The Weizmann Institute of Science
Faculty of Mathematics and Computer Science
Vision and Robotics Seminar
Benjamin Kimia
Brown University
will speak on
OBJECT RECOGNITION BASED ON SHAPE
Abstract:
In this talk a framework for the recognition of objects based on their silhouettes is presented.
The main idea is to measure the distance between two shapes as the minimum extent of deformation
necessary for one shape to match another. Since the space of deformations is very high-dimensional,
three steps are taken to make the search practical:
(i) define an equivalence class for shapes based on shock-graph topology;
(ii) define an equivalence class for deformation paths based on a formal classification of
shock-graph transitions; and
(iii) avoid complexity-increasing deformation paths by moving towards shock-graph degeneracy.
Despite these steps, which tremendously reduce the search requirement, there still remain numerous
paths to consider. To that end, we employ an edit-distance algorithm for shock graphs which finds
the optimal deformation path in polynomial time. This approach gives intuitive correspondences for
a variety of shapes, and is robust in the presence of a wide range of visual transformations.
The recognition rates on two distinct databases of 99 and 216 shapes each indicate highly successful
within category matches (100\% in top three matches), which render the framework potentially usable
in a range of shape-based recognition applications.
The lecture will take place in the
Lecture Hall, Room 1, Ziskind Building
on Monday, June 2, 2003
at 14:30
Please note the unusual day and time