Abstract

We demonstrate a close relationship between classical models from statistical physics and Markov random-field models for image labeling purposes. A picture is taken of a real image or map, defined by a measure of intensity over a set of pixels. Possible class (or gray-level) values are assigned to spin values in Potts theory. We present a continuous analysis of image relaxation by mean-field theory and apply it by using standard and extended Potts models. Accurate relaxation results were obtained with a specific deterministic method called mean-field fast annealing.

© 1997 Optical Society of America

Adaptive quadrature filters and the recovery of phase from fringe pattern images

J. L. Marroquin, M. Servin, and R. Rodriguez-Vera
J. Opt. Soc. Am. A 14(8) 1742-1753 (1997)

Generalized method for evaluating scattering parameters used in radiative transfer models

William E. Vargas and Gunnar A. Niklasson
J. Opt. Soc. Am. A 14(9) 2243-2252 (1997)

Optimal target tracking on image sequences with a deterministic background

François Goudail and Philippe Réfrégier
J. Opt. Soc. Am. A 14(12) 3197-3207 (1997)

Robust quadrature filters

J. L. Marroquin, J. E. Figueroa, and M. Servin
J. Opt. Soc. Am. A 14(4) 779-791 (1997)

Novel deblurring algorithms for images captured with CCD cameras

Chen-Hsien Wu and John M. M. Anderson
J. Opt. Soc. Am. A 14(7) 1421-1430 (1997)