Picture of smart phone in human hand

World leading smartphone and mobile technology research at Strathclyde...

The Strathprints institutional repository is a digital archive of University of Strathclyde's Open Access research outputs. Strathprints provides access to thousands of Open Access research papers by University of Strathclyde researchers, including by Strathclyde researchers from the Department of Computer & Information Sciences involved in researching exciting new applications for mobile and smartphone technology. But the transformative application of mobile technologies is also the focus of research within disciplines as diverse as Electronic & Electrical Engineering, Marketing, Human Resource Management and Biomedical Enginering, among others.

Explore Strathclyde's Open Access research on smartphone technology now...

Fast implementation of singular spectrum analysis for effective feature extraction in hyperspectral imaging

Zabalza, Jaime and Ren, Jinchang and Wang, Zheng and Zhao, Huimin and Wang, Jun and Marshall, Stephen (2015) Fast implementation of singular spectrum analysis for effective feature extraction in hyperspectral imaging. IEEE Journal of Selected Topics in Earth Observation and Remote Sensing, 8 (6). pp. 2845-2853. ISSN 1939-1404

Text (Zabalza-etal-JSTEORS2014-effective-feature-extraction-in-hyperspectral-imaging)
Zabalza_etal_JSTEORS2014_effective_feature_extraction_in_hyperspectral_imaging.pdf - Accepted Author Manuscript

Download (1MB) | Preview


As a recent approach for time series analysis, singular spectrum analysis (SSA) has been successfully applied for feature extraction in hyperspectral imaging (HSI), leading to increased accuracy in pixel-based classification tasks. However, one of the main drawbacks of conventional SSA in HSI is the extremely high computational complexity, where each pixel requires individual and complete singular value decomposition (SVD) analyses. To address this issue, a fast implementation of SSA (F-SSA) is proposed for efficient feature extraction in HSI. Rather than applying pixel-based SVD as conventional SSA does, the fast implementation only needs one SVD applied to a representative pixel, i.e., either the median or the mean spectral vector of the HSI hypercube. The result of SVD is employed as a unique transform matrix for all the pixels within the hypercube. As demonstrated in experiments using two well-known publicly available data sets, almost identical results are produced by the fast implementation in terms of accuracy of data classification, using the support vector machine (SVM) classifier. However, the overall computational complexity has been significantly reduced.