Objective video quality measurement is a challenging problem in a variety of video processing application ranging from lossy compression to printing. An ideal video quality measure should be able to mimic the human observer. We present a new video quality measure, M-SVD, to evaluate distorted video sequences based on singular value decomposition. A computationally efficient approach is developed for full-reference (FR) video quality assessment. This measure is tested on the Video Quality Experts Group (VQEG) phase I FR-TV test data set. Our experiments show the graphical measure displays the amount of distortion as well as the distribution of error in all frames of the video sequence while the numerical measure has a good correlation with perceived video quality outperforms PSNR and other objective measures by a clear margin.

Date Published: 29 January 2007
PDF: 10 pages
Proc. SPIE 6494, Image Quality and System Performance IV, 649408 (29 January 2007); doi: 10.1117/12.696142

Published in SPIE Proceedings Vol. 6494:
Image Quality and System Performance IV
Luke C. Cui; Yoichi Miyake, Editor(s)