[Colloquium] Pedro Felzenszwalb on Wednesday, February 25, 2004

[Margery Ishmael]

***Refreshments will follow this talk in RYERSON 153***

-------------------------------------------

DEPARTMENT OF COMPUTER SCIENCE
(JOINT TALK WITH TTI-C)

Date:  Wednesday, February 25, 2004
Time: 2:30 p.m.
Place: Ryerson 251

-------------------------------------------

Speaker:  PEDRO FELZENSZWALB

From: Cornell University

Url:  http://www.cs.cornell.edu/~pff/

Title:   Representation and Detection of Shapes in Images

Abstract:

The study of shape is a recurring theme in computer vision.  For
example, shape is one of the main sources of information that can be
used for object recognition.  In this talk I will present techniques
for characterizing two-dimensional shapes using a particular
representation of objects in terms of triangulated polygons.  I will
show that this representation has important properties both from a
perceptual and a computational point of view.  It is common to
consider instances of a non-rigid object as deformed versions of an
ideal template.  In this way we can use deformable shape models to
detect the locations of non-rigid objects in images.  I will describe
an efficient algorithm to solve this problem in a wide range of
situations, and show examples on both medical images and images of
natural scenes.  We will also consider the problem of learning a
deformable shape model for a particular class of objects.  Finally I
will describe a stochastic grammar that can generate arbitrary
triangulated polygons while capturing Gestalt principles of shape
regularity.  Intuitively the grammar tends to generate shapes that
have smooth boundaries and a nice decomposition into almost symmetric
parts.  This grammar can be used as a generic model by a low-level
algorithm that detects the boundaries of objects in an image.

-------------------------------------------

Host: PARTHA NIYOGI

***Refreshments will follow the talk in Ryerson 153***

People in need of assistance should call 773-834-8977 in advance.