The Community for Technology Leaders
2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (2008)
Anchorage, AK, USA
June 23, 2008 to June 28, 2008
ISBN: 978-1-4244-2339-2
pp: 1-8
Adrian Ion , PRIP, Vienna University of Technology, Austria
Walter G. Kropatsch , PRIP, Vienna University of Technology, Austria
Salvador B. Lopez Marmol , PRIP, Vienna University of Technology, Austria
Gabriel Peyre , CEREMADE, Université Paris-Dauphine, France
Nicole M. Artner , ARC, Smart Systems Division, Austria
Laurent Cohen , CEREMADE, Université Paris-Dauphine, France
ABSTRACT
This paper makes use of the continuous eccentricity transform to perform 3D shape matching. The eccentricity transform has already been proved useful in a discrete graph-theoretic setting and has been applied to 2D shape matching. We show how these ideas extend to higher dimensions. The eccentricity transform is used to compute descriptors for 3D shapes. These descriptors are defined as histograms of the eccentricity transform and are naturally invariant to euclidean motion and articulation. They show promising results for shape discrimination.
INDEX TERMS
CITATION
Adrian Ion, Walter G. Kropatsch, Salvador B. Lopez Marmol, Gabriel Peyre, Nicole M. Artner, Laurent Cohen, "3D shape matching by geodesic eccentricity", 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, vol. 00, no. , pp. 1-8, 2008, doi:10.1109/CVPRW.2008.4563032
96 ms
(Ver )