CS Faculty Candidate Colloquium

 

Friday                                     **Special Time and Location**
January 11
11:00 - 11:50 AM 
Kelley 1007

 

Dr. Sinisa Todorovic 
EECS Colloquium: Computer Science Faculty Candidate
Department of Electrical and Computer Engineering, Beckman Institute
University of Illinois at Urbana-Champaign

WHAT DO THOSE IMAGES HAVE IN COMMON? 

This talk is about discovering and modeling previously unspecified,
recurring themes in a given set of arbitrary images. Specifically, given
a set of images containing frequent occurrences of objects from multiple
categories, the goal is to learn a compact model that captures the
canonical image-space properties of the categories as well as their
relationships, for the purposes of later recognizing and extracting any
occurrences in new images. The object categories are unknown a priori.
Whether and where instances of any categories appear in a specific image
is also not known. This problem is challenging, since it involves the
following unanswered questions. What is an object category? To what
extent human supervision is necessary to communicate the nature of
object categories to a computer? What image properties should be used to
define an efficient multicategory representation? 

We will examine a methodology, developed during my postdoctoral work in
the Beckman Institute at the University of Illinois Urbana-Champaign,
which addresses these questions when objects are characterized in 2D. A
category is defined as a set of 2D objects (i.e., subimages) sharing
photometric, geometric and topological properties of their constituent
regions (e.g., color, area, shape, recursive embedding of regions). Each
image is represented by a segmentation tree whose nodes correspond to
image regions at all natural scales present, and edges between tree
nodes capture the embedding of small regions within larger ones. The
nodes contain the associated region properties. The presence of any
categories in the image set is then reflected in the frequent occurrence
of similar subtrees (i.e., 2D objects) within the image segmentation
trees. Our methodology is designed to: (1) match image trees to find
similar subtrees; (2) discover categories by clustering similar
subtrees, and use the properties of each cluster to learn the model of
the associated category; and (3) learn the grammar of the discovered
categories that compactly captures their recursive definitions in terms
of other simpler (sub)categories and their relationships (e.g.,
co-occurrence, and sharing of simple categories by more complex ones).
When a new image is encountered, its segmentation tree is matched
against the category grammar to simultaneously detect, recognize and
segment all occurrences of the learned categories. This matching also
provides a semantic explanation of object recognition in terms of the
identified subcategories (i.e., object parts) along with their spatial
relationships. 

The aforementioned methodology can also be used for detecting recurring
image themes of more general kind. An example is that of identifying and
extracting the stochastically repeating, elementary parts of visual
texture, commonly called as texture elements or texels (e.g.,
waterlilies on the water surface, a housing development, crowd of
people). 

Biography

Sinisa Todorovic received the joint B.S./M.S. degree with honors in
electrical engineering from the University of Belgrade, Serbia, in 1994.
>From 1994 until 2001, he worked as a software engineer in the
communications industry. He received his M.S. and Ph.D. degrees in
electrical and computer engineering at the University of Florida,
Gainesville, in 2002, and 2005, respectively. Since 2005, he holds the
position of Postdoctoral Research Associate in the Beckman Institute at
the University of Illinois Urbana-Champaign, where he collaborates with
Prof. Narendra Ahuja. Sinisa's main research interests concern computer
vision and machine learning, with current focus on unsupervised
extraction and representation of spatial structures recurring in images
and video. He is the recipient of Jack Neubauer Best Paper Award 2004
for a publication in IEEE Trans. Vehicular Technology, and Outstanding
Reviewer Award at the International Conf. on Computer Vision (ICCV)
2007. He serves as Associate Editor of Advances in Multimedia.

 

_______________________________________________
Colloquium mailing list
[email protected]
https://secure.engr.oregonstate.edu/mailman/listinfo/colloquium

Reply via email to