Multiview Facial Feature Tracking with a Multi-modal Probabilistic Model

Dynamically tracking facial features with large variation of face pose has been shown as one of the most challenging issues in facial feature tracking. The traditional statistical models employ a principal component analysis (PCA) to characterize the statistics of a set of example shapes, however they are restricted to a narrow view due to the global linearity assumption. In this paper, a novel model-based multi-modal probabilistic approach is proposed to capture the complicated relationships among facial features under different face poses by using a mixture of local linear probabilistic PCAs. Based on the probabilistic evaluation of the component Probabilistic PCAs, the proposed method provides an effective way to choose the appropriate local PCA automatically and accurately when face poses are undergoing large variations. Experiment results demonstrate that the proposed method could track the facial features robustly with high accuracy under large variations of pose over time

[1]  A. F. Smith,et al.  Statistical analysis of finite mixture distributions , 1986 .

[2]  K. Walker,et al.  View-based active appearance models , 2000, Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580).

[3]  XÃ Ëíç,et al.  Face Alignment Using View-Based Direct Appearance Models , 2003 .

[4]  Thomas Vetter,et al.  A morphable model for the synthesis of 3D faces , 1999, SIGGRAPH.

[5]  Trevor Darrell,et al.  On modelling nonlinear shape-and-texture appearance manifolds , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[6]  Emanuele Trucco,et al.  Introductory techniques for 3-D computer vision , 1998 .

[7]  Shaogang Gong,et al.  A Multi-View Nonlinear Active Shape Model Using Kernel PCA , 1999, BMVC.

[8]  Norbert Krüger,et al.  Face Recognition by Elastic Bunch Graph Matching , 1997, CAIP.

[9]  Michael E. Tipping,et al.  Probabilistic Principal Component Analysis , 1999 .

[10]  Christopher M. Bishop,et al.  Mixtures of Probabilistic Principal Component Analyzers , 1999, Neural Computation.

[11]  Takeo Kanade,et al.  Real-time combined 2D+3D active appearance models , 2004, CVPR 2004.

[12]  Timothy F. Cootes,et al.  Active Appearance Models , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  Timothy F. Cootes,et al.  A mixture model for representing shape variation , 1999, Image Vis. Comput..

[14]  Shaogang Gong,et al.  Modelling faces dynamically across views and over time , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[15]  David J. Kriegman,et al.  Online learning of probabilistic appearance manifolds for video-based recognition and tracking , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[16]  Timothy F. Cootes,et al.  Active Shape Models-Their Training and Application , 1995, Comput. Vis. Image Underst..

[17]  David C. Hogg,et al.  Wormholes in shape space: tracking through discontinuous changes in shape , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[18]  Qiang Ji,et al.  Learning discriminant features for multi-view face and eye detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).