Share Email Print

Proceedings Paper

Statistical morphology
Author(s): Alan L. Yuille; Luc M. Vincent; Davi Geiger
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Basic morphological operations can be incorporated within a statistical physics formulation as a limit when the temperature of the system tends to zero. These operations can then be expressed in terms of finding minimum variance estimators of probability distributions. It enables one to relate these operations to alternative Bayesian or Markovian approaches to image analysis. It is shown how to derive elementary dilations (winner-take-all) and erosions (loser-take-all). These operations, referred to as statistical dilations and erosion, depend on a temperature parameter (beta) equals 1/T. They become purely morphological as (beta) goes to infinity and purely linear averages as (beta) goes to 0. Experimental results are given for a range of intermediate values of (beta) . Concatenations of elementary operations can be naturally expressed by stringing together conditional probability distributions, each corresponding to the original operations, thus yielding statistical openings and closings. Techniques are given for computing the minimal variance estimators.

Paper Details

Date Published: 1 July 1991
PDF: 12 pages
Proc. SPIE 1568, Image Algebra and Morphological Image Processing II, (1 July 1991); doi: 10.1117/12.46122
Show Author Affiliations
Alan L. Yuille, Harvard Univ. (United States)
Luc M. Vincent, Harvard Univ. (United States)
Davi Geiger, Siemens Corporate Research, Inc. (United States)

Published in SPIE Proceedings Vol. 1568:
Image Algebra and Morphological Image Processing II
Paul D. Gader; Edward R. Dougherty, Editor(s)

© SPIE. Terms of Use
Back to Top