From Gestalt Theory to Image Analysis : A Probabilistic Approach Agnès Desolneux, Lionel Moisan, Jean-Michel Morel

Springer-Verlag, collection ``Interdisciplinary Applied Mathematics'', vol. #34, 2008 (275 p. 130 illus., Hardcover, ISBN: 978-0-387-72635-9)

---

Links

• Direct link to this book on springer.com / amazon.com / amazon.fr websites
• Most algorithms described in this book are freely available as MegaWave2 modules
• A preliminary version (preprint) is available here in PDF format. Please do not diffuse it without the consent of the authors.
• A review by Tim Patterson
• Research papers that cite this book: here

Description

This book introduces the reader to a recent theory in Computer Vision yielding elementary techniques to analyse digital images. These techniques are inspired from and are a mathematical formalization of the Gestalt theory. Gestalt theory, which had never been formalized is a rigorous realm of vision psychology developped between 1923 and 1975. From the mathematical viewpoint the closest field to it is stochastic geometry, involving basic probability and statistics, in the context of image analysis. The book is intended for a multidisciplinary audience of researchers and engineers. It is self contained in three aspects: mathematics, vision and algorithms, and requires only a background of elementary calculus and probability. A large number of illustrations, exercises and examples are included. The authors maintain a public software, MegaWave, containing implementations of most of the image analysis techniques developed in the book.

Table of contents

• Introduction
• Gestalt Theory
• The Helmholtz Principle
• Estimating the Binomial Tail
• Alignments in Digital Images
• Maximal Meaningfulness and the Exclusion Principle
• Modes of a Histogram
• Vanishing Points
• Contrasted Boundaries
• Variational or Meaningful Boundaries?
• Clusters
• Binocular Grouping
• A Psychophysical Study of the Helmholtz Principle
• Back to the Gestalt Programme

---

back to L. Moisan research page