A perceptual blurring metric for compressed video

Jun Xia; Yue Shi; Y. Ling; C. Teunissen; I.E.J. Heynderickx

doi:10.1109/ICISE.2009.133

A perceptual blurring metric for compressed video

Jun Xia, Yue Shi, Y. Ling, C. Teunissen, I.E.J. Heynderickx

Human Technology Interaction

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

Abstract

A perceptual blurring metric, based on the variance difference between the original and compressed video sequence, is proposed. The human contrast sensitivity function is used to define different spatial frequency bands in which the variance is measured. The region of interest area is used for masking video content to further improve the accuracy of the metric. The proposed metric is evaluated on subjective blurring scores, and yields a high correlation coefficient of 0.934. Robustness of the metric is tested and revealed correlations higher than 0.78, when all video fragments were used. ©2009 IEEE.

Original language	English
Title of host publication	1st International Conference on Information Science and Engineering (ICISE), 26-28 December 2009, Nanjing
Place of Publication	Nanjing
Pages	461-464
DOIs	https://doi.org/10.1109/ICISE.2009.133
Publication status	Published - 2009

Access to Document

10.1109/ICISE.2009.133

Cite this

@inproceedings{5647500b66464b48be07b7b991537670,

title = "A perceptual blurring metric for compressed video",

abstract = "A perceptual blurring metric, based on the variance difference between the original and compressed video sequence, is proposed. The human contrast sensitivity function is used to define different spatial frequency bands in which the variance is measured. The region of interest area is used for masking video content to further improve the accuracy of the metric. The proposed metric is evaluated on subjective blurring scores, and yields a high correlation coefficient of 0.934. Robustness of the metric is tested and revealed correlations higher than 0.78, when all video fragments were used. {\textcopyright}2009 IEEE.",

author = "Jun Xia and Yue Shi and Y. Ling and C. Teunissen and I.E.J. Heynderickx",

year = "2009",

doi = "10.1109/ICISE.2009.133",

language = "English",

isbn = "978-1-4244-4909-5",

pages = "461--464",

booktitle = "1st International Conference on Information Science and Engineering (ICISE), 26-28 December 2009, Nanjing",

}

TY - GEN

T1 - A perceptual blurring metric for compressed video

AU - Xia, Jun

AU - Shi, Yue

AU - Ling, Y.

AU - Teunissen, C.

AU - Heynderickx, I.E.J.

PY - 2009

Y1 - 2009

N2 - A perceptual blurring metric, based on the variance difference between the original and compressed video sequence, is proposed. The human contrast sensitivity function is used to define different spatial frequency bands in which the variance is measured. The region of interest area is used for masking video content to further improve the accuracy of the metric. The proposed metric is evaluated on subjective blurring scores, and yields a high correlation coefficient of 0.934. Robustness of the metric is tested and revealed correlations higher than 0.78, when all video fragments were used. ©2009 IEEE.

AB - A perceptual blurring metric, based on the variance difference between the original and compressed video sequence, is proposed. The human contrast sensitivity function is used to define different spatial frequency bands in which the variance is measured. The region of interest area is used for masking video content to further improve the accuracy of the metric. The proposed metric is evaluated on subjective blurring scores, and yields a high correlation coefficient of 0.934. Robustness of the metric is tested and revealed correlations higher than 0.78, when all video fragments were used. ©2009 IEEE.

U2 - 10.1109/ICISE.2009.133

DO - 10.1109/ICISE.2009.133

M3 - Conference contribution

SN - 978-1-4244-4909-5

SP - 461

EP - 464

BT - 1st International Conference on Information Science and Engineering (ICISE), 26-28 December 2009, Nanjing

CY - Nanjing

ER -

A perceptual blurring metric for compressed video

Abstract

Access to Document

Fingerprint

Cite this