Unsupervised PolSAR Image Classification and Segmentation Using Dirichlet Process Mixture Model and Markov Random Fields With Similarity Measure.
Wanying SongMing LiPeng ZhangYan WuLu JiaLin AnPublished in: IEEE J. Sel. Top. Appl. Earth Obs. Remote. Sens. (2017)
Keyphrases
- markov random field
- image classification
- image segmentation
- energy function
- similarity measure
- mrf model
- dirichlet process mixture models
- low level vision
- textured images
- pairwise
- graph cuts
- energy minimization
- belief propagation
- parameter estimation
- higher order
- maximum a posteriori
- segmentation method
- random fields
- level set
- feature extraction
- semi supervised
- multiscale
- multi label
- markov networks
- image features
- bag of words
- labeled data
- prior information
- unsupervised learning
- dictionary learning
- supervised learning
- active contours
- semi supervised learning
- natural images