Research in Computer Vision
at the Signal Analysis and Machine Perception Laboratory

Kim L. Boyer
Professor and Head
Department of Electrical, Computer, and Systems Engineering
Rensselaer

ABSTRACT

This talk will open with an overview of recent activity in the Signal Analysis and Machine Perception Laboratory, recently relocated from The Ohio State University to Rensselaer. We will briefly frame vision as an intelligent process, touching on the importance of perceptual organization to the capabilities of both biological and artificial vision systems. We will then highlight our work in a variety of applications as examples of the power of perceptual organization. The talk then moves to an in-depth discussion of our work in retinal thickness measurements, and optic nervehead tracking and characterization in optical coherence tomography (OCT). OCT uses retroreflected light to provide micrometer resolution cross-sectional scans of biological tissues; it is particularly useful in ophthalmic applications such as the diagnosis and monitoring of glaucoma and macularedema.

As glaucoma progresses, neural tissue dies, the nerve fiber layer thins, and the cup-disk ratio of the optic nerve head increases. Unfortunately, most current measurement techniques are subjective and inherently unreliable, making it difficult to monitor small, but critical, changes in nerve head geometry. We develop complete, autonomous algorithms based on a parabolic model of cup geometry and a Markov model of retinal structure. In thorough experimental evaluation against an experienced, expert ophthalmologist, we report a correlation coefficient for cup diameter above 0.8 and above 0.9 for the disk diameter.

Bio

Dr. Kim Boyer is Head of the Department of Electrical, Computer, and Systems Engineering at Rensselaer Polytechnic Institute. Dr. Boyer's research interests include all aspects of computer vision and medical image analysis, including perceptual organization, structural analysis, graph theoretical methods, stereopsis in weakly constrained environments, optimal feature extraction, large modelbases, and robust methods. He has published five books and more than 100 scientific papers. 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).

Dr. Boyer received the BSEE (with distinction), MSEE, and Ph.D. degrees, all in electrical engineering, from Purdue University in 1976, 1977, and 1986, respectively. Previously he held positions at Bell Labs, Comstat Laboratories (Clarksburg, MD), and the Department of Electrical and Computer Engineering, The Ohio State University. He is a fellow of the IEEE and IAPR, a former IEEE Computer Society Distinguished Speaker, and currently serves on the editorial boards for IEEE Transactions on Pattern Analysis and Machine Intelligence, Computer Vision and Image Understanding, and Machine Vision and Applications. 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. He retains his Fellowship as a consultant on science and technology policy for the State Department.

Colloquia Series page.