Spectral Demons - Image Registration via Global Spectral Correspondence

Abstract : Image registration is a building block for many applications in computer vision and medical imaging. However the current methods are lim- ited when large and highly non-local deformations are present. In this pa- per, we introduce a new direct feature matching technique for non-parametric image registration where efficient nearest-neighbor searches find global corre- spondences between intensity, spatial and geometric information. We exploit graph spectral representations that are invariant to isometry under complex deformations. Our direct feature matching technique is used within the estab- lished Demons framework for diffeomorphic image registration. Our method, called Spectral Demons , can capture very large, complex and highly non-local deformations between images. We evaluate the improvements of our method on 2D and 3D images and demonstrate substantial improvement over the con- ventional Demons algorithm for large deformations
Type de document :
Communication dans un congrès
Computer Vision - ECCV 2012, 2012, Florence, Italy. Springer, 7573, pp.30-44, 2012, Lecture Notes in Computer Science - LNCS. 〈10.1007/978-3-642-33709-3_3〉
Liste complète des métadonnées

https://hal.inria.fr/hal-00813833
Contributeur : Project-Team Asclepios <>
Soumis le : mardi 16 avril 2013 - 11:16:34
Dernière modification le : lundi 19 mars 2018 - 22:38:02

Lien texte intégral

Identifiants

Collections

Citation

Hervé Lombaert, Leo Grady, Xavier Pennec, Nicholas Ayache, Farida Cheriet. Spectral Demons - Image Registration via Global Spectral Correspondence. Computer Vision - ECCV 2012, 2012, Florence, Italy. Springer, 7573, pp.30-44, 2012, Lecture Notes in Computer Science - LNCS. 〈10.1007/978-3-642-33709-3_3〉. 〈hal-00813833〉

Partager

Métriques

Consultations de la notice

172