Variable rate vector quantization of images using decision trees

Eve A. Riskin, Robert M. Gray, Richard A. Olshen

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

Techniques for clustering and the design of decision trees have been combined recently to produce codes. These tree-structured codes are efficient and easy to implement for problems of variable rate image compression. A summary is presented of some techniques for the resulting vector quantizers, which are explained in the context of designing decision trees. A description is presented of how to grow large trees by splitting nodes individually, and how to prune these large trees by an algorithm termed the generalized BFOS algorithm. Estimation based on an independent test sample and on cross-validation both figure in pruning algorithms.

Original languageEnglish
Title of host publicationConference Record - Asilomar Conference on Circuits, Systems & Computers
Pages319-321
Number of pages3
StatePublished - 1991
Event24th Asilomar Conference on Signals, Systems and Computers Part 2 (of 2) - Pacific Grove, CA, USA
Duration: 5 Nov 19907 Nov 1990

Publication series

NameConference Record - Asilomar Conference on Circuits, Systems & Computers
Volume1
ISSN (Print)0736-5861

Conference

Conference24th Asilomar Conference on Signals, Systems and Computers Part 2 (of 2)
CityPacific Grove, CA, USA
Period5/11/907/11/90

Fingerprint

Dive into the research topics of 'Variable rate vector quantization of images using decision trees'. Together they form a unique fingerprint.

Cite this