Unsupervised Band Selection for Multispectral Images using Information Theory

In this paper, the implication of the relations of information in the case of multispectral images is analyzed. Higher-order mutual information can adopt positive or negative values depending of the correlation among ensembles. Therefore, the existence of negative values reflects higherorder correlations in the conditional informations. On the other hand, the extraction of optimal subsets of spectral images is proposed as a maximization of the conditional entropies at same time that the dependent information among images is minimized.

• Type: Conference
• Year: 2004
• Where: ICPR
• Authors: Arnoud C. Klaren, Filiberto Pla, José Martínez Sotoca
• Keywords: Computer Vision, Conditional Informations, ICPR 2004, Multispectral Images, Negative Values