The Weizmann Institute of Science
Faculty of Mathematics and Computer Science
Vision and Robotics Seminar
Sarit Shwartz
Department of Electrical Engineering
Technion
will speak on
Blind separation of high dimensional sources
Abstract:
Blind source separation (BSS) is part of a wide range of scientific fields such
as acoustics, image processing, medical imaging, and computer vision. In this
work we focus on separation of high dimensional mixtures of sources. In such
scenarios, existing BSS algorithms become intractable. Thus, we present two
algorithms that enable blind separation of high dimensional sources. The first
algorithm is based on minimization of mutual information. It involves a
numerically efficient algorithm for kernel (Parzen windows) entropy estimation
based on convolutions. In particular, we present an accurate and efficient
method for calculating the gradient of the mutual information. This
accelerates the optimization needed for source separation. The second
algorithm addresses convolutive mixtures of images. Such image mixtures are
common in tomography and reflections. We show that the large optimization
problem associated with convolution can be factored into several small and
simple problems. In addition, we show that the problem can be solved
efficiently by exploiting a-priori knowledge about both image statistics and a
parametric model of the convolutive blur process.
Joint work with Yoav Schechner.
The lecture will take place in the
Lecture Hall, Room 1, Ziskind Building
on Thursday, August 4, 2005
noon - 13:00