Power watersheds: A new image segmentation framework extending graph cuts, random walker and optimal spanning forest.
Camille CouprieLeo J. GradyLaurent NajmanHugues TalbotPublished in: ICCV (2009)
Keyphrases
- graph cuts
- random walker
- image segmentation
- globally optimal
- interactive image segmentation
- markov random field
- graph based image segmentation
- energy minimization
- energy function
- energy minimization framework
- shape prior
- multi label
- belief propagation
- mean shift
- object segmentation
- segmentation algorithm
- text mining
- energy minimization problems
- spatial smoothness
- labeling problems
- interactive segmentation
- min cut
- geodesic active contours
- knn
- superpixels
- foreground background segmentation
- region growing
- probabilistic model
- higher order
- segmentation method
- machine learning