NEW PREDICTIVE CLASSIFIED VECTOR QUANTIZATION SCHEME FOR IMAGE COMPRESSION

Authors
LO KT CHAM WK
Citation
Kt. Lo et Wk. Cham, NEW PREDICTIVE CLASSIFIED VECTOR QUANTIZATION SCHEME FOR IMAGE COMPRESSION, Electronics Letters, 30(16), 1994, pp. 1280-1282
Citations number
7
Categorie Soggetti
Engineering, Eletrical & Electronic
Journal title
Electronics Letters → ACNP
ISSN journal
00135194
Volume
30
Issue
16
Year of publication
1994
Pages
1280 - 1282
Database
ISI
SICI code
0013-5194(1994)30:16<1280:NPCVQS>2.0.ZU;2-V
Abstract
A new image coding method using predictive classified vector quantisat ion (PCVQ) is proposed. The image is first divided into different subs ources using a two-stage classification method based on the optimum th ree-level block truncation coding technique. Each subsource is then ve ctor quantised using different codebooks. Simulation results show that an improvement of about 2 to 6dB in PSNR performance over the JPEG sc heme is obtained at the rate of 0.4375bit/pixel.