Parameter estimation and segmentation of noisy or textured images using the EM algorithm and MPM estimation
- 17 December 2002
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 650-654
- https://doi.org/10.1109/icip.1994.413651
Abstract
In this paper we present a new algorithm for segmentationof noisy or textured images using the expectation-maximization (EM) algorithm for estimatingparameters of the probability mass function of thepixel class labels and the maximization of the posteriormarginals (MPM) criterion for the segmentation operation.A Markov random field (MRF) model is usedfor the pixel class labels. We present experimental resultsdemonstrating the use of the new algorithm onsynthetic images and medical...Keywords
This publication has 8 references indexed in Scilit:
- Maximum-likelihood parameter estimation for unsupervised stochastic model-based image segmentationIEEE Transactions on Image Processing, 1994
- The mean field theory in EM procedures for Markov random fieldsIEEE Transactions on Signal Processing, 1992
- Simultaneous parameter estimation and segmentation of Gibbs random fields using simulated annealingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1989
- Bayesian clustering for unsupervised estimation of surface and texture modelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1988
- Adaptive segmentation of speckled images using a hierarchical random field modelIEEE Transactions on Acoustics, Speech, and Signal Processing, 1988
- Probabilistic Solution of Ill-Posed Problems in Computational VisionJournal of the American Statistical Association, 1987
- Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of ImagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1984
- On the Convergence Properties of the EM AlgorithmThe Annals of Statistics, 1983