Objective and subjective quality assessment with expert and non-expert viewers
Filippo Speranza, Felix Poulin, Ron Renaud, Maxime Caron, Jonathan Dupras · 2010
The purpose of this study was to investigate whether objective models can be equally accurate for expert and non-expert viewers. We measured in both expert and non-expert viewers the subjective video quality of several high definition video sequences, which had been processed at several bit-rates using MPEG-2 and H.264 codecs. The results showed only a small but statistically significant difference, particularly at low bit-rates, in perceived quality between experts and non-experts. These subjective data were then compared to objective quality measurements obtained with a JND-based model and the standard PSNR. We found that the JND model performed better than the PSNR, but its predictive performance differed significantly for expert and non-expert viewers.