Segmentation of inhomogeneous foreground and background intensity objects using a probability density function based data term and nonparametric shape priors.
Abdurrahim SoganliMustafa Gökhan UzunbasMüjdat ÇetinPublished in: SIU (2012)
Keyphrases
- shape prior
- probability density function
- object segmentation
- foreground and background
- image segmentation
- prior information
- training data
- prior knowledge
- probability distribution
- segmentation algorithm
- data points
- kernel density estimation
- computer vision
- global optimization
- statistical methods
- graph cuts
- level set
- deformable models
- bayesian framework
- energy function
- foreground objects
- pixel wise
- color distribution
- medical images
- object recognition