EM procedures using mean field-like approximations for Markov model-based image segmentation

Pattern Recognition

Volumn 36, Issue 1, 2003, Pages 131-144

  Celeux, Gilles ^a   Forbes, Florence ^a   Peyrard, Nathalie ^a  

^a INRIA RHÔNE ALPES   (France)

Author keywords

EM algorithm; Hidden Markov random fields; ICM algorithm; Image segmentation; Mean field approximation; Pseudo likelihood; Simulated field

Indexed keywords

ALGORITHMS; APPROXIMATION THEORY; COMPUTER SIMULATION; MARKOV PROCESSES; MATHEMATICAL MODELS; PARAMETER ESTIMATION;

MARKOV RANDOM FIELDS;

IMAGE SEGMENTATION;

ALGORITHM; IMAGE PROCESSING; MARKOV CHAIN; SEGMENTATION;

EID: 0037209490     PISSN: 00313203     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0031-3203(02)00027-4     Document Type: Article

References (29)

1. Stochastic relaxation, Gibbs distributions and the Bayesian restoration of images
2. On the statistical analysis of dirty pictures
3. Statistical analysis of non-lattice data
4. An iterative Gibbsian technique for reconstruction of m-ary images
5. The mean field theory in EM procedures for Markov random fields
6. The mean field theory in EM procedures for Markov random fields
7. Maximum likelihood from incomplete data via the EM algorithm (with discussion)
8. Parallel and deterministic algorithms from MRFs: Surface reconstruction
9. Mean field approximation using compound Gauss-Markov random field for edge detection and image restoration
10. Generalized deformable models, statistical physics and matching problems
11. Improving the mean field approximation via the use of mixture distributions
12. Pairwise data clustering by deterministic annealing
13. Cluster expansions for the deterministic computation of Bayesian estimators based on Markov random fields
14. Convergence proof of an EM-type algorithm for spatial clustering
15. Estimation of parameters in hidden Markov models
16. Parameter estimation for hidden Markov chains
17. Mean fields and two-dimensional Markov random fields in image analysis
18. A classification EM algorithm for clustering and two stochastic versions
19. The SEM algorithm: A probabilistic teacher algorithm derived from the EM algorithm for the mixture problem
20. Nonuniversal critical dynamics in Monte Carlo simulations
21. Comments on a paper by S.L. Sclove
22. A Monte Carlo implementation of the EM algorithm and the poor man's data augmentation algorithms
23. The EM/MPM algorithm for segmentation of textures images: Analysis and further experimental results
24. Fine structures preserving Markov model for image processing
25. Markov random field with higher-order interactions