An approximate method of evaluating the joint likelihood for first-order GMRFs

被引：3

作者：

Wu, Zhenyu ^{[1
]}

Leahy, Richard ^{[1
]}

机构：

[1] Univ So Calif, Dept Elect Engn Syst, Inst Signal & Image Proc, Los Angeles, CA 90089 USA

来源：

IEEE TRANSACTIONS ON IMAGE PROCESSING | 1993年 / 2卷 / 04期

关键词：

D O I：

10.1109/83.242360

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We propose a highly accurate approximation for computing the joint likelihood for first-order GMRF's defined on irregular shaped lattices. The challenge of computing the likelihood lies in evaluating the determinant of a very large matrix B. Its exact evaluation is limited to either very small irregular regions or a few regular shaped regions. The approximation proposed here is based on an eigen-analysis of B.

引用

页码：520 / 523

页数：4

共 15 条

[1] STATISTICAL-ANALYSIS OF NON-LATTICE DATA
BESAG, J
[J]. JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES D-THE STATISTICIAN, 1975, 24 (03) : 179 - 195
[2] BESAG J, 1974, J ROY STAT SOC B MET, V36, P192
[3] BESAG J, 1977, BIOMETRIKA, V64, P616, DOI 10.1093/biomet/64.3.616
[4] BESAG JE, 1975, BIOMETRIKA, V62, P555
[5] TEXTURE SYNTHESIS USING 2-D NONCAUSAL AUTOREGRESSIVE MODELS
CHELLAPPA, R
KASHYAP, RL
[J]. IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1985, 33 (01): : 194 - 203
[6] MODELING AND SEGMENTATION OF NOISY AND TEXTURED IMAGES USING GIBBS RANDOM-FIELDS
DERIN, H
ELLIOTT, H
[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1987, 9 (01) : 39 - 55
[7] STOCHASTIC RELAXATION, GIBBS DISTRIBUTIONS, AND THE BAYESIAN RESTORATION OF IMAGES
GEMAN, S
GEMAN, D
[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1984, 6 (06) : 721 - 741
[8] PARAMETER-ESTIMATION FOR A STATIONARY PROCESS ON A D-DIMENSIONAL LATTICE
GUYON, X
[J]. BIOMETRIKA, 1982, 69 (01) : 95 - 105
[9] MAXIMUM-LIKELIHOOD ESTIMATION OF MODELS FOR RESIDUAL COVARIANCE IN SPATIAL REGRESSION
MARDIA, KV
MARSHALL, RJ
[J]. BIOMETRIKA, 1984, 71 (01) : 135 - 146
[10] OGATA Y, 1984, J R STAT SOC B, V46, P496

← 1 2 →