ECE Distinguished Lecture with Kim L. Boyer

4:00 pm on Wednesday, March 20, 2013
Photonics Center, 8 Saint Mary’s St., Room 211
Staring Into Your (Dry) Eyes: Monitoring the Pre-Lens Tear Film From Narrowband Interferometry Professor Kim L. Boyer Head, Electrical, Computer, and Systems Engineering Department Rensselaer Polytechnic University Refreshments will be served outside Room 339 at 3:45 p.m. Faculty Host: Janusz Konrad Abstract: Dry eye problems plague many people, especially wearers of contact lenses. In this talk Professor Boyer will present an approach to reconstructing the dynamic tear film surface from interferometric video to evaluate therapies and to support modeling of the tear film’s fluid dynamics. A better understanding of these dynamics will reveal the root causes and lead to improved treatments. First, he and his research team develop a texture based segmentation approach to identify dry regions. Because of the complexity of the class conditional distributions of wet and dry regions, they introduce Resilient Mixture Discriminant Analysis as a new Gaussian clustering method for high dimensional classification problems. The new method maintains the adaptability of subclass discriminant analysis but offers superior feature selection performance. Next, to reconstruct the tear film surface over the wet regions Boyer will present a novel method to solve the sign ambiguity for phase demodulation from a single image that possibly contains closed fringes. The problem is formulated in a Markov random field energy minimization framework with the assumption of phase gradient orientation continuity. Compared with traditional path following phase demodulation methods, the new approach requires no heuristic scanning strategy, is not subject to the propagation of error, and the extension to three dimensional fringe patterns is straightforward. A set of experiments with synthetic and real prelens tear film interferometric images of the human eye demonstrates the effectiveness and robustness of the algorithm as compared with the prior state of the art. About the Speaker: Dr. Kim Boyer is Head of the Department of Electrical, Computer, and Systems Engineering at Rensselaer Polytechnic Institute. He received the Ph.D. degree in electrical engineering from Purdue University. From 1986-2007 he was on the faculty of the Department of Electrical and Computer Engineering, The Ohio State University. He is a Fellow of the IEEE, a Fellow of IAPR, and a former IEEE Computer Society Distinguished Speaker. Dr. Boyer is also a National Academies Jefferson Science Fellow at the US Department of State, spending 2006-07 as Senior Science Advisor to the Bureau of Western Hemisphere Affairs. While at State he studied the impact of technological innovation on economic development in scientifically lagging and scientifically developing countries. He also developed policy recommendations for the use of science and engineering as instruments of diplomacy. He retains his Fellowship as a consultant on science and technology policy for the State Department. Dr. Boyer has published more than 100 scientific papers and has lectured in nearly 30 countries around the world. His books include: Computing Perceptual Organization in Computer Vision, World Scientific, 1994 (with Sudeep Sarkar); Perceptual Organization for Artificial Vision Systems, Kluwer Academic Publishers, 2000 (with Sudeep Sarkar); and Robust Range Image Registration: Using Genetic Algorithms and the Surface Interpenetration Measure, 2005 (with Luciano Silva and Olga Bellon). His sixth book, Computer Vision Techniques in High Resolution Satellite Image Understanding (with Cem Unsalan) was recently released by Springer-Verlag.