A Novel Spatial-Spectral Framework for the Classification of Hyperspectral Satellite Imagery

Shriya T.P. Gupta and Sanjay K. Sahay

This repository contains code for the models presented in the paper.

The code base is built using the Spectral Python, Numpy and Scikit-Learn libraries. The GMLC based model is implemented through the Spectral Python library whereas the CNN based model is implemented using the Keras library. The code is provided in the form of a jupyter notebook which can be run on Google Colaboratory.

The experiments have been carried out as described in the paper for the following datasets:

1. Indian Pines dataset
2. Pavia University dataset

Citation

If you find this project useful in your research, please consider citing:

@inproceedings{gupta2020novel,
  title={A Novel Spatial-Spectral Framework for the Classification of Hyperspectral Satellite Imagery},
  author={Gupta, Shriya TP and Sahay, Sanjay K},
  booktitle={International Conference on Engineering Applications of Neural Networks},
  pages={227--239},
  year={2020},
  organization={Springer}
}