Hyperspectral Data Classification using Deep Convolutional Neural Networks

In the last five years, deep learning has been gaining a large amount of interest in the computer vision community due to its capability to perform feature learning and classification at the same time. However, the studies using deep learning for hyperspectral imaging are still very few. In this paper, a deep convolutional neural network structure to classify hyperspectral data is proposed. The results are compared to the support vector machine and K-nearest neighbourhood algorithms and it has been shown that deep learning with the proposed architecture is much more successful in hyperspectral data classification.