Patch-Based texture edges and segmentation

  • Authors:
  • Lior Wolf;Xiaolei Huang;Ian Martin;Dimitris Metaxas

  • Affiliations:
  • Center for Biological and Computational Learning, The McGovern Institute for Brain Research and dept. of Brain & Cognitive Sciences, Massachusetts Institute of Technology, Cambridge, MA;Division of Computer and Information Sciences, Rutgers University, New Brunswick, NJ;Center for Biological and Computational Learning, The McGovern Institute for Brain Research and dept. of Brain & Cognitive Sciences, Massachusetts Institute of Technology, Cambridge, MA;Division of Computer and Information Sciences, Rutgers University, New Brunswick, NJ

  • Venue:
  • ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part II
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

A novel technique for extracting texture edges is introduced. It is based on the combination of two ideas: the patch-based approach, and non-parametric tests of distributions. Our method can reliably detect texture edges using only local information. Therefore, it can be computed as a preprocessing step prior to segmentation, and can be very easily combined with parametric deformable models. These models furnish our system with smooth boundaries and globally salient structures.