|
TITLE: Assessing Image Quality Using Salience
PRESENTER: Prof Murray H. Loew, http://www.ece.gwu.edu/people/peopleframe.htm, loew@gwu.edu
AFFILIATION:Department of Electrical & Computer Engineering, The George Washington University, Washington, D.C., http://www.ece.seas.gwu.edu/
DATE: Friday 16th June 2006
TIME: 12:00:00
PLACE: CSE Seminar Room, Level 1, K17
ABSTRACT:
This work derives and assesses the usefulness of an objective image
quality measure. The measure is correlated with perceived image quality
as a function of the most salient features contained within a given image.
They are determined by combining aspects of both visual discrimination
theory and signal detection theory to define a new measure that quantifies
the importance of contrast-based features as a function of spatial
frequency. We discuss the development of a perceptually-correlated metric
that is useful for quantifying the conspicuity of local, low-level or
bottom-up visual cues, and the identification of those spatial frequencies
that are most distinct and perhaps most relied upon by radiologists for
decision-making. An analysis of variance model is developed that accounts
for the variance in the salience metric. The model is generalizable to a
population of readers and to a population of cases. The salience measure
can be used to objectively assess breast density, to assess data set
difficulty for computer-assisted-diagnosis algorithm development and
testing, and to determine conspicuous regions-of-interest, which can be
used to isolate regions for higher compression using JPEG 2000.
BIOGRAPHY OF SPEAKER:
After receiving the Ph.D. in Electrical Engineering from Purdue University,
Murray Loew spent six years in industry. He then joined the Department of
Electrical and Computer Engineering at George Washington University,
Washington, D.C., where he is now professor, and director of the program
in biomedical engineering. His teaching and research interests include
medical image processing and analysis (salience; multispectral infrared
breast imaging; human vs. machine stereology), compression (task-based
measures of reconstructed image quality), and pattern recognition
(small-sample measures for error probability and ROC; multisensor fusion
for vehicle classification). He is a Fellow of the IEEE and of AIMBE.
Prof Loew is a Visiting Fellow at e-Health Research Centre, CSIRO ICT
Centre in June-July 2006.
Host:
Arcot Sowmya
Seminar Convenor:
Van Hai Ho
|
