Elsevier

Pattern Recognition

Volume 30, Issue 4, April 1997, Pages 627-641
Pattern Recognition

Deformable prototypes for encoding shape categories in image databases

https://doi.org/10.1016/S0031-3203(96)00108-2Get rights and content
Under a Creative Commons license
open archive

Abstract

An image database search method is described that uses strain energy from prototypes to represent shape categories. Rather than directly comparing a candidate shape with all entries in a database, shapes are ordered in terms of non-rigid deformations that relate them to a small subset of representative prototypes. Shape correspondences are obtained via modal matching, a decomposition for matching, describing, and comparing shapes despite sensor variations and non-rigid deformations. Deformation is decomposed into an ordered basis of orthogonal principal components. This allows selective invariance to in-plane rotation, translation, and scaling, and quasi-invariance to affine deformations. Retrieval accuracy and stability are evaluated in experiments with 2-D image databases.

Keywords

Object recognition
Energy-based shape models
Image database search
Deformable templates
Linear combinations
Shape categories
Modal matching

Cited by (0)