Encoding Visual Information Using Anisotropic Transformations

  • Authors:
  • Giuseppe Boccignone;Mario Ferraro;Terry Caelli

  • Affiliations:
  • Univ. di Salerno, Salerno, Italy;Univ. di Torino, Torino, Italy;The Univ. of Alberta, Edmonton, Alberta, Canada

  • Venue:
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Year:
  • 2001

Quantified Score

Hi-index 0.14

Visualization

Abstract

The evolution of information in images undergoing fine-to-coarse anisotropic transformations is analyzed by using an approach based on the theory of irreversible transformations. In particular, we show that, when an anisotropic diffusion model is used, local variation of entropy production over space and scale provides the basis for a general method to extract relevant image features.