Share Email Print

Proceedings Paper

Multiscale image coding using the Kohonen neural network
Author(s): Marc Antonini; Michel Barlaud; Pierre Mathieu; J. C. Feauveau
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

This paper proposes a new method for image coding involving two steps. First, we use a 'Dual Recursive Wavelet' Transform in order to obtain a set of subclasses of images with better characteristics than the original image (lower entropy, edges discrimination, ... ). Second, according to Shannon's rate distortion theory, the wavelet coefficients are vector quantized using the Kohonen Self-Organizing Feature Maps. We compare this training method with the well known LBG algorithm.

Paper Details

Date Published: 1 September 1990
PDF: 13 pages
Proc. SPIE 1360, Visual Communications and Image Processing '90: Fifth in a Series, (1 September 1990); doi: 10.1117/12.24101
Show Author Affiliations
Marc Antonini, Univ. de Nice-Sophia Antipolis (France)
Michel Barlaud, Univ. de Nice-Sophia Antipolis (France)
Pierre Mathieu, Univ. de Nice-Sophia Antipolis (France)
J. C. Feauveau, Univ. Paris-Sud (France)

Published in SPIE Proceedings Vol. 1360:
Visual Communications and Image Processing '90: Fifth in a Series
Murat Kunt, Editor(s)

© SPIE. Terms of Use
Back to Top