Satisfied user ratio prediction with support vector regression for compressed stereo images

Simple item page
dc.cclicenceCC-BY-NCen
dc.contributor.authorFan, Chunling
dc.contributor.authorZhang, Yun
dc.contributor.authorHamzaoui, Raouf
dc.contributor.authorZiou, Djemel
dc.contributor.authorJiang, Qingshan
dc.date.acceptance2020-04-15
dc.date.accessioned2020-05-19T08:53:54Z
dc.date.available2020-05-19T08:53:54Z
dc.date.issued2020-07
dc.description.abstractWe propose the first method to predict the Satisfied User Ratio (SUR) for compressed stereo images. The method consists of two main steps. First, considering binocular vision properties, we extract three types of features from stereo images: image quality features, monocular visual features, and binocular visual features. Then, we train a Support Vector Regression (SVR) model to learn a mapping function from the feature space to the SUR values. Experimental results on the SIAT-JSSI dataset show excellent prediction accuracy, with a mean absolute SUR error of only 0.08 for H.265 intra coding and only 0.13 for JPEG2000 compression.en
dc.funderNo external funderen
dc.funder.otherNSFCen
dc.identifier.citationFan, C., Zhang, Y., Hamzaoui, R., Ziou, D., Jiang, Q. (2020) Satisfied user ratio prediction with support vector regression for compressed stereo images. IEEE International Conference on Multimedia & Expo Workshops (ICMEW), London, July 2020.en
dc.identifier.urihttps://dora.dmu.ac.uk/handle/2086/19603
dc.language.isoen_USen
dc.peerreviewedYesen
dc.projectid61871372en
dc.publisherIEEEen
dc.researchinstituteInstitute of Engineering Sciences (IES)en
dc.subjectSatisfied user ratioen
dc.subjectPicture-level just noticeable differenceen
dc.subjectStereo imagesen
dc.titleSatisfied user ratio prediction with support vector regression for compressed stereo imagesen
dc.typeConferenceen

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
207.pdf
Size:
11.28 MB
Format:
Adobe Portable Document Format
Description:
Main article
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
4.2 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

School of Engineering and Sustainable Development