Direct appearance models

Active appearance model (AAM), which makes ingenious use of both shape and texture constraints, is a powerful tool for face modeling, alignment and facial feature extraction under shape deformations and texture variations. However, as we show through our analysis and experiments, there exist admissible appearances that are not modeled by AAM and hence cannot be reached by AAM search; also the mapping from the texture subspace to the shape subspace is many-to-one and therefore a shape should be determined entirely by the texture in it. We propose a new appearance model, called direct appearance model (DAM), without combining from shape and texture as in AAM. The DAM model uses texture information directly in the prediction of the shape and in the estimation of position and appearance (hence the name DAM). In addition, DAM predicts the new face position and appearance based on principal components of texture difference vectors, instead of the raw vectors themselves as in AAM. These lead to the following advantages over AAM: (1) DAM subspaces include admissible appearances previously unseen in AAM, (2) convergence and accuracy are improved, and (3) memory requirement is cut down to a large extent. The advantages are substantiated by comparative experimental results.

[1]  L Sirovich,et al.  Low-dimensional procedure for the characterization of human faces. , 1987, Journal of the Optical Society of America. A, Optics and image science.

[2]  Alex Pentland,et al.  Probabilistic Visual Learning for Object Representation , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Shaogang Gong,et al.  Dynamic Vision - From Images to Face Recognition , 2000 .

[4]  Timothy F. Cootes,et al.  Coupled-View Active Appearance Models , 2000, BMVC.

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

[6]  Timothy F. Cootes,et al.  Statistical models of appearance for computer vision , 1999 .

[7]  Timothy F. Cootes,et al.  Active Appearance Models , 1998, ECCV.

[8]  Shaogang Gong,et al.  View alignment with dynamically updated affine tracking , 1998, Proceedings Third IEEE International Conference on Automatic Face and Gesture Recognition.

[9]  Tomaso Poggio,et al.  Example Based Image Analysis and Synthesis , 1993 .

[10]  David Beymer,et al.  Vectorizing Face Images by Interleaving Shape and Texture Computations , 1995 .

[11]  Matthew Turk,et al.  A Morphable Model For The Synthesis Of 3D Faces , 1999, SIGGRAPH.

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

[13]  Timothy F. Cootes,et al.  Face Recognition Using Active Appearance Models , 1998, ECCV.

[14]  Shuicheng Yan,et al.  Multi-view face alignment using direct appearance models , 2002, Proceedings of Fifth IEEE International Conference on Automatic Face Gesture Recognition.