2007 IEEE International Conference on Image Processing - San Antonio, Texas, U.S.A. - September 16-19, 2007

Technical Program

Paper Detail

Paper:MA-P2.7
Session:Active-Contour, Level-Set, and Cluster-Based Segmentation Methods
Time:Monday, September 17, 09:50 - 12:30
Presentation: Poster
Title: LARGE SCALE LEARNING OF ACTIVE SHAPE MODELS
Authors: Atul Kanaujia; Rutgers University 
 Dimitris Metaxas; Rutgers University 
Abstract: We propose a framework to learn statistical shape models for faces as piecewise linear models. Specifically, our methodology builds upon primitive active shape models(ASM) to handle large scale variation in shapes and appearances of faces. Non-linearities in shape manifold arising due to large head rotation cannot be accurately modeled using ASM. Moreover overly general image descriptor causes the cost function to have multiple local minima which in turn degrades the quality of shape registration. We propose to use multiple overlapping subspaces with more discriminative local image descriptors to capture larger variance occurring in the data set. We also apply techniques to learn distance metric for enhancing similarity of descriptors belonging to the same class of shape subspace. Our generic algorithm can be applied to large scale shape analysis and registration.



©2016 Conference Management Services, Inc. -||- email: webmaster@icip2007.com -||- Last updated Friday, August 17, 2012