Share Email Print

Optical Engineering

Counter-propagation neural network for image compression
Author(s): Wojciech Sygnowski; Bohdan Macukow
Format Member Price Non-Member Price
PDF $20.00 $25.00

Paper Abstract

Recently, several image compression techniques based on neural network algorithms have been developed. In this paper, we propose a new method for image compression—the modified counterpropagation neural network algorithm, which is a combination of the selforganizing map of Kohonen and the outstar structure of Grossberg. This algorithm has been successfully used in many applications. The modification presented has also demonstrated an interesting performance in comparison with the standard techniques. It was found that at the learning stage we can use any image for a network training (without a significant influence on the net operation) and the compression ratio and quality depend on the size of the basic element (the number of pixels in the cluster) and the amount of error tolerated when processing.

Paper Details

Date Published: 1 August 1996
PDF: 4 pages
Opt. Eng. 35(8) doi: 10.1117/1.600828
Published in: Optical Engineering Volume 35, Issue 8
Show Author Affiliations
Wojciech Sygnowski, Warsaw Univ. of Technology (Poland)
Bohdan Macukow, Technical Univ. of Warsaw (Poland)

© SPIE. Terms of Use
Back to Top