Open AccessReduced reference metric for compressed stereoscopic videos
Author(s) -
Malekmohamadi H.,
Fernando W.A.C.,
Kondoz A.M.
Publication year - 2013
Publication title -
electronics letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.375
H-Index - 146
ISSN - 1350-911X
DOI - 10.1049/el.2013.0559
Subject(s) - metric (unit) , stereoscopy , enhanced data rates for gsm evolution , artificial intelligence , computer science , computer vision , mathematics , pattern recognition (psychology) , engineering , operations management
A new reduced reference objective quality metric for stereoscopic video is proposed that incorporates spatial neighbouring information from grey‐level co‐occurrence matrices and edge properties. Extracted colour and depth features are combined unequally to maximise the performance of the proposed metric. The performance of this metric is validated through a series of subjective tests and the average correlation 0.82 is achieved when colour to depth importance ratio is near 0.80.