Geodesic Active Fields - A Geometric Framework for Image Registration

In this paper we present a novel geometric framework called geodesic active fields for general image registration. In image registration, one looks for the underlying deformation field that best maps one image onto another. This is a classic ill-posed inverse problem, which is usually solved by adding a regularization term. Here, we propose to embed the deformation field in a weighted minimal surface problem. The energy of the deformation field is measured with the Polyakov energy weighted by a suitable image distance, borrowed from standard registration models. Minimizing this weighted Polyakov energy drives the deformation field toward a minimal surface, while being attracted by the solution of the registration problem. Our geometric framework involves two important contributions. Firstly, our general formulation for registration works on any parametrizable, smooth and differentiable surface, including non-flat and multiscale images. Secondly, to the best of our knowledge, this method is the first re-parametrization invariant registration method introduced in the literature.

Published in:
ICNAAM 2010: International Conference of Numerical Analysis and Applied Mathematics 2010, 1027-1030
Presented at:
8th ICNAAM, Rhodos, Greece, September 19-25, 2010
Amer Inst Physics, 2 Huntington Quadrangle, Ste 1No1 D, Melville, Ny 11747-4501 Usa
Invited to the Session on "Geometric Models and Applications in Image and Surface Processing" at 8th ICNAAM conference

 Record created 2010-10-01, last modified 2018-09-13

zossoICNAAM - Download fulltextPDF
zossoICNAAM2010 - Download fulltextPDF
Rate this document:

Rate this document:
(Not yet reviewed)