SAR Image Classification Through Information-Theoretic Textural Features, MRF Segmentation, and Object-Oriented Learning Vector Quantization.
Ciro D'EliaSimona RuscinoMaurizio AbbateBruno AiazziStefano BarontiLuciano AlparonePublished in: IEEE J. Sel. Top. Appl. Earth Obs. Remote. Sens. (2014)
Keyphrases
- information theoretic
- learning vector quantization
- textural features
- sar images
- mutual information
- information theory
- pixel classification
- image segmentation
- texture analysis
- synthetic aperture radar
- gray level
- self organizing maps
- energy function
- visual inspection
- texture features
- markov random field
- multiscale
- graph cuts
- neural network
- kullback leibler divergence
- text classification
- classification accuracy
- image analysis
- pattern recognition
- color image segmentation
- visual features
- feature set
- co occurrence
- pairwise
- feature space
- decision trees