Edge Detection by Helmholtz Principle

  • Authors:
  • Agnès Desolneux;Lionel Moisan;Jean-Michel Morel

  • Affiliations:
  • CMLA, ENS Cachan, 61 av. du président Wilson, 94235 Cachan cedex, France. desolneu@cmla.ens-cachan.fr;CMLA, ENS Cachan, 61 av. du président Wilson, 94235 Cachan cedex, France. moisan@cmla.ens-cachan.fr;CMLA, ENS Cachan, 61 av. du président Wilson, 94235 Cachan cedex, France. morel@cmla.ens-cachan.fr

  • Venue:
  • Journal of Mathematical Imaging and Vision
  • Year:
  • 2001

Quantified Score

Hi-index 0.00

Visualization

Abstract

We apply to edge detection a recently introduced method for computing geometric structures in a digital image, without any a priori information. According to a basic principle of perception due to Helmholtz, an observed geometric structure is perceptually “meaningful” if its number of occurences would be very small in a random situation: in this context, geometric structures are characterized as large deviations from randomness. This leads us to define and compute edges and boundaries (closed edges) in an image by a parameter-free method. Maximal detectable boundaries and edges are defined, computed, and the results compared with the ones obtained by classical algorithms.