Band selection of hyperspectral-image based weighted indipendent component analysis

Huge amounts of data in hyperspectral images have been caused to represent approaches for the band selection of these images. In this paper, a new approach based on independent component analysis (ICA) is proposed. The idea of projection pursuit is used to order the bands on the basis of a non-gaussianity distribution. Applying a negentropy function to weight bands is a novel idea that leads to the selection of bands with minimum mutual information (MI) and besides maximum entropy, with respected to the bands selected using other methods.