In this paper, we introduce a new band selection approach for the color visualization of spectral images. Unlike traditional methods, we propose to make a selection out of a comparison of the saliency maps of the individual spectral channels. This allows to assess how different they are in terms of prominent features. A comparison metric based on Shannon's information theory at the second and third order is presented and results are subjectively and objectively compared to other dimensionality reduction techniques on three datasets, demonstrating the effciency of the proposed approach.