Seminars/Colloquia/Invited Talks

Seminars

Nikos Paragios

Optimal Similarity and Gradient Free Image Registration: Discrete Optimization meets Continous Deformations

PLACE:	Clark 314
EVENT:	CIS Seminar Series
DATE:	January 23, 2007
TIME:	1:00 - 2:00 PM

Abstract

In this talk we present a framework which is similarity-independent and bridges the gap between continuous deformations and discrete optimization. We present a rather generic formulation that assumes a linear/non-linear continuous deformation field using a set of control points, and an objective function defined on these points. In particular free form deformations (FFD) are used to represent the space of solutions. The optimal one corresponds to the lowest potential of an objective function that aims to capitalize content similarities between the source and the target. These are defined on the entire image domain and are considered along with certain smoothness constraints on the deformation field. Several similarity metrics are considered for the case of inter and intra modality registration. The optimal solution of this objective function is obtained through the use of discrete optimization in an incremental fashion capable to account with important displacements from the source to the target with low computational cost.
Last, we introduce the concept of multi-dimensional uncertainty information of the registration process that provides a natural qualitative interpretation of the results. Validation and comparisons with the state-of-the-art methods demonstrate the great potentials of our approach.
Joint Work: Ben Glocker, Technical University of Munich

Brief Biography:

B.Sc. (highest honors, valedictorian) and M.Sc. (highest honors) in Computer Science [ University of Crete (Greece) - 1994,1996] , Ph.D. (highest honors) in electrical and computer engineering [I.N.R.I.A. , 2000] and HDR(Habilitation a Diriger de Recherches [ University of Nice/Sophia Antipolis (France), 2005)].
Nikos Paragios is professor at the Ecole Centrale de Paris, leading the Medical Imaging and Computer Vision Group at the Applied Mathematics and Systems laboratory (MAS). Prior to that he was professor/research scientist (2004-2005) at the Ecole Nationale de Ponts et Chaussees, leading the vision & augmented reality group at the Center for Research in Computer Science (CERTIS), was affiliated with Siemens Corporate Research (Princeton, NJ) as a project manager (smart cameras and machine vision group) (2002-2004), senior research scientist (2004) at the Real-time Vision and Modeling and research scientist (1999-2003) at the Imaging and Visualization department. In 2002 he was an adjunct professor at RutgersUniversity and in 2004 at New York University.
Professor Paragios has published more than seventy-five papers in the most prestigious journals and conferences of computer vision. He was named one of the top 35 innovators in science and technology under the age of 35 who with their accomplishments are likely to shape their fields for decades to come from the MIT's Technology Review magazine in 2006. He is a Senior member of IEEE, member of the Editorial Board of the International Journal of Computer Vision and has served several times as a guest editor for the most prestigious journals of computer Vision (IJCV, CVIU) serves regularly in the program committees of the most important computer vision and medical image conferences (ICCV, CVPR, ECCV, MICCAI,...) and is also reviewing papers for the leading journals of his domain (PAMI, IJCV, CVIU, TMI,...). Professor Paragios is a program co-chair of the 11th European Conference in Computer Vision (ECCV'10, Heraklion, Crete). He has co-edited four books.