Learning Good Features for Active Shape Models

Teaser

People

Abstract

Active Shape Models (ASMs) are commonly used to model the appearance and shape variation of objects in images. This paper proposes two strategies to improve speed and accuracy in ASMs fitting. First, we define a new criterion to select landmarks that have good generalization properties. Second, for each landmark we learn a subspace with improved facial feature response effectively avoiding local minima in the ASM fitting. Experimental results show the effectiveness and robustness of the approach.

Citation

Paper thumbnail Nuria Brunet, Francisco Perez and Fernando de la Torre,
"Learning Good Features for Active Shape Models",
2nd IEEE International Workshop on Subspace Methods in conjunction with ICCV, Kyoto, Japan, 2009.
[PDF] [Bibtex]

Copyright notice

Human Sensing Lab