Polsar image classification based on three-dimensional wavelet texture features and Markov random field.
Haixia BiLin XuXiangyong CaoZongben XuPublished in: IGARSS (2017)
Keyphrases
- texture features
- markov random field
- image classification
- feature extraction
- three dimensional
- image features
- textured images
- mrf model
- wavelet transform
- feature vectors
- texture classification
- texture analysis
- image representation
- pairwise
- parameter estimation
- local binary pattern
- higher order
- gabor filters
- graph cuts
- image segmentation
- random fields
- texture information
- energy function
- texture images
- maximum a posteriori
- gray level
- wavelet coefficients
- rotation invariant
- multiscale
- sparse coding
- wavelet decomposition
- feature set
- image processing
- conditional random fields
- object recognition
- distance measure
- denoising
- feature space
- face recognition
- wavelet domain
- multiresolution
- texture descriptors
- computer vision
- power spectrum
- matching algorithm
- sar images
- subband
- image analysis