Object Recognition as Many-to-Many Feature Matching

  • Authors:

  • M. Fatih Demirci;Ali Shokoufandeh;Yakov Keselman;Lars Bretzner;Sven Dickinson

  • Affiliations:

  • Department of Computer Science, Drexel University, Philadelphia, USA 19104;Department of Computer Science, Drexel University, Philadelphia, USA 19104;School of Computer Science, Telecommunications and Information Systems, DePaul University, Chicago, USA 60604;Department of Numerical Analysis and Computer Science, KTH, Computational Vision and Active Perception Laboratory, Stockholm, Sweden;Department of Computer Science, University of Toronto, Toronto, Canada M5S 3G4

  • Venue:
  • International Journal of Computer Vision
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

Object recognition can be formulated as matching image features to model features. When recognition is exemplar-based, feature correspondence is one-to-one. However, segmentation errors, articulation, scale difference, and within-class deformation can yield image and model features which don't match one-to-one but rather many-to-many. Adopting a graph-based representation of a set of features, we present a matching algorithm that establishes many-to-many correspondences between the nodes of two noisy, vertex-labeled weighted graphs. Our approach reduces the problem of many-to-many matching of weighted graphs to that of many-to-many matching of weighted point sets in a normed vector space. This is accomplished by embedding the initial weighted graphs into a normed vector space with low distortion using a novel embedding technique based on a spherical encoding of graph structure. Many-to-many vector correspondences established by the Earth Mover's Distance framework are mapped back into many-to-many correspondences between graph nodes. Empirical evaluation of the algorithm on an extensive set of recognition trials, including a comparison with two competing graph matching approaches, demonstrates both the robustness and efficacy of the overall approach.