The Weizmann Institute of Science
Faculty of Mathematics and Computer Science
Vision and Robotics Seminar
Michael Bronstein
Dept. of Computer Science
Technion - Haifa
will speak on
Expression-Invariant Representations of Faces and
its Application to Three Dimensional Face Recognition
Abstract:
One of the greatest challenges of automatic face recognition, is the difficulty
introduced by facial expressions. The ability to recognize human faces in the
presence of expressions is necessary for example in commercial face recognition systems.
We introduce a geometric framework, treating faces as deformable Riemannian surfaces.
Facial expressions are modeled as topologically-constrained isometries of the facial
surface, such that the recognition problem is reduced to finding similarity between
isometric surfaces.
Next, we represent the Riemannian surface as a subset of some convenient low-dimensional
space such that the original intrinsic geometric structure is preserved. This procedure,
known as isometric embedding, allows to create an expression-invariant representation of
the face. We will show several examples of embedding spaces with flat and spherical geometry.
Finally, we will demonstrate an implementation of our approach in an accurate
three-dimensional face recognition system that is capable of distinguishing between
identical twins.
* Joint work with Ron Kimmel.
The lecture will take place in the
Lecture Hall, Room 1, Ziskind Building
on Thursday, November 4, 2004
noon - 13:00