Automated data-driven selection of the hyperparameters for Total-Variation based texture segmentation.
Barbara PascalSamuel VaiterNelly PustelnikPatrice AbryPublished in: CoRR (2020)
Keyphrases
- texture segmentation
- data driven
- hyperparameters
- model selection
- cross validation
- multiresolution
- texture analysis
- region and edge information
- noise level
- support vector
- closed form
- random sampling
- bayesian inference
- image segmentation
- segmentation of textured images
- gabor filters
- em algorithm
- prior information
- maximum likelihood
- bayesian framework
- incremental learning
- noisy images
- sample size
- incomplete data
- maximum a posteriori
- active contour model
- parameter settings
- parameter space
- data sets
- missing values
- distance measure
- image processing