Home > Research > Publications & Outputs > Hyperspectral image denoising via minimizing th...

Electronic data

  • PSSV_NC

    Rights statement: This is the author’s version of a work that was accepted for publication in Neurocomputing. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Neurocomputing, 330, 2019 DOI: 10.1016/j.neucom.2018.11.039

    Accepted author manuscript, 5.79 MB, PDF document

    Available under license: CC BY-NC-ND

Links

Text available via DOI:

View graph of relations

Hyperspectral image denoising via minimizing the partial sum of singular values and superpixel segmentation

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Hyperspectral image denoising via minimizing the partial sum of singular values and superpixel segmentation. / Liu, Y.; Shan, C.; Gao, Q. et al.
In: Neurocomputing, Vol. 330, 22.02.2019, p. 465-482.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

APA

Vancouver

Liu Y, Shan C, Gao Q, Gao X, Han J, Cui R. Hyperspectral image denoising via minimizing the partial sum of singular values and superpixel segmentation. Neurocomputing. 2019 Feb 22;330:465-482. Epub 2018 Nov 20. doi: 10.1016/j.neucom.2018.11.039

Author

Liu, Y. ; Shan, C. ; Gao, Q. et al. / Hyperspectral image denoising via minimizing the partial sum of singular values and superpixel segmentation. In: Neurocomputing. 2019 ; Vol. 330. pp. 465-482.

Bibtex

@article{4bf1b566336749abac258f463a989e4c,
title = "Hyperspectral image denoising via minimizing the partial sum of singular values and superpixel segmentation",
abstract = "Hyperspectral images (HSIs) are often corrupted by noise during the acquisition process, thus degrading the HSI's discriminative capability significantly. Therefore, HSI denoising becomes an essential preprocess step before application. This paper proposes a new HSI denoising approach connecting Partial Sum of Singular Values (PSSV) and superpixels segmentation named as SS-PSSV, which can remove the noise effectively. Based on the fact that there is a high correlation between different bands of the same signal, it is easy to know the property of low rank between distinct bands. To this end, PSSV is utilized, and in order to better tap the low-rank attribute of pixels, we introduce the superpixels segmentation method, which allows pixels in HSI with high similarity to be grouped in the same sub-block as much as possible. Extensive experiments display that the proposed algorithm outperforms the state-of-the-art. {\textcopyright} 2018 Elsevier B.V.",
keywords = "Denoising, Hyperspectral images, PSSV, Superpixel segmentation, Hyperspectral imaging, Image segmentation, Pixels, Spectroscopy, Superpixels, Acquisition process, De-noising, Denoising approach, Singular values, State of the art, Superpixel segmentations, Superpixels segmentations, Image denoising, article, noise",
author = "Y. Liu and C. Shan and Q. Gao and X. Gao and J. Han and R. Cui",
note = "This is the author{\textquoteright}s version of a work that was accepted for publication in Neurocomputing. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Neurocomputing, 330, 2019 DOI: 10.1016/j.neucom.2018.11.039",
year = "2019",
month = feb,
day = "22",
doi = "10.1016/j.neucom.2018.11.039",
language = "English",
volume = "330",
pages = "465--482",
journal = "Neurocomputing",
issn = "0925-2312",
publisher = "Elsevier Science B.V.",

}

RIS

TY - JOUR

T1 - Hyperspectral image denoising via minimizing the partial sum of singular values and superpixel segmentation

AU - Liu, Y.

AU - Shan, C.

AU - Gao, Q.

AU - Gao, X.

AU - Han, J.

AU - Cui, R.

N1 - This is the author’s version of a work that was accepted for publication in Neurocomputing. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Neurocomputing, 330, 2019 DOI: 10.1016/j.neucom.2018.11.039

PY - 2019/2/22

Y1 - 2019/2/22

N2 - Hyperspectral images (HSIs) are often corrupted by noise during the acquisition process, thus degrading the HSI's discriminative capability significantly. Therefore, HSI denoising becomes an essential preprocess step before application. This paper proposes a new HSI denoising approach connecting Partial Sum of Singular Values (PSSV) and superpixels segmentation named as SS-PSSV, which can remove the noise effectively. Based on the fact that there is a high correlation between different bands of the same signal, it is easy to know the property of low rank between distinct bands. To this end, PSSV is utilized, and in order to better tap the low-rank attribute of pixels, we introduce the superpixels segmentation method, which allows pixels in HSI with high similarity to be grouped in the same sub-block as much as possible. Extensive experiments display that the proposed algorithm outperforms the state-of-the-art. © 2018 Elsevier B.V.

AB - Hyperspectral images (HSIs) are often corrupted by noise during the acquisition process, thus degrading the HSI's discriminative capability significantly. Therefore, HSI denoising becomes an essential preprocess step before application. This paper proposes a new HSI denoising approach connecting Partial Sum of Singular Values (PSSV) and superpixels segmentation named as SS-PSSV, which can remove the noise effectively. Based on the fact that there is a high correlation between different bands of the same signal, it is easy to know the property of low rank between distinct bands. To this end, PSSV is utilized, and in order to better tap the low-rank attribute of pixels, we introduce the superpixels segmentation method, which allows pixels in HSI with high similarity to be grouped in the same sub-block as much as possible. Extensive experiments display that the proposed algorithm outperforms the state-of-the-art. © 2018 Elsevier B.V.

KW - Denoising

KW - Hyperspectral images

KW - PSSV

KW - Superpixel segmentation

KW - Hyperspectral imaging

KW - Image segmentation

KW - Pixels

KW - Spectroscopy

KW - Superpixels

KW - Acquisition process

KW - De-noising

KW - Denoising approach

KW - Singular values

KW - State of the art

KW - Superpixel segmentations

KW - Superpixels segmentations

KW - Image denoising

KW - article

KW - noise

U2 - 10.1016/j.neucom.2018.11.039

DO - 10.1016/j.neucom.2018.11.039

M3 - Journal article

VL - 330

SP - 465

EP - 482

JO - Neurocomputing

JF - Neurocomputing

SN - 0925-2312

ER -