Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001 (2001)
Dec. 8, 2001 to Dec. 14, 2001
XinWen Hou , Peking University
Stan Z. Li , Microsoft Research China
HongJiang Zhang , Microsoft Research China
QianSheng Cheng , Peking University
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 will 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.<div></div> In this paper, 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) DAMsubspaces includes admissible appearances previously unseen in AAM, (2) the convergence and accuracy are improved, and (3) the memory requirement is cut down to a large extent. The advantages are substantiated by comparative experimental results.
H. Zhang, X. Hou, Q. Cheng and S. Z. Li, "Direct Appearance Models," Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001(CVPR), Kauai, Hawaii, 2001, pp. 828.