Ansatte – Københavns Universitet

Bicycle Chain Shape Models

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

Stefan Horst Sommer, Aditya Jayant Tatu, Chen Chen, Dan Jørgensen, Marleen de Bruijne, Marco Loog, Mads Nielsen, Francois Bernard Lauze

In this paper we introduce landmark-based preshapes which allow mixing of anatomical landmarks and pseudo-landmarks, constraining consecutive pseudo-landmarks to satisfy planar equidistance relations. This defines naturally a structure of Riemannian manifold on these preshapes, with a natural action of the group of planar rotations. Orbits define the shapes. We develop a Geodesic Generalized Procrustes Analysis procedure for a sample set on such a preshape spaces and use it to compute Principal Geodesic Analysis. We demonstrate it on an elementary synthetic example as well on a dataset of manually annotated vertebra shapes from X-ray. We re-landmark them consistently and show that PGA captures the variability of the dataset better than its linear counterpart, PCA.
OriginalsprogEngelsk
TitelComputer Vision and Pattern Recognition Workshops, 2009. CVPR Workshops 2009. IEEE Computer Society Conference on Computer Vision and Pattern Recognition.
Antal sider7
ForlagIEEE
Publikationsdato2009
Sider157-163
ISBN (Elektronisk)978-1-4244-3992-2
DOI
StatusUdgivet - 2009
BegivenhedCVPR 2009. IEEE Computer Society Conference on Computer Vision and Pattern Recognition. - Miami Beach, USA
Varighed: 20 jun. 200925 jun. 2009

Konference

KonferenceCVPR 2009. IEEE Computer Society Conference on Computer Vision and Pattern Recognition.
LandUSA
ByMiami Beach
Periode20/06/200925/06/2009

ID: 12872680