A stable skeletonization for tabletop gesture recognition

  • Authors:
  • Andoni Beristain;Manuel Graña

  • Affiliations:
  • Computational Intelligence Group, Universidad del Pais Vasco;Computational Intelligence Group, Universidad del Pais Vasco

  • Venue:
  • ICCSA'10 Proceedings of the 2010 international conference on Computational Science and Its Applications - Volume Part I
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

An efficient and stable skeletonization consisting of a Voronoi skeletonization following by a two step pruning is presented. The first pruning step removes Voronoi edges crossing the shape boundary. The second follows a Discrete Curve Evolution approach. Both pruning steps can be done very efficiently because entire Voronoi segments are pruned based on tests on points. The algorithm works in realtime and could be used in a gesture recognition interface for tabletop interfaces.