Unsupervised texture based image segmentation by simulated annealing using Markov random field and Potts models.
Mesut GoktepeVolkan AtalayNese YalabikCemal YalabikPublished in: ICPR (1998)
Keyphrases
- markov random field
- image segmentation
- random fields
- graph cuts
- parameter estimation
- potential functions
- mrf model
- mrf models
- simulated annealing
- energy function
- maximum a posteriori
- energy minimization
- higher order
- pairwise
- image restoration
- belief propagation
- contextual constraints
- markov random field model
- texture model
- textured images
- map estimation
- iterated conditional modes
- prior model
- clique potentials
- genetic algorithm
- loopy belief propagation
- potts model
- segmentation algorithm
- mrf optimization
- message passing
- min cut
- bayesian framework
- multi label
- conditional random fields