Robust linearized combined metrics of image visual quality

Existing full-reference metrics still do not provide a desirable degree of adequacy to a human visual perception, for evaluation of images with different types and levels of distortions. One reason for this is that it is difficult to incorporate the peculiarities of human visual system in the metric...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Electronic Imaging Jg. 30; H. 13; S. 260-1 - 260-6
Hauptverfasser:	Ieremeiev, Oleg, Lukin, Vladimir, Ponomarenko, Nikolay, Egiazarian, Karen
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Society for Imaging Science and Technology 28.01.2018
Schlagworte:	Combined Metrics Full-Reference Metrics Image Visual Quality Assessment Robust Metrics
ISSN:	2470-1173, 2470-1173
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	Existing full-reference metrics still do not provide a desirable degree of adequacy to a human visual perception, for evaluation of images with different types and levels of distortions. One reason for this is that it is difficult to incorporate the peculiarities of human visual system in the metrics design. In this paper, a robust approach to full-reference metrics' design is proposed, based on a combination of several existing full-reference metrics. A preliminary linearization (fitting) of the dependence of MOS with respect to the components metrics is performed in order to compensate shortcomings of each component. The proposed method is tested on several known databases, and demonstrate better performance than existing metrics.
Bibliographie:	2470-1173(20180128)2018:13L.2601;1-
ISSN:	2470-1173 2470-1173
DOI:	10.2352/ISSN.2470-1173.2018.13.IPAS-260