Affine invariant comparison of point-sets using convex hulls and hausdorff distances

  • Authors:
  • C. Gope;N. Kehtarnavaz

  • Affiliations:
  • Department of Electrical Engineering, EC 33, University of Texas at Dallas, Richardson, TX 75083-0688, USA;Department of Electrical Engineering, EC 33, University of Texas at Dallas, Richardson, TX 75083-0688, USA

  • Venue:
  • Pattern Recognition
  • Year:
  • 2007

Quantified Score

Hi-index 0.01

Visualization

Abstract

Many object recognition or identification applications involve comparing features associated with point-sets. This paper presents an affine invariant point-set matching technique which measures the similarity between two point-sets by embedding them into an affine invariant feature space. The developed technique assumes no a priori knowledge of reference points, as is the case in many identification problems. Reference points of a point-set are obtained based on its convex hull. An enhanced version of the Modified Hausdorff Distance is also introduced and used in the feature space for comparing two point-sets. It should be noted that the technique does not attempt to obtain correspondences between the point-sets. The introduced technique is applied to two real databases and its performance is found favorable as compared to three other affine invariant matching techniques.