Robust L1 PCA and Its Application in Image Denoising

Junbin Gao; Paul Hing Kwan; Yi Guo

doi:10.1117/12.774719

Robust L1 PCA and Its Application in Image Denoising

Junbin Gao
, Paul Hing Kwan
, Yi Guo

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

Abstract

The so-called robust L1 PCA was introduced in our recent work [1] based on the L1 noise assumption. Due to the heavy tail characteristics of the L1 distribution, the proposed model has been proved much more robust against data outliers. In this paper, we further demonstrate how the learned robust L1 PCA model can be used to denoise image data.

Original language	English
Title of host publication	Proceedings of MIPPR 2007: Automatic Target Recognition and Image Analysis and Multispectral Image Acquisition
Editors	Zhang T, Nardell CA, Smith DD, Lu H
Place of Publication	Washington, United States of America
Publisher	International Society for Optical Engineering (SPIE)
Volume	6786
ISBN (Print)	9780819469502
DOIs	https://doi.org/10.1117/12.774719
Publication status	Published - 2007
Event	MIPPR 2007: Automatic Target Recognition and Image Analysis and Multispectral Image Acquisition - Wuhan, China Duration: 15 Nov 2007 → 17 Nov 2007

Conference

Conference	MIPPR 2007: Automatic Target Recognition and Image Analysis and Multispectral Image Acquisition
City	Wuhan, China
Period	15/11/07 → 17/11/07

Keywords

Pattern Recognition and Data Mining

Access to Document

10.1117/12.774719

https://hdl.handle.net/1959.11/5808

Handle.net

Persistent link

Cite this

@inproceedings{73f4f392a7464d37b31feb0519733d36,

title = "Robust L1 PCA and Its Application in Image Denoising",

abstract = "The so-called robust L1 PCA was introduced in our recent work [1] based on the L1 noise assumption. Due to the heavy tail characteristics of the L1 distribution, the proposed model has been proved much more robust against data outliers. In this paper, we further demonstrate how the learned robust L1 PCA model can be used to denoise image data.",

keywords = "Pattern Recognition and Data Mining",

author = "Junbin Gao and Kwan, \{Paul Hing\} and Yi Guo",

year = "2007",

doi = "10.1117/12.774719",

language = "English",

isbn = "9780819469502",

volume = "6786",

editor = "Zhang T and Nardell CA and Smith DD and Lu H",

booktitle = "Proceedings of MIPPR 2007: Automatic Target Recognition and Image Analysis and Multispectral Image Acquisition",

publisher = "International Society for Optical Engineering (SPIE)",

note = "MIPPR 2007: Automatic Target Recognition and Image Analysis and Multispectral Image Acquisition ; Conference date: 15-11-2007 Through 17-11-2007",

}

Gao, J, Kwan, PH & Guo, Y 2007, Robust L1 PCA and Its Application in Image Denoising. in Z T, N CA, S DD & L H (eds), Proceedings of MIPPR 2007: Automatic Target Recognition and Image Analysis and Multispectral Image Acquisition. vol. 6786, International Society for Optical Engineering (SPIE), Washington, United States of America, MIPPR 2007: Automatic Target Recognition and Image Analysis and Multispectral Image Acquisition, Wuhan, China, 15/11/07. https://doi.org/10.1117/12.774719

Robust L1 PCA and Its Application in Image Denoising. / Gao, Junbin; Kwan, Paul Hing; Guo, Yi.
Proceedings of MIPPR 2007: Automatic Target Recognition and Image Analysis and Multispectral Image Acquisition. ed. / Zhang T; Nardell CA; Smith DD; Lu H. Vol. 6786 Washington, United States of America: International Society for Optical Engineering (SPIE), 2007.

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

TY - GEN

T1 - Robust L1 PCA and Its Application in Image Denoising

AU - Gao, Junbin

AU - Kwan, Paul Hing

AU - Guo, Yi

PY - 2007

Y1 - 2007

N2 - The so-called robust L1 PCA was introduced in our recent work [1] based on the L1 noise assumption. Due to the heavy tail characteristics of the L1 distribution, the proposed model has been proved much more robust against data outliers. In this paper, we further demonstrate how the learned robust L1 PCA model can be used to denoise image data.

AB - The so-called robust L1 PCA was introduced in our recent work [1] based on the L1 noise assumption. Due to the heavy tail characteristics of the L1 distribution, the proposed model has been proved much more robust against data outliers. In this paper, we further demonstrate how the learned robust L1 PCA model can be used to denoise image data.

KW - Pattern Recognition and Data Mining

U2 - 10.1117/12.774719

DO - 10.1117/12.774719

M3 - Conference contribution

SN - 9780819469502

VL - 6786

BT - Proceedings of MIPPR 2007: Automatic Target Recognition and Image Analysis and Multispectral Image Acquisition

A2 - T, Zhang

A2 - CA, Nardell

A2 - DD, Smith

A2 - H, Lu

PB - International Society for Optical Engineering (SPIE)

CY - Washington, United States of America

T2 - MIPPR 2007: Automatic Target Recognition and Image Analysis and Multispectral Image Acquisition

Y2 - 15 November 2007 through 17 November 2007

ER -

Robust L1 PCA and Its Application in Image Denoising

Abstract

Conference

Keywords

Access to Document

Handle.net

Fingerprint

Cite this