Title

Shape matching and modeling using skeletal context

Authors

Authors

J. Xie; P. A. Heng;M. Shah

Comments

Authors: contact us about adding a copy of your work at STARS@ucf.edu

Abbreviated Journal Title

Pattern Recognit.

Keywords

shape skeleton; saliency structure; shape matching; shape modeling; optimal matching; RECOGNITION; CONTOUR; CURVES; Computer Science, Artificial Intelligence; Engineering, Electrical &; Electronic

Abstract

Shape is a significant visual clue for human perception and shape models show considerable promise as a basis for extracting objects from images. This paper proposes a novel approach for shape matching and modeling using the symmetry characterization of shape interior and the spatial relationships of shape structures. Based on the representative skeletal features, we develop a mechanism to generate a coarse segment matching between different instances of an object. Additionally, the natural correspondence of skeletal branches to sequential segments along the shape curves is employed in the matching process to avoid false correspondences across different segments. Point matches within the corresponding segments are then obtained by solving a constrained assignment problem. The validation of the proposed approach is illustrated on various data sets in the presence of considerable deformation and occlusion and the results are compared with those of popular approaches. We also demonstrate the performance of our method on biological objects for shape modeling, showing better models than those obtained by the state-of-the-art shape modeling approaches. (C) 2007 Elsevier Ltd. All rights reserved.

Journal Title

Pattern Recognition

Volume

41

Issue/Number

5

Publication Date

1-1-2008

Document Type

Article

Language

English

First Page

1756

Last Page

1767

WOS Identifier

WOS:000253845700026

ISSN

0031-3203

Share

COinS