HYPERSPECTRAL IMAGE DENOISING WITH LOG-BASED ROBUST PCA

Yang Liu; Qian Zhang; Yongyong Chen; Qiang Cheng; Chong Peng

doi:10.1109/ICIP42928.2021.9506050

HYPERSPECTRAL IMAGE DENOISING WITH LOG-BASED ROBUST PCA

Yang Liu, Qian Zhang, Yongyong Chen, Qiang Cheng, Chong Peng

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

8 Scopus citations

Abstract

It is a challenging task to remove heavy and mixed types of noise from Hyperspectral images (HSIs). In this paper, we propose a novel nonconvex approach to RPCA for HSI denoising, which adopts the log-determinant rank approximation and a novel `_2,log norm, to restrict the low-rank or column-wise sparse properties for the component matrices, respectively. For the `_2,log-regularized shrinkage problem, we develop an efficient, closed-form solution, which is named `_2,log-shrinkage operator, which can be generally used in other problems. Extensive experiments on both simulated and real HSIs demonstrate the effectiveness of the proposed method in denoising HSIs.

Original language	English
Title of host publication	2021 IEEE International Conference on Image Processing, ICIP 2021 - Proceedings
Pages	1634-1638
Number of pages	5
ISBN (Electronic)	9781665441155
DOIs	https://doi.org/10.1109/ICIP42928.2021.9506050
State	Published - 2021
Event	2021 IEEE International Conference on Image Processing, ICIP 2021 - Anchorage, United States Duration: Sep 19 2021 → Sep 22 2021

Publication series

Name	Proceedings - International Conference on Image Processing, ICIP
Volume	2021-September
ISSN (Print)	1522-4880

Conference

Conference	2021 IEEE International Conference on Image Processing, ICIP 2021
Country/Territory	United States
City	Anchorage
Period	9/19/21 → 9/22/21

Bibliographical note

Publisher Copyright:
© 2021 IEEE

Funding

This work is supported by National Natural Foundation of China (NSFC) under grant 61806106, and Shandong Provincial Natural Science Foundation, China under grant ZR2019QF009. C.P. is the corresponding author (email: [email protected]).

Funders	Funder number
National Natural Science Foundation of China (NSFC)	61806106
National Natural Science Foundation of China (NSFC)
Natural Science Foundation of Shandong Province	ZR2019QF009
Natural Science Foundation of Shandong Province

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition
Signal Processing

Access to Document

10.1109/ICIP42928.2021.9506050

Cite this

@inproceedings{4e42ce7f974543ae99d0173b7e53a932,

title = "HYPERSPECTRAL IMAGE DENOISING WITH LOG-BASED ROBUST PCA",

abstract = "It is a challenging task to remove heavy and mixed types of noise from Hyperspectral images (HSIs). In this paper, we propose a novel nonconvex approach to RPCA for HSI denoising, which adopts the log-determinant rank approximation and a novel `2,log norm, to restrict the low-rank or column-wise sparse properties for the component matrices, respectively. For the `2,log-regularized shrinkage problem, we develop an efficient, closed-form solution, which is named `2,log-shrinkage operator, which can be generally used in other problems. Extensive experiments on both simulated and real HSIs demonstrate the effectiveness of the proposed method in denoising HSIs.",

author = "Yang Liu and Qian Zhang and Yongyong Chen and Qiang Cheng and Chong Peng",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE; 2021 IEEE International Conference on Image Processing, ICIP 2021 ; Conference date: 19-09-2021 Through 22-09-2021",

year = "2021",

doi = "10.1109/ICIP42928.2021.9506050",

language = "English",

series = "Proceedings - International Conference on Image Processing, ICIP",

pages = "1634--1638",

booktitle = "2021 IEEE International Conference on Image Processing, ICIP 2021 - Proceedings",

}

Liu, Y, Zhang, Q, Chen, Y, Cheng, Q & Peng, C 2021, HYPERSPECTRAL IMAGE DENOISING WITH LOG-BASED ROBUST PCA. in 2021 IEEE International Conference on Image Processing, ICIP 2021 - Proceedings. Proceedings - International Conference on Image Processing, ICIP, vol. 2021-September, pp. 1634-1638, 2021 IEEE International Conference on Image Processing, ICIP 2021, Anchorage, United States, 9/19/21. https://doi.org/10.1109/ICIP42928.2021.9506050

HYPERSPECTRAL IMAGE DENOISING WITH LOG-BASED ROBUST PCA. / Liu, Yang; Zhang, Qian; Chen, Yongyong et al.
2021 IEEE International Conference on Image Processing, ICIP 2021 - Proceedings. 2021. p. 1634-1638 (Proceedings - International Conference on Image Processing, ICIP; Vol. 2021-September).

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

TY - GEN

T1 - HYPERSPECTRAL IMAGE DENOISING WITH LOG-BASED ROBUST PCA

AU - Liu, Yang

AU - Zhang, Qian

AU - Chen, Yongyong

AU - Cheng, Qiang

AU - Peng, Chong

PY - 2021

Y1 - 2021

N2 - It is a challenging task to remove heavy and mixed types of noise from Hyperspectral images (HSIs). In this paper, we propose a novel nonconvex approach to RPCA for HSI denoising, which adopts the log-determinant rank approximation and a novel `2,log norm, to restrict the low-rank or column-wise sparse properties for the component matrices, respectively. For the `2,log-regularized shrinkage problem, we develop an efficient, closed-form solution, which is named `2,log-shrinkage operator, which can be generally used in other problems. Extensive experiments on both simulated and real HSIs demonstrate the effectiveness of the proposed method in denoising HSIs.

AB - It is a challenging task to remove heavy and mixed types of noise from Hyperspectral images (HSIs). In this paper, we propose a novel nonconvex approach to RPCA for HSI denoising, which adopts the log-determinant rank approximation and a novel `2,log norm, to restrict the low-rank or column-wise sparse properties for the component matrices, respectively. For the `2,log-regularized shrinkage problem, we develop an efficient, closed-form solution, which is named `2,log-shrinkage operator, which can be generally used in other problems. Extensive experiments on both simulated and real HSIs demonstrate the effectiveness of the proposed method in denoising HSIs.

UR - http://www.scopus.com/inward/record.url?scp=85125562095&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85125562095&partnerID=8YFLogxK

U2 - 10.1109/ICIP42928.2021.9506050

DO - 10.1109/ICIP42928.2021.9506050

M3 - Conference contribution

AN - SCOPUS:85125562095

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 1634

EP - 1638

BT - 2021 IEEE International Conference on Image Processing, ICIP 2021 - Proceedings

T2 - 2021 IEEE International Conference on Image Processing, ICIP 2021

Y2 - 19 September 2021 through 22 September 2021

ER -

HYPERSPECTRAL IMAGE DENOISING WITH LOG-BASED ROBUST PCA

Abstract

Publication series

Conference

Bibliographical note

Funding

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this