This paper addresses the following problem: How can we make a complicated m
athematical shape model simpler while keeping a comparable level of represe
ntational power? The proposed solution is to use the original model itself
which represents a class of shapes - to train a Point Distribution Model (P
DM). In this paper the idea is applied to the case of deformable superellip
ses. (C) 1999 Elsevier Science B.V. All rights reserved.