Bone graphs: Medial shape parsing and abstraction

  • Authors:

  • Diego Macrini;Sven Dickinson;David Fleet;Kaleem Siddiqi

  • Affiliations:

  • School of Information Technology and Engineering, University of Ottawa, 800 King Edward Av., Colonel By, Room B407, Ottawa, Ontario, Canada K1N 6N;Department of Computer Science, University of Toronto, 6 King's College Rd, Room PT 283, Toronto, Ontario, Canada M5S 3H5;Department of Computer Science, University of Toronto, 6 King's College Rd, Room PT 283, Toronto, Ontario, Canada M5S 3H5;McGill University, McConnell Eng., 3480 University Street, Room 318, Montreal, Quebec, Canada H3A 2A7

  • Venue:
  • Computer Vision and Image Understanding
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

The recognition of 3-D objects from their silhouettes demands a shape representation which is stable with respect to minor changes in viewpoint and articulation. This can be achieved by parsing a silhouette into parts and relationships that do not change across similar object views. Medial descriptions, such as skeletons and shock graphs, provide part-based decompositions but suffer from instabilities. As a result, similar shapes may be represented by dissimilar part sets. We propose a novel shape parsing approach which is based on identifying and regularizing the ligature structure of a medial axis, leading to a bone graph, a medial abstraction which captures a more stable notion of an object's parts. Our experiments show that it offers improved recognition and pose estimation performance in the presence of within-class deformation over the shock graph.