Modularity versus Laplacian Eigenmaps for dimensionality reduction and classification of hyperspectral imagery.
Nathan D. CahillD. Benjamin StartSelene E. ChewPublished in: WHISPERS (2014)
Keyphrases
- hyperspectral imagery
- laplacian eigenmaps
- manifold learning
- kernel pca
- nonlinear dimensionality reduction
- multispectral
- remote sensing
- spatial resolution
- hyperspectral images
- hyperspectral
- target detection
- dimensionality reduction
- low dimensional
- empirical mode decomposition
- infrared
- euclidean space
- multi band
- computer vision
- kernel methods
- high dimensional data
- principal component analysis
- high dimensional
- input space
- kernel matrix
- support vector regression
- image data
- feature space