Multimodal Image Fusion in Presence of Noise Using Sparse Coding of ICA Coefficients

In this paper we present a novel image fusion method using Independent Component Analysis (ICA). The method uses sparse coding of the coefficients in ICA domain to determine the ICA coefficients to be used in the fused image reconstruction, so that the noise transferred from input images into the fused output is minimized. Compared to the standard multiresolutional fusion methods, the noise in the fused image is visually less annoying, while the important detail is still adequately represented. The proposed method exhibits considerably higher fusion performance, than the state-of-the-art algorithms, measured by Piella and Petrovic fusion metric.