The Weizmann Institute of Science
Faculty of Mathematics and Computer Science
Vision and Robotics Seminar
Michael Zibulevsky
Faculty of Electrical Engineering
Technion - Haifa
will speak on
Blind source separation and
deconvolution using sparsity priors
Abstract:
The blind source separation problem is concerned with extraction of the underlying unknown source
signals from a set of their linear mixtures, where the mixing matrix is unknown. The blind deconvolution
problem consists in recovery of a signal/image blurred by unknown convolution kernel.
These two problems are close related and are encountered in acoustics, radio, radar, medical signal
and image processing, hyperspectral imaging, and more, hence the tremendous interest to them.
We show how to exploit the sparsity of a wavelet-type and other representations of the sources in order
to obtain high quality separation and deconvolution. We also discuss optimization methods,
like the Relative Newton method and the Smoothing Method of Multipliers (SMOM) for efficient solution of
arising L1-norm minimization problem.
The lecture will take place in the
Lecture Hall, Room 1, Ziskind Building
on Thursday, December 2, 2004
at noon