Share Email Print

Proceedings Paper

Vector quantization of image pyramids with the ECPNN algorithm
Author(s): Diego Pinto de Garrido; William A. Pearlman; Weiler A. Finamore
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

A recent algorithm for single rate vector quantization is used for coding image pyramids. The algorithm, called entropy-constrained pairwise-nearest-neighbor (ECPNN), designs codebooks by merging the pair of Voronoi regions which gives the most decrease in entropy for a given increase in distortion. In terms of performance in the mean-squared-error sense the algorithm produces codebooks with the same performance as the ECVQ design algorithm. The main advantage over ECVQ is that ECPNN algorithm enables much faster codebook design. A single pass through the ECPNN design algorithm, which progresses from large to successively smaller rates, allows the storage of any desired number of optimal intermediate-rate codebooks. In the context of pyramid coding, this feature is especially desirable, since the ECPNN design algorithm must be run for each sub-band and storage of codebooks of different rates are required for each subband. Good results at 0.5 bpp, judged both visually and using peak-to-peak SNR criterion, have been obtained by coding image pyramids using ECPNN codebooks.

Paper Details

Date Published: 1 November 1991
PDF: 12 pages
Proc. SPIE 1605, Visual Communications and Image Processing '91: Visual Communication, (1 November 1991); doi: 10.1117/12.50307
Show Author Affiliations
Diego Pinto de Garrido, Rensselaer Polytechnic Institute (United States)
William A. Pearlman, Rensselaer Polytechnic Institute (United States)
Weiler A. Finamore, IBM/Rio Scientific Ctr. (Brazil)

Published in SPIE Proceedings Vol. 1605:
Visual Communications and Image Processing '91: Visual Communication
Kou-Hu Tzou; Toshio Koga, Editor(s)

© SPIE. Terms of Use
Back to Top