Systems Seminar
Multiresolution Techniques in Pattern Recognition
Clay Scott
ECE Department
Rice University
Abstract
We use the expression "pattern recognition" to refer to a wide range of
applications. In this talk I will distinguish two ways of thinking about
patterns, and discuss what pattern recognition looks like in each setting.
The first case is typical of many applications in signal and image
processing as well as computer vision, while the second case is more common
in statistics, artificial intelligence, and data mining. I will provide
examples of how multiresolution techniques can be used to do pattern
recognition in both cases. The first example examines the problem of object
recognition in cluttered scenery, while the second looks at recent
developments in the analysis of decision trees. Finally, I will look at
connections between the two perspectives, and discuss possibilities for
future work.
Time and Place: Thu., Apr. 15, at 4 pm in 3609 Engr. Hall.
*** NOTE SPECIAL DAY, TIME, & PLACE ***
SYSTEMS SEMINAR WEB PAGE:
http://www.cae.wisc.edu/~gubner/seminar/