The representation and matching of categorical shape

Shokoufandeh A., Bretzner L., Macrini D., Fatih Demirci M. F., Jönsson C., Dickinson S.

Computer Vision and Image Understanding, vol.103, no.2, pp.139-154, 2006 (SCI-Expanded, Scopus) identifier

  • Publication Type: Article / Article
  • Volume: 103 Issue: 2
  • Publication Date: 2006
  • Doi Number: 10.1016/j.cviu.2006.05.001
  • Journal Name: Computer Vision and Image Understanding
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.139-154
  • Keywords: Generic object recognition, Graph matching, Scale-spaces, Shape categorization, Spectral graph theory
  • Ankara Yıldırım Beyazıt University Affiliated: No

Abstract

We present a framework for categorical shape recognition. The coarse shape of an object is captured by a multiscale blob decomposition, representing the compact and elongated parts of an object at appropriate scales. These parts, in turn, map to nodes in a directed acyclic graph, in which edges encode both semantic relations (parent/child) as well as geometric relations. Given two image descriptions, each represented as a directed acyclic graph, we draw on spectral graph theory to derive a new algorithm for computing node correspondence in the presence of noise and occlusion. In computing correspondence, the similarity of two nodes is a function of their topological (graph) contexts, their geometric (relational) contexts, and their node contents. We demonstrate the approach on the domain of view-based 3-D object recognition. © 2006 Elsevier Inc. All rights reserved.