On the resolution of local ambiguity in visual recognition: Modeling by tree-structured Markov random fields.
Akira DatePublished in: Systems and Computers in Japan (2005)
Keyphrases
- visual recognition
- markov random field
- image classification
- graph cuts
- belief propagation
- energy minimization
- energy function
- random fields
- parameter estimation
- pairwise
- image restoration
- mrf model
- potential functions
- higher order
- low level vision
- object recognition
- maximum a posteriori
- visual recognition tasks
- image segmentation
- conditional random fields
- high resolution
- loopy belief propagation
- map inference
- map estimation
- partition function
- undirected graphical models
- approximate inference
- stereo matching
- image reconstruction
- low resolution
- latent topic models
- discriminative random fields