University of Houston
Department of Computer Science
In
partial fulfillment of the Requirements for the Degree of
Master of
Science
Nikhil Vajramushti
will defend his
thesis
Efficient 3D Object Retrieval Using Depth Images
Abstract
With the growing availability of 3D objects, the need for a retrieval system to
fetch a certain 3D object is increasing. We propose a novel 3D object retrieval
method that employs depth buffers for representing and comparing the objects.
The depth buffers of the objects (computed in hardware) are compared for surface
and volume similarity. Multiple depth buffers from different points of view are
employed. The accuracy of the method depends on the number of depth buffers and
the depth buffer resolution. We have performed a number of experiments to evaluate
the performance of our method within a class and between classes with very encouraging
results.
Date: Monday, May 3, 2004
Time: 11:30 AM
Place:
550-PGH
Faculty, students, and the general public are
invited.
Thesis Advisor: Professor Ioannis A. Kakadiaris