Share Email Print
cover

Proceedings Paper

Training a Boltzmann machine for edge-preserving image restoration
Author(s): Luigi Bedini; Simone Pandolfi; Anna Tonazzini
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

The most successful methods to stabilize inverse ill-posed problems in visual reconstruction use a priori information on the local regularity of the image as well as constraints on the geometry of the discontinuities. A commonly used method to incorporate prior knowledge into the problem is to adopt a Bayesian approach in which the image is modelled by a parametric Gibbs prior and the solution is obtained by minimizing the resulting posterior energy function (MAP estimate). However, this approach presents two major difficulties: the first is related to the non-convexity of the function to be optimized; the second to the choice of the model parameters that best fit the available prior knowledge. Since these parameters strongly affect the quality of the reconstructions, their selection is a critical task. They are usually determined empirically by trial and error. The paper proposes a generalized Boltzmann Machine which makes it possible to learn the most appropriate parameters for a given class of images from a series of examples. The trained Boltzmann Machine is then used to implement an annealing scheme for the minimization of the non-convex posterior energy. The method is applied to the restoration of piecewise smooth images.

Paper Details

Date Published: 29 October 1993
PDF: 11 pages
Proc. SPIE 2032, Neural and Stochastic Methods in Image and Signal Processing II, (29 October 1993); doi: 10.1117/12.162032
Show Author Affiliations
Luigi Bedini, Istituto di Elaborazione della Informazione (Italy)
Simone Pandolfi, Istituto di Elaborazione della Informazione (Italy)
Anna Tonazzini, Istituto di Elaborazione della Informazione (Italy)


Published in SPIE Proceedings Vol. 2032:
Neural and Stochastic Methods in Image and Signal Processing II
Su-Shing Chen, Editor(s)

© SPIE. Terms of Use
Back to Top