Impact of Feature Extraction and Feature Selection Techniques on Extended Attribute Profile-based Hyperspectral Image Classification

Rania Zaatour, Sonia Bouzidi, Ezzeddine Zagrouba

2017

Abstract

Extended multiattribute profiles (EMAPs) are morphological profiles built on the features of a HSI reduced using a Feature Extraction (FE) technique, Principal Component Analysis (PCA) in most cases. In this paper, we propose to replace PCA with other Dimensionality Reduction (DR) techniques. First, we replace it with Local Fisher Discriminant Analysis (LFDA), a supervised locality preserving DR method. Second, we replace it with two Feature Selection (FS) techniques: \textit{ICAbs}, an Independent Component Analysis (ICA) based band selection, and its modified version that we propose in this article and which we are calling \textit{mICAbs}. In the experimental part of this paper, we compare the accuracies of classifying the sparse representations of the EMAPs built on features obtained using each of the aforementioned DR techniques. Our experiments reveal that LFDA gives, amongst all, the best classification accuracies. Besides, our proposed modification gives comparable to higher accuracies.

Paper Citation

in Harvard Style

Zaatour R., Bouzidi S. and Zagrouba E. (2017). Impact of Feature Extraction and Feature Selection Techniques on Extended Attribute Profile-based Hyperspectral Image Classification . In Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2017) ISBN 978-989-758-225-7, pages 579-586. DOI: 10.5220/0006171305790586

in Bibtex Style

@conference{visapp17,
author={Rania Zaatour and Sonia Bouzidi and Ezzeddine Zagrouba},
title={Impact of Feature Extraction and Feature Selection Techniques on Extended Attribute Profile-based Hyperspectral Image Classification},
booktitle={Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2017)},
year={2017},
pages={579-586},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006171305790586},
isbn={978-989-758-225-7},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2017)
TI - Impact of Feature Extraction and Feature Selection Techniques on Extended Attribute Profile-based Hyperspectral Image Classification
SN - 978-989-758-225-7
AU - Zaatour R.
AU - Bouzidi S.
AU - Zagrouba E.
PY - 2017
SP - 579
EP - 586
DO - 10.5220/0006171305790586