A Novel Approach to the Selection of Spatially Invariant Features for the Classification of Hyperspectral Images With Improved Generalization Capability.
Lorenzo BruzzoneClaudio PerselloPublished in: IEEE Trans. Geosci. Remote. Sens. (2009)
Keyphrases
- hyperspectral images
- invariant features
- hyperspectral data
- hyperspectral
- hyperspectral imagery
- classification accuracy
- support vector
- remote sensing
- multispectral
- pattern recognition
- image matching
- feature space
- feature vectors
- image classification
- feature extraction
- multiscale
- face detection
- target detection
- hyperspectral remote sensing
- shape features
- detection algorithm
- co occurrence
- training set
- similarity measure