Why is Image Quality Assessment So Difficult?

Electrical and Computer Engineering
The University of Texas at Austin

Friday, March 29th, 11:00 AM, WRW 102

Abstract

Image quality assessment plays an important role in various image processing applications. A great deal of effort has been made in recent years to develop objective image quality metrics that can predict perceived quality measurement. Unfortunately, only limited success has been achieved. In this talk, we provide some insights on why image quality assessment is so difficult by pointing out the weaknesses of the error sensitivity based framework, which has been used by most image quality assessment approaches in the literature. Furthermore, we propose a new philosophy in designing image quality metrics, which considers image degradation as structural distortions instead of certain types of errors. A simple but effective image quality indexing algorithm is implemented, which is very promising as shown by our current results. The general idea of this method may also be extended to many other image processing, computer vision, and signal processing areas.

Biography

Zhou Wang received his Ph.D. degree from the Department of Electrical and Computer Engineering at the University of Texas at Austin in 2001. His thesis topic is about rate scalable image/video coding and communications considering human visual system features. He has a broad research interest including image and video processing, coding, communication and quality assessment, computer vision, wavelets, fractals, fuzzy technologies, and artificial neural networks.

A list of Telecommunications and Signal Processing Seminars is available at from the ECE department Web pages under "Seminars". The Web address for the Telecommunications and Signal Processing Seminars is http://signal.ece.utexas.edu/seminars