13 April 2018 A no-reference image and video visual quality metric based on machine learning
Author Affiliations +
Proceedings Volume 10696, Tenth International Conference on Machine Vision (ICMV 2017); 106961Y (2018) https://doi.org/10.1117/12.2309517
Event: Tenth International Conference on Machine Vision, 2017, Vienna, Austria
Abstract
The paper presents a novel visual quality metric for lossy compressed video quality assessment. High degree of correlation with subjective estimations of quality is due to using of a convolutional neural network trained on a large amount of pairs video sequence-subjective quality score. We demonstrate how our predicted no-reference quality metric correlates with qualitative opinion in a human observer study. Results are shown on the EVVQ dataset with comparison existing approaches.
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Vladimir Frantc, Vladimir Frantc, Viacheslav Voronin, Viacheslav Voronin, Evgenii Semenishchev, Evgenii Semenishchev, Maxim Minkin, Maxim Minkin, Aliy Delov, Aliy Delov, } "A no-reference image and video visual quality metric based on machine learning", Proc. SPIE 10696, Tenth International Conference on Machine Vision (ICMV 2017), 106961Y (13 April 2018); doi: 10.1117/12.2309517; https://doi.org/10.1117/12.2309517
PROCEEDINGS
5 PAGES


SHARE
Back to Top