A convolutional deep belief network for polarimetric SAR data feature extraction.
Radu TanaseMihai DatcuDan RaducanuPublished in: IGARSS (2016)
Keyphrases
- deep belief networks
- sar data
- feature extraction
- synthetic aperture radar
- sar imagery
- sar images
- deep learning
- unsupervised learning
- restricted boltzmann machine
- hierarchical models
- probabilistic model
- generative model
- sparse coding
- polarimetric sar
- image reconstruction
- image processing
- image classification
- approximate inference
- feature selection
- dimensionality reduction
- feature vectors
- machine learning
- wavelet transform
- face recognition
- pattern recognition
- hierarchical model
- parameter estimation
- feature representation
- wavelet domain
- target detection
- feature space
- principal component analysis
- probabilistic graphical models
- frequency domain
- denoising
- input image
- target recognition
- edge detection
- super resolution
- maximum likelihood