Facial expression recognition(FER)has numerous applications in computer security,neuroscience,psychology,and engineering.Owing to its non-intrusiveness,it is considered a useful technology for combating crime.However,...Facial expression recognition(FER)has numerous applications in computer security,neuroscience,psychology,and engineering.Owing to its non-intrusiveness,it is considered a useful technology for combating crime.However,FER is plagued with several challenges,the most serious of which is its poor prediction accuracy in severe head poses.The aim of this study,therefore,is to improve the recognition accuracy in severe head poses by proposing a robust 3D head-tracking algorithm based on an ellipsoidal model,advanced ensemble of AdaBoost,and saturated vector machine(SVM).The FER features are tracked from one frame to the next using the ellipsoidal tracking model,and the visible expressive facial key points are extracted using Gabor filters.The ensemble algorithm(Ada-AdaSVM)is then used for feature selection and classification.The proposed technique is evaluated using the Bosphorus,BU-3DFE,MMI,CK^(+),and BP4D-Spontaneous facial expression databases.The overall performance is outstanding.展开更多
In this paper,a gas-kinetic unified algorithm(GKUA)is developed to investigate the non-equilibrium polyatomic gas flows covering various regimes.Based on the ellipsoidal statistical model with rotational energy excita...In this paper,a gas-kinetic unified algorithm(GKUA)is developed to investigate the non-equilibrium polyatomic gas flows covering various regimes.Based on the ellipsoidal statistical model with rotational energy excitation,the computable modelling equation is presented by unifying expressions on the molecular collision relaxing parameter and the local equilibrium distribution function.By constructing the corresponding conservative discrete velocity ordinate method for this model,the conservative properties during the collision procedure are preserved at the discrete level by the numerical method,decreasing the computational storage and time.Explicit and implicit lower-upper symmetric Gauss-Seidel schemes are constructed to solve the discrete hyperbolic conservation equations directly.Applying the new GKUA,some numerical examples are simulated,including the Sod Riemann problem,homogeneous flow rotational relaxation,normal shock structure,Fourier and Couette flows,supersonic flows past a circular cylinder,and hypersonic flow around a plate placed normally.The results obtained by the analytic,experimental,direct simulation Monte Carlo method,and other measurements in references are compared with the GKUA results,which are in good agreement,demonstrating the high accuracy of the present algorithm.Especially,some polyatomic gas non-equilibrium phenomena are observed and analysed by solving the Boltzmann-type velocity distribution function equation covering various flow regimes.展开更多
文摘Facial expression recognition(FER)has numerous applications in computer security,neuroscience,psychology,and engineering.Owing to its non-intrusiveness,it is considered a useful technology for combating crime.However,FER is plagued with several challenges,the most serious of which is its poor prediction accuracy in severe head poses.The aim of this study,therefore,is to improve the recognition accuracy in severe head poses by proposing a robust 3D head-tracking algorithm based on an ellipsoidal model,advanced ensemble of AdaBoost,and saturated vector machine(SVM).The FER features are tracked from one frame to the next using the ellipsoidal tracking model,and the visible expressive facial key points are extracted using Gabor filters.The ensemble algorithm(Ada-AdaSVM)is then used for feature selection and classification.The proposed technique is evaluated using the Bosphorus,BU-3DFE,MMI,CK^(+),and BP4D-Spontaneous facial expression databases.The overall performance is outstanding.
基金supported by the Project of manned space engineering technology(2018-14)“Large-scale parallel computation of aerodynamic problems of irregular spacecraft reentry covering various flow regimes”the National Natural Science Foundation of China(91530319).
文摘In this paper,a gas-kinetic unified algorithm(GKUA)is developed to investigate the non-equilibrium polyatomic gas flows covering various regimes.Based on the ellipsoidal statistical model with rotational energy excitation,the computable modelling equation is presented by unifying expressions on the molecular collision relaxing parameter and the local equilibrium distribution function.By constructing the corresponding conservative discrete velocity ordinate method for this model,the conservative properties during the collision procedure are preserved at the discrete level by the numerical method,decreasing the computational storage and time.Explicit and implicit lower-upper symmetric Gauss-Seidel schemes are constructed to solve the discrete hyperbolic conservation equations directly.Applying the new GKUA,some numerical examples are simulated,including the Sod Riemann problem,homogeneous flow rotational relaxation,normal shock structure,Fourier and Couette flows,supersonic flows past a circular cylinder,and hypersonic flow around a plate placed normally.The results obtained by the analytic,experimental,direct simulation Monte Carlo method,and other measurements in references are compared with the GKUA results,which are in good agreement,demonstrating the high accuracy of the present algorithm.Especially,some polyatomic gas non-equilibrium phenomena are observed and analysed by solving the Boltzmann-type velocity distribution function equation covering various flow regimes.
