loading
Documents

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Rania Zaatour ; Sonia Bouzidi and Ezzeddine Zagrouba

Affiliation: University of Tunis El Manar, Tunisia

ISBN: 978-989-758-225-7

ISSN: 2184-4321

Keyword(s): Dimensionality Reduction, Principal Component Analysis (PCA), Local Fisher Discriminant Analysis (LFDA), Independent Component Analysis-based Band Selection, Extended MultiAttribute Profile (EMAP), Hyperspectral Image Classification.

Related Ontology Subjects/Areas/Topics: Computer Vision, Visualization and Computer Graphics ; Features Extraction ; Image and Video Analysis ; Image Formation and Preprocessing ; Multimodal and Multi-Sensor Models of Image Formation

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 ac curacies. (More)

PDF ImageFull Text

Download
CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.85.214.125

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
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: VISAPP, (VISIGRAPP 2017) ISBN 978-989-758-225-7, ISSN 2184-4321, pages 579-586. DOI: 10.5220/0006171305790586

@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: VISAPP, (VISIGRAPP 2017)},
year={2017},
pages={579-586},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006171305790586},
isbn={978-989-758-225-7},
}

TY - CONF

JO - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4 VISAPP: 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

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.