| | |
Summary: Groupwise Pose Normalization for Craniofacial Applications
Jiun-Hung Chen and Linda G. Shapiro
University of Washington
Seattle, WA 98195
{jhchen,shapiro}@cs.washington.edu
Abstract
A general framework is proposed for solving groupwise
pose normalization problems and is analyzed in detail un-
der different feature spaces. The analysis shows that using
principal component analysis for pose normalization is a
special case of using the proposed framework under a spe-
cial feature space. The experimental results on two cranio-
facial datasets show the proposed method achieved promis-
ing results for solving groupwise pose normalization prob-
lems for craniofacial applications.
1. Introduction
3D shape analysis is an important tool for both recog-
nition and retrieval of 3D shapes [19]. If two 3D shapes
are members of the same class of objects, their comparison
is simplified if they are both canonical views of their class.
|
