Share Email Print

Proceedings Paper

Super-Resolution And Neural Computing
Author(s): J B Abbiss; B J Braves; J S Bayley; M A Fiddy
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

The possibility of using a neural network to perform super-resolution is discussed. A method is presented for mapping a regularized super-resolution cost function onto a neural network of the Hopfield type. The required computational effort is compared to conventional matrix-based approaches to super-resolution.

Paper Details

Date Published: 20 April 1988
PDF: 7 pages
Proc. SPIE 0880, High Speed Computing, (20 April 1988); doi: 10.1117/12.944042
Show Author Affiliations
J B Abbiss, Spectron Development Laboratories (United States)
B J Braves, Spectron Development Laboratories (United States)
J S Bayley, University of Lowell (United States)
M A Fiddy, University of Lowell (United States)

Published in SPIE Proceedings Vol. 0880:
High Speed Computing
David P. Casasent, Editor(s)

© SPIE. Terms of Use
Back to Top