Keynote Address 3: Probabilistic Inference in Low Level Vision

Abstract: Three ideas are singled out that launched the modern era of Computer Vision 20 years ago. They are: variational analysis (Horn and Schunk 1980); active shape models (Kass, Witkin and Terzopoulos 1987); probabilistic inference in images (Geman and Geman 1984). These foundations have been coupled with more recent advances in inference algorithms -- particle filtering, belief propagation and graph cut -- and with advances in modelling such as active appearance models and Markov random fields. Finally, Probabilistic approaches enable system parameters, whose multiplicity plagued conventional machine vision systems, to be set automatically by the learning those parameters from data. This viewpoint is illustrated by reference to modern systems for image segmentation, motion tracking and stereo vision.

Biography: Andrew Blake graduated in 1977 from Trinity College, Cambridge with a B.A. in Mathematics and Electrical Sciences. After a year as a Kennedy Scholar at MIT and two years in the defence electronics industry, he studied for a doctorate at the University of Edinburgh which was awarded in 1983. Until 1987 he was on the faculty of the department of Computer Science at the University of Edinburgh and a Royal Society Research Fellow. From 1987 to 1999, he has been on the faculty of the Department of Engineering Science in the University of Oxford, where he ran the Visual Dynamics Research Group, became a Professor in 1996, and and was a Royal Society Senior Research Fellow for 1998-9. In 1999 he moved to Microsoft Research Cambridge as Senior Research Scientist, leading the Vision Group. He was elected Fellow of the Royal Academy of Engineering in 1998, and Fellow of the Royal Society in 2005.

His main research activities are in computer vision. He has published several books including "Visual Reconstruction" with A.Zisserman (MIT press), "Active Vision" with A. Yuille (MIT Press) and "Active Contours" with M. Isard (Springer-Verlag). He has twice won the prize of the European Conference on Computer Vision, with R. Cipolla in 1992 and with M. Isard in 1996, and was awarded the IEEE David Marr Prize (jointly with K. Toyama) in 2001. He has served as programme chairman for the International Conference on Computer Vision in 1995 and 1999, and is on the editorial boards of the journals "Image and Vision Computing", the "International Journal of Computer Vision" and "Computer Vision and Image Understanding". Current research spans image interaction, stereo vision and motion tracking.