Multimodal image sensor fusion using independent component analysis

Abstract

In this chapter, we present a novel multimodal image fusion algorithm using the Independent Component Analysis (ICA). Region-based fusion of ICA coefficients is implemented, in which the mean absolute value of ICA coefficients is used as an activity indicator for the given region. The ICA coefficients from given regions are consequently weighted using the Piella fusion metric in order to maximise the quality of the fused image. The proposed method exhibits significantly higher performance than the basic ICA algorithm and improvement over the other state-of-the-art algorithms. © 2008 Springer-Verlag Berlin Heidelberg.