Share Email Print

Journal of Electronic Imaging

Thin-slice vision: inference of confidence measure from perceptual video quality
Author(s): Abdul Hameed; Benjamin Balas; Rui Dai
Format Member Price Non-Member Price
PDF $20.00 $25.00

Paper Abstract

There has been considerable research on thin-slice judgments, but no study has demonstrated the predictive validity of confidence measures when assessors watch videos acquired from communication systems, in which the perceptual quality of videos could be degraded by limited bandwidth and unreliable network conditions. This paper studies the relationship between high-level thin-slice judgments of human behavior and factors that contribute to perceptual video quality. Based on a large number of subjective test results, it has been found that the confidence of a single individual present in all the videos, called speaker’s confidence (SC), could be predicted by a list of features that contribute to perceptual video quality. Two prediction models, one based on artificial neural network and the other based on a decision tree, were built to predict SC. Experimental results have shown that both prediction models can result in high correlation measures.

Paper Details

Date Published: 21 December 2016
PDF: 4 pages
J. Electron. Imaging. 25(6) 060501 doi: 10.1117/1.JEI.25.6.060501
Published in: Journal of Electronic Imaging Volume 25, Issue 6
Show Author Affiliations
Abdul Hameed, COMSATS Institute of Information Technology (Pakistan)
Benjamin Balas, North Dakota State Univ. (United States)
Rui Dai, Univ. of Cincinnati (United States)

© SPIE. Terms of Use
Back to Top