Image Segmentation by Spatially Varying Gaussian Mixture Models

When: Monday, September 12, 2016
Where: PGH 563
Time: 11:00 AM

Speaker: Prof. Christophoros Nikou

Host: Prof. Ioannis Kakadiaris

In image segmentation, the spatially varying Gaussian mixture model (SV-GMM) is a generalization of the standard GMM, whose mixing proportions depend on the local image coordinates. The common approach to estimate them using the expectation-maximization (EM) algorithm is to assume that they are random variables enforcing image smoothness. In this talk, SVGMM models addressing two important issues in image segmentation will be presented: (i) how to preserve image boundaries, (ii) how to automatically estimate the number of mixture components. Finally, a method for ensuring that the mixing proportions are always probability values (sum to one and be non-negative) will be discussed.

Bio:

Christophoros Nikou is an Associate Professor at the Department of Computer Science and Engineering, University of Ioannina, Greece. During the academic year 2015-2016 he has been a Visiting Associate Professor at the Department of Computer Science, University of Houston, USA.

His research interests mainly include computer vision and pattern recognition, image processing and analysis and their application to medical imaging. He is a member of EURASIP and an IEEE Senior Member.

He received the Diploma in electrical engineering from the Aristotle University of Thessaloniki, Greece, in 1994 and the DEA and Ph.D. degrees in image processing and computer vision from Louis Pasteur University, Strasbourg, France, in 1995 and 1999, respectively. He was a Senior Researcher with the Department of Informatics, Aristotle University of Thessaloniki, Greece in 2001. From 2002 to 2004, he was a Research Engineer and Project Manager with Compucon S.A., Thessaloniki, Greece. He has been with the Department of Computer Science and Engineering, University of Ioannina, Ioannina, Greece since 2004, where he has been a Lecturer (2004-2009), Assistant Professor (2009-2013) and an Associate Professor (since 2013).