matrices A1 and A2 of the left and right cameras and the extrinsic parameter matrix [R, T], the basic matrix F between the left and right cameras is constructed through the optical flow initialization of the binocular face recognition system t , and obtain the corresponding binocular projection correlation function μ(F t ).

[0080] Fundamental matrix F t The expression is as follows:

[0081] I L (x,y)=F t *I R (x,y) (6)

[0082] Among them, I L (x, y) is the optical flow feature point of the left camera face, I R (x,y) is the optical flow feature point of the face of the right camera.

[0083] By matching the key features of the binocular face image, the basic matrix F in the time series can be calculated in real time. t . Based on the basic matrix F under time series t , and the assumption that real faces have small fluctuations in a certain time dimension, the basic matrix F under the time series t Statistical analysis is performed to obtain the corresponding binocular projection correlation function μ(F t ). Specifically, the singular value decomposition method is used to obtain the eigenvector corresponding to the basic matrix. By counting the variance value of the eigenvector modulus change within a certain time range, it is judged whether it is a real face. If the modulus change is less than the set variance threshold, it is considered that the face model has not changed and is a fake face, otherwise it is a real face.

[0084] S9: Monocular projection error correlation function h(H) based on face feature time series t ) and binocular projection correlation function μ(F t ), construct the constraint evaluation function T(t) in the time dimension.

[0085] The expression of the constraint evaluation function T(t) in the time dimension is:

[0086] T(t)=h(H t )+μ(F t ) (7)

[0087] Among them, h(H t ) is the monocular projection error correlation function; μ(F t ) is the binocular projection correlation function.

[0088] S10: Based on the constraint evaluation function T(t) in the time dimension and the evaluation function g(P 3d ,S) and their mutual matching relationship, a face anti-counterfeiting detection model with collaborative constraints of binocular spatiotemporal data is constructed to realize real-time judgment and recognition of face detection.

[0089] The output expression of the detection model is:

[0090]

[0091] Among them, F is the output value of the detection model; T(t) is the constraint evaluation function in the time dimension; g(P 3d ,S) is the evaluation function of the spatial association constraint of facial features; α and β are the association parameters of the time series and space series respectively; min is the objective function; ‖·‖ is the modulo operation.

[0092] Formula (7) is used to solve the global optimal value of the associated parameters α and β in a certain time-space sequence, and then the output value F of the corresponding anti-counterfeiting detection model is obtained. The output value of the model is compared with the set threshold to achieve the final judgment of face recognition and its corresponding liveness detection.

[0093] The above is a detailed description of a face anti-counterfeiting detection method based on binocular spatiotemporal data collaborative constraints provided by the present invention. The method realizes face anti-counterfeiting detection based on binocular spatiotemporal data collaborative constraints by performing feature extraction and tracking detection of face spatial sequences and time series on the image video streams of the left and right cameras in real time.

[0094] Based on the face anti-counterfeiting detection method, the embodiment of the present invention further provides a face anti-counterfeiting detection system based on binocular spatiotemporal data collaborative constraints, such as Figure 2 As shown, the detection system includes one or more processors and a memory. The memory is coupled to the processor and is used to store one or more computer programs. When the one or more computer programs are executed by the one or more processors, the one or more processors implement the face anti-counterfeiting detection method based on binocular spatiotemporal data collaborative constraint as in the above embodiment.

[0095] Among them, the processor is used to control the overall operation of the face anti-counterfeiting detection system based on binocular spatiotemporal data collaborative constraints to complete all or part of the steps of the face anti-counterfeiting detection method based on binocular spatiotemporal data collaborative constraints. The processor module can be a central processing unit (CPU), a graphics processing unit (GPU), a field programmable gate array (FPGA), an application-specific integrated circuit (ASIC), a digital signal processing (DSP) chip, etc. The memory is used to store various types of data to support operations on the face anti-counterfeiting detection system based on binocular spatiotemporal data collaborative constraints. These data may, for example, include instructions for any application or method for operating the face anti-counterfeiting detection system based on binocular spatiotemporal data collaborative constraints, and application-related data. The memory module can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic memory, a flash memory, etc.

[0096] The face anti-counterfeiting detection system based on the collaborative constraint of binocular spatiotemporal data realizes the face anti-counterfeiting detection based on the collaborative constraint of binocular spatiotemporal data by extracting and tracking the features of the face space sequence and time series of the image video streams of the left and right cameras in real time. It can solve the security risks such as the false recognition process that is vulnerable to attacks by face prostheses such as photos and videos.

[0097] To sum up, compared with the prior art, the face anti-counterfeiting detection method based on binocular spatiotemporal data collaborative constraints provided by the present invention obtains the key features of the face on the image video stream of the binocular vision system and aligns the spatiotemporal features, adopts the spatial constraints between binocular multi-frame face feature images to prevent planar prosthesis attacks, and at the same time adopts the optical flow constraints between continuous image frames in a time series to identify whether the prosthetic face has tiny dynamic features, constructs a face anti-counterfeiting detection model with binocular spatiotemporal data collaborative constraints, realizes real-time and accurate judgment and anti-counterfeiting identification of face detection, and improves the detection accuracy and environmental adaptability of the binocular living face detection system.

[0098] The above is a detailed description of the face anti-counterfeiting detection method and system based on binocular spatiotemporal data collaborative constraint provided by the present invention. For those skilled in the art, any obvious changes made to it without departing from the essence of the present invention will constitute an infringement of the patent right of the present invention and will bear corresponding legal responsibilities.

Claims

1. A face anti-counterfeiting detection method based on binocular spatiotemporal data collaborative constraints, characterized in that The steps include: (1) Obtain the original video stream data of the left and right cameras in the application scene; (2) Perform stereo calibration on the left and right cameras to obtain the intrinsic parameter matrices of the left and right cameras and the extrinsic parameter matrix between the two cameras; (3) performing distortion correction and stereo correction on the original video streams of the left and right cameras according to the intrinsic parameter matrix and the extrinsic parameter matrix to obtain a distortion-free front-view image video stream; (4) performing face detection on the image video streams of the left and right cameras using the RetinaFace network model, and inferring feature point sets for face detection of the left and right cameras respectively; (5) Based on the feature point sets of the left and right cameras and the correspondence between the feature points with the same name on the left and right cameras, as well as the intrinsic parameter matrices and the extrinsic parameter matrices of the left and right cameras, a binocular triangulation method is used to reconstruct a face feature point cloud set; (6) Based on the face feature point cloud set, a face spatial topological structure information representation vector is established, the spatial topological similarity is obtained by calculation, and an evaluation function of the spatial association constraint is constructed; (7) Using the grayscale consistency assumption of the key features corresponding to consecutive facial image frames, a tracking mathematical model based on the temporal correlation of facial features is constructed. The homography transformation matrix between adjacent facial image frames is obtained by calculation, and the monocular projection error correlation function under the facial feature time series is constructed. (8) Based on the intrinsic parameter matrix and the extrinsic parameter matrix of the left and right cameras, the basic matrix between the left and right cameras is constructed by initializing the optical flow of the binocular face recognition system to obtain the corresponding binocular projection correlation function; (9) constructing a constraint evaluation function in the time dimension based on the monocular projection error correlation function and the binocular projection correlation function in the face feature time series; (10) Based on the constraint evaluation function under the time dimension and the evaluation function of the spatial correlation constraint and their mutual matching relationship, a face anti-counterfeiting detection model with coordinated constraints of binocular spatiotemporal data is constructed to achieve real-time judgment and recognition of face detection.

2. The face anti-counterfeiting detection method based on binocular spatiotemporal data collaborative constraint as claimed in claim 1, characterized in that In step (4), the feature points used for face detection include the left eye, the right eye, the tip of the nose, the left corner of the mouth and the right corner of the mouth.

3. The face anti-counterfeiting detection method based on binocular spatiotemporal data collaborative constraint as claimed in claim 1, characterized in that In step (6), the spatial topological similarity S satisfies the following formula: S=cos<N1,N s > Among them, N1 is the representation vector of the face space topological structure information, N s is the spatial topological structure information representation vector of a standard face, <N1,N s > represents the angle between two vectors, and cos is the cosine function.

4. The face anti-counterfeiting detection method based on binocular spatiotemporal data collaborative constraint as claimed in claim 1, characterized in that In step (7), the tracking mathematical model based on the time correlation of facial features satisfies the following formula: I(x,y,t)=I(x+Δx,y+Δy,t+Δt) Among them, I(x,y,t) represents the grayscale value of the facial feature coordinate point (x,y) at the t-th time; I(x+Δx,y+Δy,t+Δt) represents the grayscale value of the facial feature coordinate point (x+Δx,y+Δy) at the (t+Δt)-th time; Δt represents the interval time between image frames, and Δx and Δy represent the changes in the coordinates respectively.

5. The face anti-counterfeiting detection method based on binocular spatiotemporal data collaborative constraint as claimed in claim 1, characterized in that The homography transformation matrix H between adjacent face image frames t Satisfies the following formula: X t+1 =H t X t Among them, X t and X t+1 are the sets of facial feature points at time t and time (t+1), respectively. Time t and time (t+1) are the times of adjacent facial image frames, and the interval between them is Δt.

6. The face anti-counterfeiting detection method based on binocular spatiotemporal data collaborative constraint as claimed in claim 1, characterized in that In step (8), the basic matrix F t Satisfies the following formula: I L (x,y)=F t *I R (x,y) Among them, I L (x, y) is the optical flow feature point of the left camera face, I R (x,y) is the optical flow feature point of the face of the right camera.

7. The face anti-counterfeiting detection method based on binocular spatiotemporal data collaborative constraint as claimed in claim 1, characterized in that In step (9), the constraint evaluation function T(t) in the time dimension satisfies the following formula: T(t)=h(H t )+μ(F t ) Among them, h(H t ) is the monocular projection error correlation function; μ(F t ) is the binocular projection correlation function, H t is the homography transformation matrix between adjacent face image frames; F t is the basic matrix between the left and right cameras.

8. The face anti-counterfeiting detection method based on binocular spatiotemporal data collaborative constraint as claimed in claim 1, characterized in that In step (10), the output value F of the face anti-counterfeiting detection model with binocular spatiotemporal data collaborative constraints satisfies the following formula: Among them, F is the output value of the detection model; T(t) is the constraint evaluation function in the time dimension; g(P 3d ,S) is the evaluation function of the spatial association constraint of facial features; α and β are the association parameters of the time series and space series respectively; min is the objective function; ||·|| is the modulo operation.

9. A face anti-counterfeiting detection system based on binocular spatiotemporal data collaborative constraints, characterized by It includes a processor and a memory, wherein the processor and the memory are coupled; wherein, The memory is used to store computer programs; The processor is used to run the computer program stored in the memory to execute the face anti-counterfeiting detection method based on binocular spatiotemporal data collaborative constraints as described in any one of claims 1 to 8.

Images