Identification of Craters on Lunar Surface Using Hyperspectral Chandrayan Data

The aim of this paper is to identify Craters on Lunar surface on spectral basis by using Hyperspectral data since each landform of Moon have different spectral signature. Although Hyperspectral images contain a wealth of information due to its fine spectral resolution, the information is often redundant. It is therefore expedient to reduce the dimensionality of the data without losing significant information content then fractal based dimensionality reduction applied on high dimensional Hyperspectral data can be proved to be a better solution desired at a reduced computational complexity. Amongst a number of methods of computing fractal dimension, Multi Resolution Box Counting Method has been applied here. The experiments have been performed on a Hyperspectral data set acquired from HySI sensor of Chandrayan Satellite.