A new image quality metric for image auto-denoising

Xiangfei Kong, Kuan Li, Qingxiong Yang, Liu Wenyin, Ming Hsuan Yang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

28 Citations (Scopus)

Abstract

This paper proposes a new non-reference image quality metric that can be adopted by the state-of-the-art image/video denoising algorithms for auto-denoising. The proposed metric is extremely simple and can be implemented in four lines of Matlab code. The basic assumption employed by the proposed metric is that the noise should be independent of the original image. A direct measurement of this dependence is, however, impractical due to the relatively low accuracy of existing denoising method. The proposed metric thus aims at maximizing the structure similarity between the input noisy image and the estimated image noise around homogeneous regions and the structure similarity between the input noisy image and the denoised image around highly-structured regions, and is computed as the linear correlation coefficient of the two corresponding structure similarity maps. Numerous experimental results demonstrate that the proposed metric not only outperforms the current state-of-the-art non-reference quality metric quantitatively and qualitatively, but also better maintains temporal coherence when used for video denoising.

Original languageEnglish
Title of host publicationProceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2888-2895
Number of pages8
ISBN (Print)9781479928392
DOIs
Publication statusPublished - 2013 Jan 1
Event2013 14th IEEE International Conference on Computer Vision, ICCV 2013 - Sydney, NSW, Australia
Duration: 2013 Dec 12013 Dec 8

Publication series

NameProceedings of the IEEE International Conference on Computer Vision

Other

Other2013 14th IEEE International Conference on Computer Vision, ICCV 2013
CountryAustralia
CitySydney, NSW
Period13/12/113/12/8

Fingerprint

Image quality

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Kong, X., Li, K., Yang, Q., Wenyin, L., & Yang, M. H. (2013). A new image quality metric for image auto-denoising. In Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013 (pp. 2888-2895). [6751470] (Proceedings of the IEEE International Conference on Computer Vision). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCV.2013.359
Kong, Xiangfei ; Li, Kuan ; Yang, Qingxiong ; Wenyin, Liu ; Yang, Ming Hsuan. / A new image quality metric for image auto-denoising. Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013. Institute of Electrical and Electronics Engineers Inc., 2013. pp. 2888-2895 (Proceedings of the IEEE International Conference on Computer Vision).
@inproceedings{150df94c853043a2930c4aae06ed6400,
title = "A new image quality metric for image auto-denoising",
abstract = "This paper proposes a new non-reference image quality metric that can be adopted by the state-of-the-art image/video denoising algorithms for auto-denoising. The proposed metric is extremely simple and can be implemented in four lines of Matlab code. The basic assumption employed by the proposed metric is that the noise should be independent of the original image. A direct measurement of this dependence is, however, impractical due to the relatively low accuracy of existing denoising method. The proposed metric thus aims at maximizing the structure similarity between the input noisy image and the estimated image noise around homogeneous regions and the structure similarity between the input noisy image and the denoised image around highly-structured regions, and is computed as the linear correlation coefficient of the two corresponding structure similarity maps. Numerous experimental results demonstrate that the proposed metric not only outperforms the current state-of-the-art non-reference quality metric quantitatively and qualitatively, but also better maintains temporal coherence when used for video denoising.",
author = "Xiangfei Kong and Kuan Li and Qingxiong Yang and Liu Wenyin and Yang, {Ming Hsuan}",
year = "2013",
month = "1",
day = "1",
doi = "10.1109/ICCV.2013.359",
language = "English",
isbn = "9781479928392",
series = "Proceedings of the IEEE International Conference on Computer Vision",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "2888--2895",
booktitle = "Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013",
address = "United States",

}

Kong, X, Li, K, Yang, Q, Wenyin, L & Yang, MH 2013, A new image quality metric for image auto-denoising. in Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013., 6751470, Proceedings of the IEEE International Conference on Computer Vision, Institute of Electrical and Electronics Engineers Inc., pp. 2888-2895, 2013 14th IEEE International Conference on Computer Vision, ICCV 2013, Sydney, NSW, Australia, 13/12/1. https://doi.org/10.1109/ICCV.2013.359

A new image quality metric for image auto-denoising. / Kong, Xiangfei; Li, Kuan; Yang, Qingxiong; Wenyin, Liu; Yang, Ming Hsuan.

Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013. Institute of Electrical and Electronics Engineers Inc., 2013. p. 2888-2895 6751470 (Proceedings of the IEEE International Conference on Computer Vision).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - A new image quality metric for image auto-denoising

AU - Kong, Xiangfei

AU - Li, Kuan

AU - Yang, Qingxiong

AU - Wenyin, Liu

AU - Yang, Ming Hsuan

PY - 2013/1/1

Y1 - 2013/1/1

N2 - This paper proposes a new non-reference image quality metric that can be adopted by the state-of-the-art image/video denoising algorithms for auto-denoising. The proposed metric is extremely simple and can be implemented in four lines of Matlab code. The basic assumption employed by the proposed metric is that the noise should be independent of the original image. A direct measurement of this dependence is, however, impractical due to the relatively low accuracy of existing denoising method. The proposed metric thus aims at maximizing the structure similarity between the input noisy image and the estimated image noise around homogeneous regions and the structure similarity between the input noisy image and the denoised image around highly-structured regions, and is computed as the linear correlation coefficient of the two corresponding structure similarity maps. Numerous experimental results demonstrate that the proposed metric not only outperforms the current state-of-the-art non-reference quality metric quantitatively and qualitatively, but also better maintains temporal coherence when used for video denoising.

AB - This paper proposes a new non-reference image quality metric that can be adopted by the state-of-the-art image/video denoising algorithms for auto-denoising. The proposed metric is extremely simple and can be implemented in four lines of Matlab code. The basic assumption employed by the proposed metric is that the noise should be independent of the original image. A direct measurement of this dependence is, however, impractical due to the relatively low accuracy of existing denoising method. The proposed metric thus aims at maximizing the structure similarity between the input noisy image and the estimated image noise around homogeneous regions and the structure similarity between the input noisy image and the denoised image around highly-structured regions, and is computed as the linear correlation coefficient of the two corresponding structure similarity maps. Numerous experimental results demonstrate that the proposed metric not only outperforms the current state-of-the-art non-reference quality metric quantitatively and qualitatively, but also better maintains temporal coherence when used for video denoising.

UR - http://www.scopus.com/inward/record.url?scp=84898782573&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84898782573&partnerID=8YFLogxK

U2 - 10.1109/ICCV.2013.359

DO - 10.1109/ICCV.2013.359

M3 - Conference contribution

AN - SCOPUS:84898782573

SN - 9781479928392

T3 - Proceedings of the IEEE International Conference on Computer Vision

SP - 2888

EP - 2895

BT - Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Kong X, Li K, Yang Q, Wenyin L, Yang MH. A new image quality metric for image auto-denoising. In Proceedings - 2013 IEEE International Conference on Computer Vision, ICCV 2013. Institute of Electrical and Electronics Engineers Inc. 2013. p. 2888-2895. 6751470. (Proceedings of the IEEE International Conference on Computer Vision). https://doi.org/10.1109/ICCV.2013.359