Share Email Print

Optical Engineering

Hyperparameter estimation in image restoration problems with partially-known blurs
Author(s): Nikolas P. Galatsanos; Vladimir Z. Mesarovic; Rafael Molina; Aggelos K. Katsaggelos; Javier Mateos
Format Member Price Non-Member Price
PDF $20.00 $25.00
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

This work is motivated by the observation that it is not possible to reliably estimate simultaneously all the necessary hyperparameters in an image restoration problem when the point-spread function is assumed to be the sum of a known deterministic and an unknown random component. To solve this problem we propose to use gamma hyperpriors for the unknown hyperparameters. Two iterative algorithms that simultaneously restore the image and estimate the hyperparameters are derived, based on the application of evidence analysis within the hierarchical Bayesian framework. Numerical experiments are presented that show the benefits of introducing hyperpriors for this problem.

Paper Details

Date Published: 1 August 2002
PDF: 10 pages
Opt. Eng. 41(8) doi: 10.1117/1.1487850
Published in: Optical Engineering Volume 41, Issue 8
Show Author Affiliations
Nikolas P. Galatsanos, Illinois Institute of Technology (United States)
Vladimir Z. Mesarovic, Crystal Semiconductor Corp. (United States)
Rafael Molina, Univ. de Granada (Spain)
Aggelos K. Katsaggelos, Northwestern Univ. (United States)
Javier Mateos, Univ. de Granada (Spain)

© SPIE. Terms of Use
Back to Top