3D shape analysis for matching, modelling and classification
Martedì 14 Marzo ore 11,30
Sala Lauree sede di Milano
Relatore: Umberto Castellani
Responsabile: Alessandro Rizzi
3D shape analysis is a fundamental research topic for different domains like computer graphics, computer vision and pattern recognition. In this talk we introduce the recent advances on spectral shape techniques based on the functional map framework. Moreover, we propose a new approach to extend standard signal processing methods to manifold (i.e., 3D meshes). We show the effectiveness of the proposed methods on two different applicative scenarios: i) brain classification for bipolar disorder detection, and ii) point to point matching for 3D shape retrieval. Finally, some work in progress will be introduced on the smart generation of digital contents for interactive application and gaming.
Umberto Castellani is Ricercatore (i.e., Assistant Professor) of Department of Computer Science at University of Verona. He received his PhD in Computer Science from the University of Verona in 2003 working on 3D data modelling and reconstruction. He held visiting research positions at Edinburgh University (UK), Universite' Blaise Pascal (France), Michigan State University (USA), Universite' D'Auvergne (France), Italian Institute of Technology (IIT), and University College London (UK). His research is focused on 3D data processing, statistical learning and medical image analysis. He is teaching Computer Vision at the Computer Science Department, and Multimedia at the department of filologia, letteratura e linguistica at the University of Verona. He is the Director of the Master in Computer Game Development of the University of Verona. He is member of the editorial board of the Pattern Recognition journal. He is member of Eurographics, IAPR, MICCAI and IEEE.