A Scale-Space Approach to Landmark Constrained Image Registration


Adding external knowledge improves the results for ill-posed problems. In this paper we present a new multi-level optimization framework for image registration when adding landmark constraints on the transformation. Previous approaches are based on a fixed discretization and lack of allowing for continuous landmark positions that are not on grid points. Our novel approach overcomes these problems such that we can apply multi-level methods which have been proven being crucial to avoid local minima in the course of optimization. Furthermore, for our numerical method we are able to use constraint elimination such that we trace back the landmark constrained problem to a unconstrained optimization leading to an efficient algorithm.
TitelScale Space and Variational Methods in Computer Vision
Redakteure/-innenXue-Cheng Tai, Knut Mørken, Marius Lysaker, Knut-Andreas Lie
Band5567 LNCS
ErscheinungsortBerlin, Heidelberg
Herausgeber (Verlag)Springer Berlin Heidelberg
ISBN (Print)978-3-642-02255-5
ISBN (elektronisch)978-3-642-02256-2
PublikationsstatusVeröffentlicht - 01.06.2009
Veranstaltung2nd International Conference on Scale Space and Variational Methods in Computer Vision - Voss, Norwegen
Dauer: 01.06.200905.06.2009
Konferenznummer: 77044


Untersuchen Sie die Forschungsthemen von „A Scale-Space Approach to Landmark Constrained Image Registration“. Zusammen bilden sie einen einzigartigen Fingerprint.