Title: Practical Computer Vision Systems
Dr. Sharath Pankanti, IBM T. J. Watson Research Center
Date: April 1, 2011
Time: 10:20 am
Room: 1279 Anthony Hall
The ease with which humans process and understand the visual around them is very deceiving and tends to underestimate the effort and methods needed to build practical and effective, and inexpensive computer vision systems. Since practically the birth of the field, when famously, a robotic researcher at MIT was asked to solve the computer vision as a summer project, the hyperbole of what can be accomplished by artificial computer vision systems has persisted through sci-fi movies, popular literature, and even, in semi-technical AI communities. In this talk, I will overview our group's work and attempt to provide a sense of reality of the challenges involved in building real computer vision systems and trying make business out of it.Biography:
Sharath Pankanti is manager of Exploratory Computer Vision Group at T J Watson Research Center, IBM and proud Prippie/Spartan (although uses more words than necessary). He leads a number of safety, productivity, and security focused projects involving biometrics-, multi-sensor surveillance, driver assistance technologies that entail object/event modeling, detection and recognition from information provided by static and moving sensors and cameras. Many of these works are integrated into systems that have been rigorously evaluated in real world applications. His research interests include performance metrics metrics/evaluation, computer vision system designs for effective privacy, safety, security, productivity, and convenience. He has published about 70 publications in peer-reviewed conference/workshop proceedings and journals and has contributed to over 50 inventions spanning biometrics, object detection, and recognition. He has co-edited the first comprehensive book on biometrics, “Biometrics: Personal Identification” Kluwer, 1999 and co-authored, “A Guide to Biometrics”, Springer 2004 which is being used in many undergraduate and graduate biometrics curricula. For more information: https://researcher.ibm.com/researcher/view.php?person=us-sharat.