Share Email Print

Proceedings Paper

Blind deconvolution of images using neural networks
Author(s): Ronald J. Steriti; Michael A. Fiddy
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

In this paper we consider the blind deconvolution of an image from an unknown blurring function using a technique employing two nested Hopfield neural networks. This iterative method consists of two steps, first estimating the blurring function followed by the use of this function to estimate the original image. The successive inter-linked energy minimizations are found to converge in practice although a convergence proof has not yet been established.

Paper Details

Date Published: 8 July 1994
PDF: 7 pages
Proc. SPIE 2241, Inverse Optics III, (8 July 1994); doi: 10.1117/12.179744
Show Author Affiliations
Ronald J. Steriti, Univ. of Massachusetts/Lowell (United States)
Michael A. Fiddy, Univ. of Massachusetts/Lowell (United States)

Published in SPIE Proceedings Vol. 2241:
Inverse Optics III
Michael A. Fiddy, Editor(s)

© SPIE. Terms of Use
Back to Top