21. The Non-Accidentalness Principle for Visual Perception

  1. Liliana Albertazzi
  1. Agnès Desolneux1,
  2. Lionel Moisan2 and
  3. Jean-Michel Morel3

Published Online: 31 MAR 2013

DOI: 10.1002/9781118329016.ch21

Handbook of Experimental Phenomenology: Visual Perception of Shape, Space and Appearance

Handbook of Experimental Phenomenology: Visual Perception of Shape, Space and Appearance

How to Cite

Desolneux, A., Moisan, L. and Morel, J.-M. (2013) The Non-Accidentalness Principle for Visual Perception, in Handbook of Experimental Phenomenology: Visual Perception of Shape, Space and Appearance (ed L. Albertazzi), John Wiley & Sons, Ltd, Chichester, UK. doi: 10.1002/9781118329016.ch21

Editor Information

  1. University of Trento Center for the Mind and Brain (CIMeC), Italy

Author Information

  1. 1

    French National Center of Scientific Research (CNRS), France

  2. 2

    Paris Descartes University, France

  3. 3

    Ecole Normale Supérieure de Cachan, France

Publication History

  1. Published Online: 31 MAR 2013
  2. Published Print: 30 APR 2013

ISBN Information

Print ISBN: 9781119954682

Online ISBN: 9781118329016

SEARCH

Keywords:

  • a contrario methodology;
  • Gestalt grouping laws;
  • non-accidentalness principle;
  • quantitative way;
  • visual perception

Summary

To analyze images automatically with a computer the way a human being would do it, it first needs to answer, from a computational viewpoint, the question: “How can we go from qualitative to quantitative?”. Such a goal can be achieved by combining two principles of visual perception: the non-accidentalness principle and the Gestalt grouping laws. This chapter details these two principles, and shows how they can be combined in the framework of the so-called a contrario methodology. It illustrates this methodology on three examples: alignments, contrasted curves and good continuations. The chapter ends with an experimental section in which it proposes some protocols to check the validity of the a contrario methodology.