Home // International Journal On Advances in Software, volume 5, numbers 3 and 4, 2012 // View article

Restoration of Blurred Images Using Revised Bayesian-Based Iterative Method

Authors:
Sigeru Omatu
Hideo Araki
Yuka Nagashima

Keywords: point spread function;Bayesian rule

Abstract:
A restoration method of degraded images based on the Bayesian-based iterative method is proposed. An iterative method is developed by regarding the observed degraded images as probabilities and point spread functions as the conditional probabilities. The restored images are estimated by using Bayesian rule. We have proposed two kinds of the iterative method. One is to use the observed images as the initial values of the estimated images when we estimate the point spread function. The other method is to estimate the initial values of the point spread function by using the logarithmic amplitude spectrum of the blurred image. The simulation results show that the proposed methods are effective to restore the blurred images.

Pages: 358 to 367

Copyright: Copyright (c) to authors, 2012. Used with permission.

Publication date: December 31, 2012

Published in: journal

ISSN: 1942-2628