A Comparative Analysis on the Applicability of Entropy in Remote Sensing

Entropy is the measure of uncertainty in any data and is adopted for maximisation of mutual information in many remote sensing operations. The availability of wide entropy variations motivated us for an investigation over the suitability preference of these versions to specific operations. The popular available versions like Tsalli's, Shannon's, and Renyi's entropies have been analysed in context of various remote sensing operations namely thresholding, clustering and registration. These methodologies have been evaluated with reference to the study area using different statistical parameters. Renyi's entropy has been found to be suitable for image registration purpose followed by Tsalli's and Shannon; whereas Tsalli's entropy has been found preferable for thresholding and clustering.