A no-reference perceptual blur metric using histogram of gradient profile sharpness

Luhong Liang; Jianhua Chen; Siwei Ma; Debin Zhao; Wen Gao

doi:10.1109/ICIP.2009.5413545

A no-reference perceptual blur metric using histogram of gradient profile sharpness

Luhong Liang^*
, Jianhua Chen
, Siwei Ma
, Debin Zhao
, Wen Gao

^*Corresponding author for this work

Faculty of Computing

Chinese Academy of Sciences
CAS - Institute of Computing Technology
University of Chinese Academy of Sciences
Peking University

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

29 Scopus citations

Abstract

No-reference measurement of blurring artifacts in images is a challenging problem in image quality assessment field. One of the difficulties is that the inherently blurry regions in some natural images may disturb the evaluation of blurring artifacts. In this paper, we study the image gradients along local image structures and propose a new perceptual blur metric to deal with the above problem. The gradient profile sharpness of image edge is efficiently calculated along horizontal or vertical direction. Then the sharpness distribution histogram rectified by just noticeable distortion (JND) threshold is used to evaluate the blurring artifacts and assess the image quality. Experimental results show that the proposed method can achieve good image quality prediction performance.

Original language	English
Title of host publication	2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings
Publisher	IEEE Computer Society
Pages	4369-4372
Number of pages	4
ISBN (Print)	9781424456543
DOIs	https://doi.org/10.1109/ICIP.2009.5413545
State	Published - 2009
Event	2009 IEEE International Conference on Image Processing, ICIP 2009 - Cairo, Egypt Duration: 7 Nov 2009 → 10 Nov 2009

Publication series

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

Conference

Conference	2009 IEEE International Conference on Image Processing, ICIP 2009
Country/Territory	Egypt
City	Cairo
Period	7/11/09 → 10/11/09

Keywords

Blur metric
Gradient profile
Image quality assessment
Just noticeable distortion

Access to Document

10.1109/ICIP.2009.5413545

Cite this

Liang, L., Chen, J., Ma, S., Zhao, D., & Gao, W. (2009). A no-reference perceptual blur metric using histogram of gradient profile sharpness. In 2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings (pp. 4369-4372). Article 5413545 (Proceedings - International Conference on Image Processing, ICIP). IEEE Computer Society. https://doi.org/10.1109/ICIP.2009.5413545

@inproceedings{973b9aec5cbc4475b1cfea39819b5eff,

title = "A no-reference perceptual blur metric using histogram of gradient profile sharpness",

abstract = "No-reference measurement of blurring artifacts in images is a challenging problem in image quality assessment field. One of the difficulties is that the inherently blurry regions in some natural images may disturb the evaluation of blurring artifacts. In this paper, we study the image gradients along local image structures and propose a new perceptual blur metric to deal with the above problem. The gradient profile sharpness of image edge is efficiently calculated along horizontal or vertical direction. Then the sharpness distribution histogram rectified by just noticeable distortion (JND) threshold is used to evaluate the blurring artifacts and assess the image quality. Experimental results show that the proposed method can achieve good image quality prediction performance.",

keywords = "Blur metric, Gradient profile, Image quality assessment, Just noticeable distortion",

author = "Luhong Liang and Jianhua Chen and Siwei Ma and Debin Zhao and Wen Gao",

year = "2009",

doi = "10.1109/ICIP.2009.5413545",

language = "英语",

isbn = "9781424456543",

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

publisher = "IEEE Computer Society",

pages = "4369--4372",

booktitle = "2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings",

address = "美国",

note = "2009 IEEE International Conference on Image Processing, ICIP 2009 ; Conference date: 07-11-2009 Through 10-11-2009",

}

Liang, L, Chen, J, Ma, S, Zhao, D & Gao, W 2009, A no-reference perceptual blur metric using histogram of gradient profile sharpness. in 2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings., 5413545, Proceedings - International Conference on Image Processing, ICIP, IEEE Computer Society, pp. 4369-4372, 2009 IEEE International Conference on Image Processing, ICIP 2009, Cairo, Egypt, 7/11/09. https://doi.org/10.1109/ICIP.2009.5413545

A no-reference perceptual blur metric using histogram of gradient profile sharpness. / Liang, Luhong; Chen, Jianhua; Ma, Siwei et al.
2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings. IEEE Computer Society, 2009. p. 4369-4372 5413545 (Proceedings - International Conference on Image Processing, ICIP).

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

TY - GEN

T1 - A no-reference perceptual blur metric using histogram of gradient profile sharpness

AU - Liang, Luhong

AU - Chen, Jianhua

AU - Ma, Siwei

AU - Zhao, Debin

AU - Gao, Wen

PY - 2009

Y1 - 2009

N2 - No-reference measurement of blurring artifacts in images is a challenging problem in image quality assessment field. One of the difficulties is that the inherently blurry regions in some natural images may disturb the evaluation of blurring artifacts. In this paper, we study the image gradients along local image structures and propose a new perceptual blur metric to deal with the above problem. The gradient profile sharpness of image edge is efficiently calculated along horizontal or vertical direction. Then the sharpness distribution histogram rectified by just noticeable distortion (JND) threshold is used to evaluate the blurring artifacts and assess the image quality. Experimental results show that the proposed method can achieve good image quality prediction performance.

AB - No-reference measurement of blurring artifacts in images is a challenging problem in image quality assessment field. One of the difficulties is that the inherently blurry regions in some natural images may disturb the evaluation of blurring artifacts. In this paper, we study the image gradients along local image structures and propose a new perceptual blur metric to deal with the above problem. The gradient profile sharpness of image edge is efficiently calculated along horizontal or vertical direction. Then the sharpness distribution histogram rectified by just noticeable distortion (JND) threshold is used to evaluate the blurring artifacts and assess the image quality. Experimental results show that the proposed method can achieve good image quality prediction performance.

KW - Blur metric

KW - Gradient profile

KW - Image quality assessment

KW - Just noticeable distortion

UR - https://www.scopus.com/pages/publications/77951947395

U2 - 10.1109/ICIP.2009.5413545

DO - 10.1109/ICIP.2009.5413545

M3 - 会议稿件

AN - SCOPUS:77951947395

SN - 9781424456543

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 4369

EP - 4372

BT - 2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings

PB - IEEE Computer Society

T2 - 2009 IEEE International Conference on Image Processing, ICIP 2009

Y2 - 7 November 2009 through 10 November 2009

ER -

A no-reference perceptual blur metric using histogram of gradient profile sharpness

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this