English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In subjective full-reference image quality assessment, differences betweenperceptual image qualities of the reference image and its distorted versionsare evaluated, often using degradation category ratings (DCR). However, the DCRhas been criticized since differences between rating categories on this ordinalscale might not be perceptually equidistant, and observers may have differentunderstandings of the categories. Pair comparisons (PC) of distorted images,followed by Thurstonian reconstruction of scale values, overcome theseproblems. In addition, PC is more sensitive than DCR, and it can provide scalevalues in fractional, just noticeable difference (JND) units that express aprecise perceptional interpretation. Still, the comparison of images of nearlythe same quality can be difficult. We introduce boosting techniques embedded inmore general triplet comparisons (TC) that increase the sensitivity even more.Boosting amplifies the artefacts of distorted images, enlarges their visualrepresentation by zooming, increases the visibility of the distortions by aflickering effect, or combines some of the above. Experimental results show theeffectiveness of boosted TC for seven types of distortion. We crowdsourced over1.7 million responses to triplet questions. A detailed analysis shows thatboosting increases the discriminatory power and allows to reduce the number ofsubjective ratings without sacrificing the accuracy of the resulting relativeimage quality values. Our technique paves the way to fine-grained image qualitydatasets, allowing for more distortion levels, yet with high-quality subjectiveannotations. We also provide the details for Thurstonian scale reconstructionfrom TC and our annotated dataset, KonFiG-IQA, containing 10 source images,processed using 7 distortion types at 12 or even 30 levels, uniformly spacedover a span of 3 JND units.

Subjective Image Quality Assessment with Boosted Triplet Comparisons