A Variational Approach to Multi-Modal Image Matching

Gerardo Hermosillo (1) , Christophe Chefd'Hotel , Olivier Faugeras

1 ROBOTVIS - Computer Vision and Robotics

We address the problem of non-parametric multi-modal image matching. We propose a generic framework which relies on a global variational formulation and show its versatility through three different multi-modal registration methods : supervised registration by joint intensity learning, maximization of the mutual information and maximization of the correlation ratio. Regulariz- ation is performed by using a functional borrowed from linear elasticity theory. We also consider a geometry-driven regularization method. Experiments on synthetic images and preliminary results on the realignment of MRI datasets are presented.

Mots clés: MULTI-MODAL IMAGE MATCHING; VARIATIONAL METHODS; REGISTRATION; OPTICAL FLOW; MUTUAL INFORMATION; CORRELATION RATIO

Domaines: Autre [cs.OH]

Gerardo Hermosillo, Christophe Chefd'Hotel, Olivier Faugeras. A Variational Approach to Multi-Modal Image Matching. RR-4117, INRIA. 2001. ⟨inria-00072513⟩