|
|
|
|
|
|
|
|
Seminar Announcement Friday, November 20, 2009 Yali Amit
The goal of Computer Vision is the automatic
labeling of images containing multiple objects as well as noise and clutter.
Recent work has focused on two main tasks. The first is the classification
among object classes in segmented images containing only one object and the
second is the detection of a particular object class in a large image. Both
tasks have been primarily addressed using discriminative learning. It is not
clear however how these methods can extend to deal with the recognition of
multiple object classes in images containing a number of objects in a wide
range of configurations. I will present an approach which starts from simple
statistical models for individual objects. With these models the important
notion of invariance can be clearly formulated. Furthermore the individual
object models can be composed to define models for object configurations.
Decisions are likelihood based and do not depend on pretrained decision
boundaries. I will show some applications, and describe some major difficulties
we face in making further progress. Professional Biography: Yali Amit received the PhD degree in mathematics from the Weizmann Institute, Israel in 1988. He spent three years as a visiting assistant professor in the Division of Applied Math at Brown University, where he started working on image analysis. In 1991, he joined the Department of Statistics at the University of Chicago. He has been Professor in Statistics and Computer Science at the University of Chicago since 1996, He is also member of the Committee on Computational Neuroscience. In 2002, he published the book 2D Object Detection and Recognition: Models, Algorithms and Networks (MIT Press). His main fields of interest are Computer Vision, Pattern Recognition and Computational Neuroscience. |
|
If you would like to contact the SPS Chicago
Webmaster, email to webmaster
|
|
