Abstract

The field of chemical hyperspectral (CHS) imaging is one that is still in the process of evolving, but it already has a wide range of applications in a variety of fields, including the military and the civilian sector. The detection and localization of materials based on the known spectrum properties of those materials is one application that may be carried out with the use of HS spectral data. In this paper, we develop a deep convolutional neural network to sense the minerals from the hyper spectral images using remote sensing. The images collected are used to classified using the deep learning model that classifies the instances and provides accurate results. The simulations are conducted to evaluate the efficacy of the model in detecting the minerals from the hyperspectral images. An accuracy of 92% is obtained during testing than other methods.

Key words: Chemical Hyperspectral Imaging, Convolutional Neural Network, Remote Sensing