Sparse-Based Modeling of Hyperspectral Data

Rosalba Calvini; Alessandro Ulrici; Jose Manuel Amigo Rubio

doi:10.1016/B978-0-444-63638-6.00019-X

Sparse-Based Modeling of Hyperspectral Data

Rosalba Calvini, Alessandro Ulrici, Jose Manuel Amigo Rubio^*

^*Corresponding author for this work

Food Analytics and Biotechnology

Abstract

One of the main issues of hyperspectral imaging data is to unravel the relevant, yet overlapped, huge amount of information contained in the spatial and spectral dimensions. When dealing with the application of multivariate models in such high-dimensional data, sparsity can improve the interpretability and the performance of the model. In this chapter, we will introduce the exploration of hyperspectral images using a sparse version of the well-known principal component analysis method to demonstrate how the derived models can reveal very useful spectral zones. In particular, we will present two practical applications related to different issues: the separation among groups of homogeneous samples and the identification of outlier pixels in the spatial domain. For both case studies, guidance to the identification of the proper level of sparsity will be provided and, furthermore, we will show how sparsity can improve the chemical interpretation of the results.

Original language	English
Title of host publication	Data Handling in Science and Technology : Resolving Spectral Mixtures With Applications from Ultrafast Time-Resolved Spectroscopy to Super-Resolution Imaging, 2016
Editors	Cyril Ruckebusch
Number of pages	22
Volume	30
Publisher	Elsevier
Publication date	2016
Pages	613-634
Chapter	19
ISBN (Print)	9780444636386
DOIs	https://doi.org/10.1016/B978-0-444-63638-6.00019-X
Publication status	Published - 2016

Keywords

Hyperspectral imaging
Lasso
Sparse methods
Sparse PCA
Variable selection

Access to Document

10.1016/B978-0-444-63638-6.00019-X

Cite this

Calvini, R., Ulrici, A., & Amigo Rubio, J. M. (2016). Sparse-Based Modeling of Hyperspectral Data. In C. Ruckebusch (Ed.), Data Handling in Science and Technology: Resolving Spectral Mixtures With Applications from Ultrafast Time-Resolved Spectroscopy to Super-Resolution Imaging, 2016 (Vol. 30, pp. 613-634). Elsevier. https://doi.org/10.1016/B978-0-444-63638-6.00019-X

Sparse-Based Modeling of Hyperspectral Data. / Calvini, Rosalba; Ulrici, Alessandro; Amigo Rubio, Jose Manuel.

Data Handling in Science and Technology: Resolving Spectral Mixtures With Applications from Ultrafast Time-Resolved Spectroscopy to Super-Resolution Imaging, 2016. ed. / Cyril Ruckebusch. Vol. 30 Elsevier, 2016. p. 613-634.

Research output: Chapter in Book/Report/Conference proceeding › Book chapter › Research › peer-review

@inbook{2d367ca09e57470b9804e2dc6a984e85,

title = "Sparse-Based Modeling of Hyperspectral Data",

abstract = "One of the main issues of hyperspectral imaging data is to unravel the relevant, yet overlapped, huge amount of information contained in the spatial and spectral dimensions. When dealing with the application of multivariate models in such high-dimensional data, sparsity can improve the interpretability and the performance of the model. In this chapter, we will introduce the exploration of hyperspectral images using a sparse version of the well-known principal component analysis method to demonstrate how the derived models can reveal very useful spectral zones. In particular, we will present two practical applications related to different issues: the separation among groups of homogeneous samples and the identification of outlier pixels in the spatial domain. For both case studies, guidance to the identification of the proper level of sparsity will be provided and, furthermore, we will show how sparsity can improve the chemical interpretation of the results.",

keywords = "Hyperspectral imaging, Lasso, Sparse methods, Sparse PCA, Variable selection",

author = "Rosalba Calvini and Alessandro Ulrici and {Amigo Rubio}, {Jose Manuel}",

year = "2016",

doi = "10.1016/B978-0-444-63638-6.00019-X",

language = "English",

isbn = "9780444636386",

volume = "30",

pages = "613--634",

editor = "Ruckebusch, {Cyril }",

booktitle = "Data Handling in Science and Technology",

publisher = "Elsevier",

address = "Netherlands",

}

TY - CHAP

T1 - Sparse-Based Modeling of Hyperspectral Data

AU - Calvini, Rosalba

AU - Ulrici, Alessandro

AU - Amigo Rubio, Jose Manuel

PY - 2016

Y1 - 2016

N2 - One of the main issues of hyperspectral imaging data is to unravel the relevant, yet overlapped, huge amount of information contained in the spatial and spectral dimensions. When dealing with the application of multivariate models in such high-dimensional data, sparsity can improve the interpretability and the performance of the model. In this chapter, we will introduce the exploration of hyperspectral images using a sparse version of the well-known principal component analysis method to demonstrate how the derived models can reveal very useful spectral zones. In particular, we will present two practical applications related to different issues: the separation among groups of homogeneous samples and the identification of outlier pixels in the spatial domain. For both case studies, guidance to the identification of the proper level of sparsity will be provided and, furthermore, we will show how sparsity can improve the chemical interpretation of the results.

AB - One of the main issues of hyperspectral imaging data is to unravel the relevant, yet overlapped, huge amount of information contained in the spatial and spectral dimensions. When dealing with the application of multivariate models in such high-dimensional data, sparsity can improve the interpretability and the performance of the model. In this chapter, we will introduce the exploration of hyperspectral images using a sparse version of the well-known principal component analysis method to demonstrate how the derived models can reveal very useful spectral zones. In particular, we will present two practical applications related to different issues: the separation among groups of homogeneous samples and the identification of outlier pixels in the spatial domain. For both case studies, guidance to the identification of the proper level of sparsity will be provided and, furthermore, we will show how sparsity can improve the chemical interpretation of the results.

KW - Hyperspectral imaging

KW - Lasso

KW - Sparse methods

KW - Sparse PCA

KW - Variable selection

U2 - 10.1016/B978-0-444-63638-6.00019-X

DO - 10.1016/B978-0-444-63638-6.00019-X

M3 - Book chapter

AN - SCOPUS:84994410744

SN - 9780444636386

VL - 30

SP - 613

EP - 634

BT - Data Handling in Science and Technology

A2 - Ruckebusch, Cyril

PB - Elsevier

ER -

Sparse-Based Modeling of Hyperspectral Data

Abstract

Keywords

Access to Document

Fingerprint

Cite this