Color image segmentation and parameter estimation in a markovian framework

被引：30

作者：

Kato, Z

Pong, TC ^{[1
]}

Lee, JCM

机构：

[1] Hong Kong Univ Sci & Technol, Dept Comp Sci, Kowloon, Hong Kong, Peoples R China

[2] Natl Univ Singapore, Sch Comp, Singapore 117543, Singapore

来源：

PATTERN RECOGNITION LETTERS | 2001年 / 22卷 / 3-4期

关键词：

unsupervised image segmentation; color; Markov random fields; pixel classification; parameter estimation;

D O I：

10.1016/S0167-8655(00)00106-9

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

An unsupervised color image segmentation algorithm is presented, using a Markov random field (MRF) pixel classification model. We propose a new method to estimate initial mean vectors effectively even if the histogram does not have clearly distinguishable peaks. The only parameter supplied by the user is the number of classes. (C) 2001 Elsevier Science B.V. All rights reserved.

引用

页码：309 / 321

页数：13

共 15 条

[1]

[Anonymous], EXACTLY SOLVED MODEL

[2]

[Anonymous], P INT GEOSC REM SENS

[3]

Besag J., 1986, J ROY STAT SOC B

[4]

DAILY MJ, 1989, P DARPA IMAGE UNDERS