A variational approach to multi-modal image matching

A variational approach to multi-modal image matching
of 38
All materials on our website are shared by users. If you have any questions about copyright issues, please report us to resolve them. We are always happy to assist you.
Related Documents
  A Variational Approach to Multi-Modal Image Matching Gerardo Hermosillo, Christophe Chefd’Hotel, Olivier Faugeras To cite this version: Gerardo Hermosillo, Christophe Chefd’Hotel, Olivier Faugeras. A Variational Approach toMulti-Modal Image Matching. RR-4117, 2001.  < inria-00072513 > HAL Id: inria-00072513https://hal.inria.fr/inria-00072513 Submitted on 24 May 2006 HAL  is a multi-disciplinary open accessarchive for the deposit and dissemination of sci-entific research documents, whether they are pub-lished or not. The documents may come fromteaching and research institutions in France orabroad, or from public or private research centers.L’archive ouverte pluridisciplinaire  HAL , estdestin´ee au d´epˆot et `a la diffusion de documentsscientifiques de niveau recherche, publi´es ou non,´emanant des ´etablissements d’enseignement et derecherche fran¸cais ou ´etrangers, des laboratoirespublics ou priv´es.     I   S   S   N    0   2   4   9  -   6   3   9   9   I   S   R   N    I   N   R   I   A   /   R   R  -  -   4   1   1   7  -  -   F   R  +   E   N   G  apport  de recherche TH`EME 3 INSTITUT NATIONAL DE RECHERCHE EN INFORMATIQUE ET EN AUTOMATIQUE  A Variational Approach to Multi-Modal Image Matching Gerardo Hermosillo Christophe Chefd’Hotel and Olivier Faugeras N° 4117 February 16, 2001  Unit´e de recherche INRIA Sophia Antipolis2004, route des Lucioles, B.P. 93, 06902 Sophia Antipolis Cedex (France) T´el´ephone : 04 92 38 77 77 - International : +33 4 92 38 77 77 — Fax : 04 92 38 77 65 - International : +33 4 92 38 77 65 A Variational Approach to Multi-Modal ImageMatching Gerardo Hermosillo Christophe Chefd’Hotel and Olivier Faugeras Th`eme 3 — Interaction homme-machine,images, donn´ees, connaissancesProjet RobotvisRapport de recherche n° 4117 — February 16, 2001 — 34 pages Abstract:  We address the problem of non-parametric multi-modal image match-ing. We propose a generic framework which relies on a global variational formula-tion and show its versatility through three different multi-modal registration meth-ods : supervised registration by joint intensity learning, maximization of the mutualinformation and maximization of the correlation ratio. Regularization is performedby using a functional borrowed from linear elasticity theory. We also consider ageometry-driven regularization method. Experiments on synthetic images and pre-liminary results on the realignment of MRI datasets are presented. Key-words:  Multi-modal Image Matching, Variational Methods, Registration,Optical Flow, Mutual Information, Correlation Ratio. A short version of this report has been submitted to the IEEE Workshop on Variational andLevel Set Methods in Computer Vision (VLSM01).This work was partially supported by EC contract No QLG3-CT-2000-30161,Mapawamo.  Une Approche Variationnelle pour l’AppariementMultimodal d’Images R´esum´e :  Nous consid´erons le probl`eme du recalage non-rigide entre images demodalit´es diff´erentes. Nous proposons un cadre g´en´eral qui repose sur une for-mulation variationnelle, que nous appliquons sous la forme de trois algorithmes derecalage multimodal: recalage supervis´e par apprentissage de la loi jointe, maximi-sation de l’information mutuelle, et maximisation du rapport de corr´elation. Pourpermettre une r´egularisation de la solution, nous utilisons un op´erateur issu dela th´eorie de l’´elasticit´e. Nous consid´erons aussi une m´ethode de r´egularisationavec pr´eservation des contours. Des r´esultats exp´erimentaux pr´eliminaires sur desimages synth´etiques et des donn´ees IRM sont pr´esent´es. Mots-cl´es :  Mise en Correspondence Multimodale, M ´ ethodes Variationnelles, Flot Optique, Information Mutuelle, Rapport de Corr ´ elation.
Related Search
We Need Your Support
Thank you for visiting our website and your interest in our free products and services. We are nonprofit website to share and download documents. To the running of this website, we need your help to support us.

Thanks to everyone for your continued support.

No, Thanks