Skeleton Based Shape Matching and Retrieval

  • Authors:
  • H. Sundar;D. Silver;N. Gagvani;S. Dickinson

  • Affiliations:
  • -;-;-;-

  • Venue:
  • SMI '03 Proceedings of the Shape Modeling International 2003
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, we describe a novel method for searchingand comparing 3D objects. The method encodes the geometricand topological information in the form of a skeletalgraph and uses graph matching techniques to match theskeletons and to compare them. The skeletal graphs canbe manually annotated to refine or restructure the search.This helps in choosing between a topological similarity anda geometric (shape) similarity. A feature of skeletal matchingis the ability to perform part-matching, and its inherentintuitiveness, which helps in defining the search and invisualizing the results. Also, the matching results, whichare presented in a per-node basis can be used for driving anumber of registration algorithms, most of which require agood initial guess to perform registration. In this paper, wealso describe a visualization tool to aid in the selection andspecification of the matched objects.