Seventh IEEE International Conference on Automatic Face and Gesture Recognition (FG'06)
Multi-template ASM Method for Feature Points Detection of Facial Image with Diverse Expressions
University of Southampton,UK
April 10-April 12
ISBN: 0-7695-2503-2
This paper proposed a multi-template ASM algorithm addressing facial feature points detection under nonlinear shape variation of facial images with various kinds of expression. By adding texture information, adopting asymmetric sampling strategy for the feature points on outer contour of face, building multiple templates and integrating local ASM and global ASM, experimental results show that the proposed multi-template ASM algorithm outperforms traditional single template ASM.
Citation:
Ying Li, J H Lai, Pong C Yuen, "Multi-template ASM Method for Feature Points Detection of Facial Image with Diverse Expressions," fg, pp.435-440, Seventh IEEE International Conference on Automatic Face and Gesture Recognition (FG'06), 2006