Tampere University of Technology

TUTCRIS Research Portal

Robust linearized combined metrics of image visual quality

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Details

Original languageEnglish
Title of host publicationElectronic Imaging
Subtitle of host publicationImage Processing: Algorithms and Systems XVI
PublisherSociety for Imaging Science and Technology
DOIs
Publication statusPublished - 2018
Publication typeA4 Article in a conference publication
EventIS&T International Symposium on Electronic Imaging -
Duration: 28 Jan 20182 Feb 2018

Publication series

Name
ISSN (Electronic)2470-1173

Conference

ConferenceIS&T International Symposium on Electronic Imaging
Period28/01/182/02/18

Abstract

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.

Keywords

  • Combined metrics, Full-reference metrics, Image visual quality assessment, Robust metrics

Publication forum classification

Field of science, Statistics Finland