Share Email Print

Proceedings Paper

Neural network approach to adaptive image enhancement
Author(s): Ling Guan
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

This paper introduces a two-stage adaptive filter for digital image enhancement. This filter has good edge preservation as well as optical enhancement characteristics. The first stage of the filter uses a set of three-layer perceptron neural networks to predict the location of edges. As a result, a piecewise linear model for the image is obtained. With that knowledge, the second stage uses a neural network similar to Hopfield-Tank network to optimally smooth the image to fit the model.

Paper Details

Date Published: 1 April 1992
PDF: 9 pages
Proc. SPIE 1658, Nonlinear Image Processing III, (1 April 1992); doi: 10.1117/12.58382
Show Author Affiliations
Ling Guan, Array Systems Computing Inc. (Canada)

Published in SPIE Proceedings Vol. 1658:
Nonlinear Image Processing III
Edward R. Dougherty; Jaakko T. Astola; Charles G. Boncelet Jr., Editor(s)

© SPIE. Terms of Use
Back to Top