Bimean clustering

被引：5

作者：

Dunn, Stanley ^{[1
]}

Janos, Ludvik ^{[1
]}

Rosenfeld, Azriel ^{[1
]}

机构：

[1] Univ Maryland, Ctr Comp Sci, Comp Vis Lab, College Pk, MD 20742 USA

来源：

PATTERN RECOGNITION LETTERS | 1983年 / 1卷 / 03期

关键词：

Image processing; segmentation; thresholding; clustering; ISODATA;

D O I：

10.1016/0167-8655(83)90058-2

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

An algorithm is presented which finds the best-fitting pair of constants, in the least squares sense, to a set of scalar data; we call this pair of constants the 'bimean' of the data. The relationship of the bimean clustering to the ISODATA clustering algorithm, and its application to image thresholding, are also discussed

引用

页码：169 / 173

页数：5