Share Email Print

Proceedings Paper

Regularized image reconstruction using neural networks
Author(s): Ronald J. Steriti; Michael A. Fiddy
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Iterative methods have long been studied in order to reconstruct images from limited noisy spectral data or low pass filtered noisy images; they rely on minimizing a well-defined energy function. Such methods can be implemented on Hopfield neural networks, as a direct result of comparing energy function parameters. Consequently, a fully parallel (neural) processor can be programmed to implement a reconstruction algorithm. We have studied the properties of these neural solutions and show that they provide a regularized and apodized result with some attractive and interesting properties.

Paper Details

Date Published: 29 December 1992
PDF: 8 pages
Proc. SPIE 1767, Inverse Problems in Scattering and Imaging, (29 December 1992); doi: 10.1117/12.139010
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. 1767:
Inverse Problems in Scattering and Imaging
Michael A. Fiddy, Editor(s)

© SPIE. Terms of Use
Back to Top