|
2D Face Alignment |
| Problem Definition: Given a set of face samples with labeled key feature points{(Ii,Si)} (e.g. eye and mouth corners, nose tips, face contour points), the task is to localize these points for a new face image I, i.e. S' = arg max P(S|I). |
|
T. Cootes did the pioneer work on ASM and AAM.
|
|
Related publications:
[1]S.C. Yan, M. J. Li, H.J. Zhang, Q. S. Cheng. Ranking Prior Likelihood Distributions for Bayesian Shape Localization Framework .IEEE Conferece. ICCV 2003. |
| [2]S.C. Yan, C, Liu, S. Z. Li, H.J. Zhang, H. Shum. Face alignment using texture-constrained active shape models . ECCV'02 Workshop on Generative-Model-Based Vision. (Accepted as a special issue paper of Image and Vision Computing. |
| [3]S.Z. Li, S.C. Yan, H.J. Zhang, Q. S. Cheng. Multi-View Face Alignment Using Direct Appearance Models. International Conf. on FG 2002. |
| กก |
| กก |
| กก |
|
Copyright (C) 2004,
Last upate June 09, 2004
|
