A technique for the selection of kernel-function parameters in RBF neural networks for classification of remote-sensing images.
Lorenzo BruzzoneDiego Fernández-PrietoPublished in: IEEE Trans. Geosci. Remote. Sens. (1999)
Keyphrases
- kernel function
- remote sensing images
- kernel parameters
- support vector
- change detection
- remote sensing
- multispectral
- support vector machine
- radial basis function
- feature space
- kernel methods
- rbf kernel
- input space
- high dimensional feature space
- multispectral images
- positive definite
- kernel learning
- marked point processes
- satellite images
- artificial neural networks
- landsat etm
- feature set
- high dimensional
- hyperspectral
- kernel matrix
- polynomial kernels
- reproducing kernel hilbert space
- neural network
- rbf network
- rbf neural network
- feature selection
- data sets
- kernel machines
- semantic similarity
- basis functions
- support vector machine svm
- dimensionality reduction
- image analysis