Sequential fuzzy cluster extraction by a graph spectral method

被引：31

作者：

Inoue, K ^{[1
]}

Urahama, K ^{[1
]}

机构：

[1] Kyushu Inst Design, Dept Visual Commun Design, Fukuoka 8158540, Japan

来源：

PATTERN RECOGNITION LETTERS | 1999年 / 20卷 / 07期

关键词：

fuzzy clustering; graph spectral method; weighted graph; image segmentation;

D O I：

10.1016/S0167-8655(99)00034-3

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Sequential extraction method is presented for fuzzy clusters from a set of point data which is represented by a weighted graph. Nodes and links in the graph have nonnegative real weights. Memberships of data in a cluster are evaluated by the principal eigenvector of the weighted adjacency matrix of the graph. Node weights are successively reduced after extraction of clusters. The extraction of clusters is stopped when the volume of an extracted cluster reveals abrupt rebound. The method is applied to image segmentation and extraction of skin color regions from color images. (C) 1999 Elsevier Science B.V. All rights reserved.

引用

页码：699 / 705

页数：7

共 7 条

[1]

Bezdek J. C., 1981, Pattern recognition with fuzzy objective function algorithms

[2]

Chiu SL., 1994, J INTELL FUZZY SYST, V2, P267, DOI [DOI 10.3233/IFS-1994-2306, 10.3233/IFS-1994-2306]

[3]

Cvetkovic D. M., 1980, Spectra of Graphs-Theory and Application

[4]

Krishnapuram R., 1993, IEEE Transactions on Fuzzy Systems, V1, P98, DOI 10.1109/91.227387

[5] Quantitative measures of change based on feature organization: Eigenvalues and eigenvectors [J].

Sarkar, S ;

Kim, KL .

COMPUTER VISION AND IMAGE UNDERSTANDING, 1998, 71 (01) :110-136

[6] Extracting straight lines by sequential fuzzy clustering [J].

Tsuda, K ;

Minoh, M ;

Ikeda, K .

PATTERN RECOGNITION LETTERS, 1996, 17 (06) :643-649

[7] APPROXIMATE CLUSTERING VIA THE MOUNTAIN METHOD [J].

YAGER, RR ;

FILEV, DP .

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1994, 24 (08) :1279-1284

← 1 →