Shape matching and modeling using skeletal context

    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