New MRF Parameter Estimation Technique for Texture Image Segmentation using Hierarchical GMRF Model Based on Random Spatial Interaction and Mean Field Theory.
Dong Hwan KimIl Dong YunSang Uk LeePublished in: ICPR (2) (2006)
Keyphrases
- parameter estimation
- markov random field
- texture image segmentation
- image segmentation
- maximum a posteriori
- random fields
- higher order
- gauss markov random fields
- belief propagation
- active contours
- graph cuts
- mrf model
- image restoration
- pairwise
- statistical models
- maximum likelihood
- model selection
- approximate inference
- energy function
- parameter estimation algorithm
- fully automatic
- posterior distribution
- prior model
- multiresolution
- expectation maximization
- least squares
- model fitting
- computer vision
- markov fields
- parameter estimates
- image processing
- parameter values
- textured images
- bayesian framework
- semi automatic
- em algorithm
- optical flow