Driving facial animation based on tens of tracked markers is a challenging task due to the complex topology and to the non-rigid nature of human faces. We propose a solution named manifold Bayesian regression. First a...Driving facial animation based on tens of tracked markers is a challenging task due to the complex topology and to the non-rigid nature of human faces. We propose a solution named manifold Bayesian regression. First a novel distance metric, the geodesic manifold distance, is introduced to replace the Euclidean distance. The problem of facial animation can be formulated as a sparse warping kernels regression problem, in which the geodesic manifold distance is used for modelling the topology and discontinuities of the face models. The geodesic manifold distance can be adopted in traditional regression methods, e.g. radial basis functions without much tuning. We put facial animation into the framework of Bayesian regression. Bayesian approaches provide an elegant way of dealing with noise and uncertainty. After the covariance matrix is properly modulated, Hybrid Monte Carlo is used to approximate the integration of probabilities and get deformation results. The experimental results showed that our algorithm can robustly produce facial animation with large motions and complex face models.展开更多
This paper presents a novel face recognition algorithm. To provide additional variations to training data set, even-odd decomposition is adopted, and only the even components (half-even face images) are used for furth...This paper presents a novel face recognition algorithm. To provide additional variations to training data set, even-odd decomposition is adopted, and only the even components (half-even face images) are used for further processing. To tackle with shift-variant problem,Fourier transform is applied to half-even face images. To reduce the dimension of an image,PCA (Principle Component Analysis) features are extracted from the amplitude spectrum of half-even face images. Finally, nearest neighbor classifier is employed for the task of classification. Experimental results on ORL database show that the proposed method outperforms in terms of accuracy the conventional eigenface method which applies PCA on original images and the eigenface method which uses both the original images and their mirror images as training set.展开更多
基金Project supported by the National Natural Science Foundation of China (No. 60272031), the National Basic Research Program (973) of China (No. 2002CB312101) and the Technology Plan Program of Zhejiang Province (No. 2003C21010), China
文摘Driving facial animation based on tens of tracked markers is a challenging task due to the complex topology and to the non-rigid nature of human faces. We propose a solution named manifold Bayesian regression. First a novel distance metric, the geodesic manifold distance, is introduced to replace the Euclidean distance. The problem of facial animation can be formulated as a sparse warping kernels regression problem, in which the geodesic manifold distance is used for modelling the topology and discontinuities of the face models. The geodesic manifold distance can be adopted in traditional regression methods, e.g. radial basis functions without much tuning. We put facial animation into the framework of Bayesian regression. Bayesian approaches provide an elegant way of dealing with noise and uncertainty. After the covariance matrix is properly modulated, Hybrid Monte Carlo is used to approximate the integration of probabilities and get deformation results. The experimental results showed that our algorithm can robustly produce facial animation with large motions and complex face models.
文摘This paper presents a novel face recognition algorithm. To provide additional variations to training data set, even-odd decomposition is adopted, and only the even components (half-even face images) are used for further processing. To tackle with shift-variant problem,Fourier transform is applied to half-even face images. To reduce the dimension of an image,PCA (Principle Component Analysis) features are extracted from the amplitude spectrum of half-even face images. Finally, nearest neighbor classifier is employed for the task of classification. Experimental results on ORL database show that the proposed method outperforms in terms of accuracy the conventional eigenface method which applies PCA on original images and the eigenface method which uses both the original images and their mirror images as training set.
