Convergence of an EM-type algorithm for spatial clustering

被引:53
作者
Ambroise, C [1 ]
Govaert, G
机构
[1] Univ Paris 06, LODYC, F-75252 Paris, France
[2] Univ Technol Compiegne, UMR CNRS 6599, F-60200 Compiegne, France
关键词
EM algorithm; Gaussian mixtures; spatial data; penalization;
D O I
10.1016/S0167-8655(98)00076-2
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Ambroise et al. (1996) have proposed a clustering algorithm that is well-suited for dealing with spatial data. This algorithm, derived from the EM algorithm (Dempster et al., 1977), has been designed for penalized likelihood estimation in situations with unobserved class labels. Some very satisfactory empirical results lead us to believe that this algorithm converges (Ambroise et al., 1996). However, this convergence has not been proven theoretically. In this paper, we present sufficient conditions and proof of the convergence. A practical application illustrates the use of this algorithm. (C) 1998 Published by Elsevier Science B.V. All rights reserved.
引用
收藏
页码:919 / 927
页数:9
相关论文
共 19 条
[1]  
AMBROISE C, 1996, P GEOENV
[2]  
AMBROISE C, 1996, THESIS U TECHNOLOGIE
[3]  
BERRY BJL, 1966, 111 U CHIC DEP GEOGR
[4]   FUZZY RANDOM-FIELDS AND UNSUPERVISED IMAGE SEGMENTATION [J].
CAILLOL, H ;
HILLION, A ;
PIECZYNSKI, W .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 1993, 31 (04) :801-810
[5]   GAUSSIAN PARSIMONIOUS CLUSTERING MODELS [J].
CELEUX, G ;
GOVAERT, G .
PATTERN RECOGNITION, 1995, 28 (05) :781-793
[6]   AN ITERATIVE GIBBSIAN TECHNIQUE FOR RECONSTRUCTION OF M-ARY IMAGES [J].
CHALMOND, B .
PATTERN RECOGNITION, 1989, 22 (06) :747-761
[7]   MAXIMUM LIKELIHOOD FROM INCOMPLETE DATA VIA EM ALGORITHM [J].
DEMPSTER, AP ;
LAIRD, NM ;
RUBIN, DB .
JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-METHODOLOGICAL, 1977, 39 (01) :1-38
[8]   STOCHASTIC RELAXATION, GIBBS DISTRIBUTIONS, AND THE BAYESIAN RESTORATION OF IMAGES [J].
GEMAN, S ;
GEMAN, D .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1984, 6 (06) :721-741
[9]  
Hart P.E., 1973, Pattern recognition and scene analysis
[10]   ANOTHER INTERPRETATION OF THE EM ALGORITHM FOR MIXTURE DISTRIBUTIONS [J].
HATHAWAY, RJ .
STATISTICS & PROBABILITY LETTERS, 1986, 4 (02) :53-56