DETERMINING THE SIMILARITY OF DEFORMABLE SHAPES

Determining the similarity of two shapes is a significant task in both machine and human vision systems that must recognize or classify obje cts. The exact properties of human shape similarity judgements are not well understood yet, and this task is particularly difficult in domai ns where the shapes are not related by rigid transformations. In this paper we identify a number of possibly desirable properties of a shape similarity method, and determine the extent to which these properties can be captured by approaches that compare local properties of the co ntours of the shapes, through elastic matching. Special attention is d evoted to objects that possess articulations, i.e. articulated parts. Elastic matching evaluates the similarity of two shapes as the sum of local deformations needed to change one shape into another. We show th at similarities of part structure can be captured by such an approach, without the explicit computation of part structure. This may be of im portance, since although parts appear to play a significant role in vi sual recognition, it is difficult to stably determine part structure. We also show novel results about how one can evaluate smooth and polyh edral shapes with the same method. Finally, we describe shape similari ty effects that cannot be handled by current approaches. (C) 1998 Else vier Science Ltd. All rights reserved.