Fast clustering algorithm for vector quantisation

被引：4

作者：

Baek, S ^{[1
]}

Jeon, B ^{[1
]}

Lee, D ^{[1
]}

Sung, KM ^{[1
]}

机构：

[1] Seoul Natl Univ, Sch Elect Engn, Appl Elect Lab, Kwanak Gu, Seoul 151742, South Korea

来源：

ELECTRONICS LETTERS | 1998年 / 34卷 / 02期

关键词：

D O I：

10.1049/el:19980217

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

A fast clustering algorithm is presented as an alternative to the K-means algorithm. By encoding training vectors selectively and changing the codebook updating step, the algorithm reduces the computation time. Simulations show that the algorithm outperforms the K-means algorithm in computation time and performance in terms of mean-squared-error.

引用

页码：151 / 152

页数：2

共 6 条

[1]

Anderberg M.R., 1973, Probability and Mathematical Statistics

[2]

BAEK SJ, 1997, IEEE SIGNAL PROCESS, V4

[3]

LEE D, 1997, IEEE SIGNAL PROCESS, V4

[4] A FAST MEAN-DISTANCE-ORDERED PARTIAL CODEBOOK SEARCH ALGORITHM FOR IMAGE VECTOR QUANTIZATION [J].

RA, SW ;

KIM, JK .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-ANALOG AND DIGITAL SIGNAL PROCESSING, 1993, 40 (09) :576-579

[5] GLOBALLY OPTIMAL VECTOR QUANTIZER DESIGN BY STOCHASTIC RELAXATION [J].

ZEGER, K ;

VAISEY, J ;

GERSHO, A .

IEEE TRANSACTIONS ON SIGNAL PROCESSING, 1992, 40 (02) :310-322

[6]

[No title captured]

← 1 →