A complete statistical evaluation of state-of-the-art image quality measures

Atidel Lahoulou; Emmanuel Viennet; Ahmed Bouridane; Mourad Haddadi

doi:10.1109/WOSSPA.2011.5931456

A complete statistical evaluation of state-of-the-art image quality measures

Atidel Lahoulou, Emmanuel Viennet, Ahmed Bouridane, Mourad Haddadi

Computer and Information Sciences Department

Research output: Contribution to conference › Paper › peer-review

9 Citations (Scopus)

Abstract

A quantitative predictive performance evaluation of seventeen full-reference image quality assessment metrics has been conducted in the present work. The process has been made over six publicly available subjectively rated image quality databases for four degradation types namely JPEG and JPEG2000 compression, Gaussian blur and Gaussian noise. Results show that there is no significant impact of the choice of image quality databases on the evaluation of the different full reference image quality metrics. These latter are found to fall into the same range of performance in terms of their correlation to the subjective human ratings, accuracy and monotonicity.

Original language	English
DOIs	https://doi.org/10.1109/WOSSPA.2011.5931456
Publication status	Published - 2011
Event	7th International Workshop on Systems, Signal Processing and their Applications (WOSSPA) - Tipaza, Algeria Duration: 1 Jan 2011 → …

Conference

Conference	7th International Workshop on Systems, Signal Processing and their Applications (WOSSPA)
Period	1/01/11 → …

Access to Document

10.1109/WOSSPA.2011.5931456

Cite this

@conference{a9cd8bba399640a8969b2fac8361ed90,

title = "A complete statistical evaluation of state-of-the-art image quality measures",

abstract = "A quantitative predictive performance evaluation of seventeen full-reference image quality assessment metrics has been conducted in the present work. The process has been made over six publicly available subjectively rated image quality databases for four degradation types namely JPEG and JPEG2000 compression, Gaussian blur and Gaussian noise. Results show that there is no significant impact of the choice of image quality databases on the evaluation of the different full reference image quality metrics. These latter are found to fall into the same range of performance in terms of their correlation to the subjective human ratings, accuracy and monotonicity.",

author = "Atidel Lahoulou and Emmanuel Viennet and Ahmed Bouridane and Mourad Haddadi",

year = "2011",

doi = "10.1109/WOSSPA.2011.5931456",

language = "English",

note = "7th International Workshop on Systems, Signal Processing and their Applications (WOSSPA) ; Conference date: 01-01-2011",

}

TY - CONF

T1 - A complete statistical evaluation of state-of-the-art image quality measures

AU - Lahoulou, Atidel

AU - Viennet, Emmanuel

AU - Bouridane, Ahmed

AU - Haddadi, Mourad

PY - 2011

Y1 - 2011

N2 - A quantitative predictive performance evaluation of seventeen full-reference image quality assessment metrics has been conducted in the present work. The process has been made over six publicly available subjectively rated image quality databases for four degradation types namely JPEG and JPEG2000 compression, Gaussian blur and Gaussian noise. Results show that there is no significant impact of the choice of image quality databases on the evaluation of the different full reference image quality metrics. These latter are found to fall into the same range of performance in terms of their correlation to the subjective human ratings, accuracy and monotonicity.

AB - A quantitative predictive performance evaluation of seventeen full-reference image quality assessment metrics has been conducted in the present work. The process has been made over six publicly available subjectively rated image quality databases for four degradation types namely JPEG and JPEG2000 compression, Gaussian blur and Gaussian noise. Results show that there is no significant impact of the choice of image quality databases on the evaluation of the different full reference image quality metrics. These latter are found to fall into the same range of performance in terms of their correlation to the subjective human ratings, accuracy and monotonicity.

U2 - 10.1109/WOSSPA.2011.5931456

DO - 10.1109/WOSSPA.2011.5931456

M3 - Paper

T2 - 7th International Workshop on Systems, Signal Processing and their Applications (WOSSPA)

Y2 - 1 January 2011

ER -

A complete statistical evaluation of state-of-the-art image quality measures

Abstract

Conference

Access to Document

Fingerprint

Cite this