Seminario - Spectral Matching & Learning of Surface Data - Examples on Brain Surfaces

Mercoledì 31 Ottobre, alle ore 11:00, in aula Anile, il prof. Hervé Lombaert dell’ ETS Montreal terrà un seminario dal titolo " Spectral Matching & Learning of Surface Data - Examples on Brain Surfaces“.

Abstract:
How to analyze complex shapes?  This talk will show how spectral shape analysis can benefit general problems where data fundamentally lives on surfaces.  Here, we exploit spectral coordinates derived from the Laplacian eigenfunctions of shapes.  Spectral coordinates have the advantage over Euclidean coordinates, to be geometry aware and to parameterize surfaces explicitly.  This change of paradigm, from Euclidean to spectral representations, enables a classifier to be applied *directly* on surface data, via spectral coordinates.  Brain matching and learning of surface data will be shown as examples.  

Speaker
Hervé Lombaert is a Faculty at ETS Montreal, and Canada Research Chair on Shape Analysis in Medical Imaging - His research interests are in Statistics on Shapes, Data & Medical Images.  He had the chance to work in multiple centers, including Microsoft Research (Cambridge, UK), Siemens Corporate Research (Princeton, NJ), Inria Sophia-Antipolis (France), McGill University (Canada)  -  more at [ http://cim.mcgill.ca/~lombaert ]