Probabilistic models of digital region maps based on Markov random fields with short- and long-range interaction.
Georgy L. Gimel'farbAlexey ZalesnyPublished in: Pattern Recognit. Lett. (1993)
Keyphrases
- markov random field
- probabilistic model
- conditional random fields
- random fields
- graph cuts
- graphical models
- belief propagation
- markov networks
- parameter estimation
- pairwise
- higher order
- image segmentation
- mrf model
- maximum a posteriori
- energy minimization
- low level vision
- energy function
- expectation maximization
- undirected graphical models
- map inference
- potential functions
- map estimation
- generative model
- image restoration
- iterative conditional
- loopy belief propagation
- hidden variables
- parameter learning
- efficient inference
- long range
- bayesian inference
- input image
- bayesian networks
- potts model
- discriminative random fields
- crf model
- message passing
- latent variables
- partition function
- textured images
- maximum entropy