Singular spectrum analysis for effective feature extraction in hyperspectral imaging

Zabalza, Jaime and Ren, Jinchang and Wang, Zheng and Marshall, Stephen and Wang, Jun (2014) Singular spectrum analysis for effective feature extraction in hyperspectral imaging. IEEE Geoscience and Remote Sensing Letters, 11 (11). pp. 1886-1890. ISSN 1545-598X (https://doi.org/10.1109/LGRS.2014.2312754)

[thumbnail of 1D-SSA]
Preview
 PDF. Filename: 1D_SSA.pdf
Preprint
Download (970kB)| Preview

Abstract

As a very recent technique for time series analysis, Singular Spectrum Analysis (SSA) has been applied in many diverse areas, where an original 1D signal can be decomposed into a sum of components including varying trends, oscillations and noise. Considering pixel based spectral profiles as 1D signals, in this paper, SSA has been applied in Hyperspectral Imaging (HSI) for effective feature extraction. By removing noisy components in extracting the features, the discriminating ability of the features has been much improved. Experiments show that this SSA approach supersedes the Empirical Mode Decomposition (EMD) technique from which our work was originally inspired, where improved results in effective data classification using Support Vector Machine (SVM) are also reported.

ORCID iDs

Zabalza, Jaime ORCID logoORCID: https://orcid.org/0000-0002-0634-1725, Ren, Jinchang ORCID logoORCID: https://orcid.org/0000-0001-6116-3194, Wang, Zheng, Marshall, Stephen ORCID logoORCID: https://orcid.org/0000-0001-7079-5628 and Wang, Jun;
CORE (COnnecting REpositories)