Hyperspectral Image Features Classification Using Deep Learning Recurrent Neural Networks

The implementation of Deep learning (DL) techniques, Object detection and classification has achieved remarkable results in remote sensing application. Deep learning with Recurrent Neural Network (RNN) technique on hyper-spectral data has been presented here. The only model which can analyze the hyper-spectral pixels as the sequence of information and also to identify the additional information categories through network reasoning is RNN model. This is first time that the framework of RNN has been introduced for the classification of hyper spectral Image. An activation function is proposed by the DL-RNN and also the parameter rectified functions for analyzing the sequence of data in the hyper-spectral images. Throughout the training procedure, the higher learning rates are fairly used by the activation function which has been proposed by avoiding the risk of divergence. In the proposed system the pixels of hyper-spectral images through the sequential perspective has been processed for capturing the sequence based data. The experimental result also shows that the proposed RNN has produced the improved F- score than the traditional deep learning methods.