Singular spectrum analysis for effective noise removal and improved data classification in hyperspectral imaging

Jaime Zabalza; Jinchang Ren; Stephen Marshall

doi:10.1109/WHISPERS.2014.8077583

Singular spectrum analysis for effective noise removal and improved data classification in hyperspectral imaging

Jaime Zabalza, Jinchang Ren, Stephen Marshall

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

5 Citations (Scopus)

31 Downloads (Pure)

Abstract

Based on the well-known Singular Value Decomposition (SVD), Singular Spectrum Analysis (SSA) has been widely employed for time series analysis and forecasting in decomposing the original series into a sum of components. As such, each 1-D signal can be represented with varying trend, oscillations and noise for easy enhancement of the signal. Taking each spectral signature in Hyperspectral Imaging (HSI) as a 1-D signal, SSA has been successfully applied for signal decomposition and noise removal whilst preserving the discriminating power of the spectral profile. Two well-known remote sensing datasets for land cover analysis, AVIRIS 92AV3C and Salinas C, are used for performance assessment. Experimental results using Support Vector Machine (SVM) in pixel based classification have indicated that SSA has suppressed the noise in significantly improving the classification accuracy.

Original language	English
Title of host publication	2014 6th Workshop on Hyperspectral Image and Signal Processing
Subtitle of host publication	Evolution in Remote Sensing (WHISPERS)
Place of Publication	Piscataway, NJ
Publisher	IEEE
Number of pages	4
ISBN (Electronic)	9781467390125
DOIs	https://doi.org/10.1109/WHISPERS.2014.8077583
Publication status	Published - 26 Oct 2017
Event	2014 6th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS) - Lausanne, Switzerland Duration: 24 Jun 2014 → 27 Jun 2014

Conference

Conference	2014 6th Workshop on Hyperspectral Image and Signal Processing
Country/Territory	Switzerland
City	Lausanne
Period	24/06/14 → 27/06/14

Keywords

hyperspectral imaging
feature extraction
spectral analysis
support vector machines
image reconstruction
matrix decomposition

Access to Document

10.1109/WHISPERS.2014.8077583

Zabalza-etal-Whispers2014-Singular-spectrum-analysis-for-effective-noise-removalAccepted author manuscript, 426 KB

Cite this

@inproceedings{cb7db82b59b84f60adca3cbc9b320ec7,

title = "Singular spectrum analysis for effective noise removal and improved data classification in hyperspectral imaging",

abstract = "Based on the well-known Singular Value Decomposition (SVD), Singular Spectrum Analysis (SSA) has been widely employed for time series analysis and forecasting in decomposing the original series into a sum of components. As such, each 1-D signal can be represented with varying trend, oscillations and noise for easy enhancement of the signal. Taking each spectral signature in Hyperspectral Imaging (HSI) as a 1-D signal, SSA has been successfully applied for signal decomposition and noise removal whilst preserving the discriminating power of the spectral profile. Two well-known remote sensing datasets for land cover analysis, AVIRIS 92AV3C and Salinas C, are used for performance assessment. Experimental results using Support Vector Machine (SVM) in pixel based classification have indicated that SSA has suppressed the noise in significantly improving the classification accuracy.",

keywords = "hyperspectral imaging, feature extraction, spectral analysis, support vector machines, image reconstruction, matrix decomposition",

author = "Jaime Zabalza and Jinchang Ren and Stephen Marshall",

note = "{\textcopyright} 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.; 2014 6th Workshop on Hyperspectral Image and Signal Processing : Evolution in Remote Sensing (WHISPERS) ; Conference date: 24-06-2014 Through 27-06-2014",

year = "2017",

month = oct,

day = "26",

doi = "10.1109/WHISPERS.2014.8077583",

language = "English",

booktitle = "2014 6th Workshop on Hyperspectral Image and Signal Processing",

publisher = "IEEE",

}

Zabalza, J, Ren, J & Marshall, S 2017, Singular spectrum analysis for effective noise removal and improved data classification in hyperspectral imaging. in 2014 6th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS). IEEE, Piscataway, NJ, 2014 6th Workshop on Hyperspectral Image and Signal Processing, Lausanne, Switzerland, 24/06/14. https://doi.org/10.1109/WHISPERS.2014.8077583

Singular spectrum analysis for effective noise removal and improved data classification in hyperspectral imaging. / Zabalza, Jaime; Ren, Jinchang; Marshall, Stephen.
2014 6th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS). Piscataway, NJ: IEEE, 2017.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

TY - GEN

T1 - Singular spectrum analysis for effective noise removal and improved data classification in hyperspectral imaging

AU - Zabalza, Jaime

AU - Ren, Jinchang

AU - Marshall, Stephen

N1 - © 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

PY - 2017/10/26

Y1 - 2017/10/26

N2 - Based on the well-known Singular Value Decomposition (SVD), Singular Spectrum Analysis (SSA) has been widely employed for time series analysis and forecasting in decomposing the original series into a sum of components. As such, each 1-D signal can be represented with varying trend, oscillations and noise for easy enhancement of the signal. Taking each spectral signature in Hyperspectral Imaging (HSI) as a 1-D signal, SSA has been successfully applied for signal decomposition and noise removal whilst preserving the discriminating power of the spectral profile. Two well-known remote sensing datasets for land cover analysis, AVIRIS 92AV3C and Salinas C, are used for performance assessment. Experimental results using Support Vector Machine (SVM) in pixel based classification have indicated that SSA has suppressed the noise in significantly improving the classification accuracy.

AB - Based on the well-known Singular Value Decomposition (SVD), Singular Spectrum Analysis (SSA) has been widely employed for time series analysis and forecasting in decomposing the original series into a sum of components. As such, each 1-D signal can be represented with varying trend, oscillations and noise for easy enhancement of the signal. Taking each spectral signature in Hyperspectral Imaging (HSI) as a 1-D signal, SSA has been successfully applied for signal decomposition and noise removal whilst preserving the discriminating power of the spectral profile. Two well-known remote sensing datasets for land cover analysis, AVIRIS 92AV3C and Salinas C, are used for performance assessment. Experimental results using Support Vector Machine (SVM) in pixel based classification have indicated that SSA has suppressed the noise in significantly improving the classification accuracy.

KW - hyperspectral imaging

KW - feature extraction

KW - spectral analysis

KW - support vector machines

KW - image reconstruction

KW - matrix decomposition

UR - https://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=8055034

U2 - 10.1109/WHISPERS.2014.8077583

DO - 10.1109/WHISPERS.2014.8077583

M3 - Conference contribution book

BT - 2014 6th Workshop on Hyperspectral Image and Signal Processing

PB - IEEE

CY - Piscataway, NJ

T2 - 2014 6th Workshop on Hyperspectral Image and Signal Processing

Y2 - 24 June 2014 through 27 June 2014

ER -

Singular spectrum analysis for effective noise removal and improved data classification in hyperspectral imaging

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this