Share Email Print
cover

Proceedings Paper • new

A no-reference image and video visual quality metric based on machine learning
Author(s): Vladimir Frantc; Viacheslav Voronin; Evgenii Semenishchev; Maxim Minkin; Aliy Delov
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper 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.

Paper Details

Date Published: 13 April 2018
PDF: 5 pages
Proc. SPIE 10696, Tenth International Conference on Machine Vision (ICMV 2017), 106961Y (13 April 2018); doi: 10.1117/12.2309517
Show Author Affiliations
Vladimir Frantc, Don State Technical Univ. (Russian Federation)
Viacheslav Voronin, Don State Technical Univ. (Russian Federation)
Evgenii Semenishchev, Don State Technical Univ. (Russian Federation)
Maxim Minkin, Don State Technical Univ. (Russian Federation)
Aliy Delov, SC "Science and Innovations" (Russian Federation)


Published in SPIE Proceedings Vol. 10696:
Tenth International Conference on Machine Vision (ICMV 2017)
Antanas Verikas; Petia Radeva; Dmitry Nikolaev; Jianhong Zhou, Editor(s)

© SPIE. Terms of Use
Back to Top