Bayesian image segmentations by Potts prior and loopy belief propagation.
Kazuyuki TanakaShun KataokaMuneki YasudaYuji WaizumiChiou-Ting HsuPublished in: CoRR (2014)
Keyphrases
- loopy belief propagation
- image segmentations
- markov random field
- graph cuts
- image segmentation
- maximum a posteriori
- belief propagation
- posterior distribution
- segmentation algorithm
- energy minimization
- approximate inference
- conditional random fields
- markov chain monte carlo
- message passing
- graphical models
- energy function
- prior knowledge
- bayesian networks
- image segmentation algorithms
- region growing
- parameter estimation
- region merging
- pairwise
- computer vision
- scene images
- higher order
- posterior probability
- multiscale
- hyperparameters
- bayesian framework
- free energy
- maximum likelihood
- em algorithm
- three dimensional
- image processing
- feature selection
- machine learning