Share Email Print
cover

Proceedings Paper

Mean-field theory for grayscale texture synthesis using Gibbs random fields
Author(s): Ibrahim M. Elfadel; Alan L. Yuille
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

This paper shows how methods developed in the context of statistical physics can be used to analyze gray-scale texture synthesis procedures based on the probabilistic paradigm of Gibbs random fields (GRF). In particular, using the mean-field equations of the texture GRF, the existence of a bifurcation point indicating the presence of a phase transition in the textural pattern is shown. Using simulations, it is shown that a number of interesting phenomena occur at the bifurcation temperature like a sudden decrease in energy, sharp peaks in similarity measures between textural patterns, and sudden saturation of the mean-field variables. For texture synthesis, it is sufficient to simulate the mean-field equations near the bifurcation temperature.

Paper Details

Date Published: 1 October 1991
PDF: 12 pages
Proc. SPIE 1569, Stochastic and Neural Methods in Signal Processing, Image Processing, and Computer Vision, (1 October 1991); doi: 10.1117/12.48383
Show Author Affiliations
Ibrahim M. Elfadel, Massachusetts Institute of Technology (United States)
Alan L. Yuille, Harvard Univ. (United States)


Published in SPIE Proceedings Vol. 1569:
Stochastic and Neural Methods in Signal Processing, Image Processing, and Computer Vision
Su-Shing Chen, Editor(s)

© SPIE. Terms of Use
Back to Top