A new full-reference image quality metric based on just noticeable difference

Basit Öğe Kaydı
dc.contributor.authorToprak, Sevil
dc.contributor.authorYalman, Yildiray
dc.date.accessioned2025-10-24T18:08:59Z
dc.date.available2025-10-24T18:08:59Z
dc.date.issued2017
dc.departmentMalatya Turgut Özal Üniversitesi
dc.description.abstractAn Image Quality Metric (IQM) is used to measure how the image on which modifications are carried out is distorted. Knowing the distortion scale of the image is of significance for the intended purposes (compression, forensic, medical, etc.). The amount of distortion has different implications for each of the application and whether the image is convenient for the relevant application by using the IQM. One of the most basic approaches in the literature which is used in measuring the amount of the distortion is the Full-Reference Image Quality Metric (FR-IQM). The FR-IQM needs both the original and distorted image in the phase of comparison. In this study, taking into consideration the Human Vision System (HVS), a new full-reference image quality metric based on Just Noticeable Difference (JND) has been presented. Through this new metric, the HVS's physiological (color and light sensitivity) and psycho-physiological (texture and edge sensitivity) characteristics have been taken into consideration. Through the JND, the inclusion of the unintended modifications that cannot be sensed by the HVS has been prevented. The near-zero quality results point out the more quality image. The experimental results have showed that the metric in question demonstrates a higher level of performance for the HVS when compared with its counterparts.
dc.description.sponsorshipScientific and Technological Research Council of Turkey (TUBITAK) [115E651]
dc.description.sponsorshipThis work has been supported in part by The Scientific and Technological Research Council of Turkey (TUBITAK) research grant 115E651. The authors would like to thank the anonymous reviewers and the editor for their invaluable comments and suggestions.
dc.identifier.doi10.1016/j.csi.2016.08.003
dc.identifier.endpage25
dc.identifier.issn0920-5489
dc.identifier.issn1872-7018
dc.identifier.scopus2-s2.0-84989196171
dc.identifier.scopusqualityQ1
dc.identifier.startpage18
dc.identifier.urihttps://doi.org/10.1016/j.csi.2016.08.003
dc.identifier.urihttps://hdl.handle.net/20.500.12899/3404
dc.identifier.volume50
dc.identifier.wosWOS:000390074900002
dc.identifier.wosqualityQ2
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherElsevier
dc.relation.ispartofComputer Standards & Interfaces
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.snmzKA_20251023
dc.subjectImage quality metric; Full-reference image quality metric; Human vision system; Just noticeable difference
dc.titleA new full-reference image quality metric based on just noticeable difference
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu