The manifold learning for dimensionality reduction with hyperspectral image.
Zezhong ZhengPengxu ChenMingcang ZhuZhiqin HuangYong HeYicong FengYufeng LuZhenlu YuShijie YuShengli WangJiang LiPublished in: IGARSS (2016)
Keyphrases
- manifold learning
- dimensionality reduction
- hyperspectral images
- hyperspectral
- low dimensional
- high dimensional
- high dimensional data
- nonlinear dimensionality reduction
- diffusion maps
- remote sensing
- principal component analysis
- feature extraction
- subspace learning
- singular value decomposition
- multispectral
- feature selection
- high dimensionality
- pattern recognition
- feature space
- unsupervised learning
- locally linear embedding
- linear discriminant analysis
- input space
- discriminant projection
- laplacian eigenmaps
- manifold structure
- dimensionality reduction methods
- lower dimensional
- image analysis
- random projections
- principal components
- geodesic distance
- target detection
- multispectral images
- data sets
- sparse representation
- nearest neighbor
- information content
- dimension reduction
- infrared
- metric learning
- image features
- training set
- image classification
- data analysis
- high dimensional feature space
- image segmentation
- intrinsic dimensionality
- graph embedding
- discriminant analysis
- computer vision