A4 Conference proceedings

Unsupervised Multi-manifold Classification of Hyperspectral Remote Sensing Images with Contractive Autoencoder


Open Access publication

Publication Details
Authors: Hassanzadeh Aidin, Kaarna Arto, Kauranne Tuomo
Publisher: Springer Verlag (Germany): Series
Publication year: 2017
Language: English
Related Journal or Series Information: Lecture Notes in Computer Science
Title of parent publication: Scandinavian Conference on Image Analysis
Journal acronym: LNCS
Volume number: 10270
Start page: 169
End page: 180
Number of pages: 12
ISBN: 978-3-319-59128-5
eISBN: 978-3-319-59129-2
ISSN: 0302-9743
eISSN: 1611-3349
JUFO-Level of this publication: 1
Open Access: Open Access publication

Abstract

Unsupervised classification is a crucial step in remote sensing hyperspectral image analysis where producing training labelled data is a laborious task. Hyperspectral imagery is basically of high-dimensions and indeed dimensionality reduction is considered a vital step in its preprocessing chain. A majority of conventional dimensionality reduction techniques rely on single global manifold assumptions and they can not handle data coming from a multi-manifold structure. In this paper, the unsupervised classification of hyperspectral imaging is addressed through a multi-manifold learning framework. To this end, this paper proposes a Contractive Autoencoder based multi-manifold spectral clustering algorithm for unsupervised classification of hyperspectral imagery. The proposed algorithm follows the same outline as the general multi-manifold clustering but exploits contractive autoencoder for tangent space estimation. We evaluate the proposed algorithm with two benchmark hyperspectral datasets, Salinas and Pavia Center Scene. The experimental results show the improvements made by the proposed method with respect to the conventional multi-manifold clustering based on local PCA and the basic autoencoder.


Last updated on 2018-19-10 at 07:55