Estimating Image and Video Quality: Applications and Accuracy
|Event Date:||March 31, 2014|
|Speaker Affiliation:||AT&T Labs - Research|
|Sponsor:||Prospective ECE Faculty Candidate|
|Contact Name:||Professor Ed Delp
As digital images become ubiquitous, it is increasingly necessary to accurately estimate the visual quality of images and video. Unfortunately, the subjective tests used to evaluate image and video quality estimators (QEs) are expensive and time consuming. More problematic, the majority of subjective testing is not designed to find systematic weaknesses in the elevated QEs.
In this talk, I draw on some lessons of software testing to create additional evaluation procedures that can identify a QE’s potential weaknesses. Knowledge of these weaknesses can be used to improve a QE during its design process, to assist in selecting which QE to deploy in a real system, and to interpret the results of a chosen QE once deployed. The ease with which the proposed methods identify weaknesses in a variety of existing QEs indicates significant flaws in the current evaluation methodology. These methodological flaws are more important than any specific weaknesses in a particular QE.
I’ll conclude by presenting a sampling of recent contributions to image and video quality estimation, including measuring video quality inside the network, and a pairwise preference predictor.
Amy R. Reibman is a Lead member of Technical Staff at AT&T Labs – Research. She received the B.S., M.S. and Ph.D. degrees in electrical engineering from Duke University. After being an Assistant Professor in the Department of Electrical Engineering at Princeton University, she joined AT&T Bell Laboratories, and became a Distinguished Member of Technical Staff in 1995. She is currently a Lead Member of Technical Staff in the Video and Multimedia Services Research Department at AT&T Laboratories.
Dr. Reibman was elected Fellow in 2005, for her contributions to video transport over networks. In 1998, she won the IEEE Communications Society Leonard G. Abraham Prize Paper Award. She was the Technical co-chair of the IEEE International Conference on Image Processing in 2002; the Technical Co-Chair for the First IEEE Workshop
on Multimedia Signal Processing in 1997; the Technical Chair for the Sixth International Workshop on Packet Video in 1994. She was a Distinguished Lecturer for the IEEE Signal Processing Society from 2008 – 2009, and served on the IEEE Fellow Selection Committee from 2012 – 2014.
Dr. Reibman’s research interests include video compression systems for transport over packet and wireless networks, video quality estimation, video analytics, and 3-D and multiview video.