Band selection and classification of hyperspectral images using Mutual Information: An algorithm based on minimizing the error probability using the inequality of Fano.
Elkebir SarhrouniAhmed HammouchDriss AboutajdinePublished in: ICMCS (2012)
Keyphrases
- hyperspectral images
- error probability
- band selection
- mutual information
- hyperspectral
- hyperspectral data
- similarity measure
- hyperspectral imagery
- hyperspectral remote sensing images
- pixel classification
- pattern recognition
- target detection
- remote sensing
- learning algorithm
- detection algorithm
- segmentation algorithm
- support vector
- upper bound
- hyperspectral imaging
- training set
- feature selection