Curvature-driven diffusion-based mathematical image registration models

doi:10.1186/1687-1847-2012-193

Curvature-driven diffusion-based mathematical image registration models

2012-11-07

2

OA

AI

DOI：10.1186/1687-1847-2012-193

Original

Original request for help

Save

Abstract

En 中文

This paper introduces several mathematical image registration models. Image registration, an ill-posed optimization problem, is formulated as the minimization of the sum of an image similarity metric and a regularization term. Curvature-driven diffusion-based techniques, in particular Perona-Malik, anisotropic diffusion, mean curvature motion (MCM), affine invariant MCM (AIMCM), are employed as a regularization term in this optimal control formulation. Adopting the steepest-descent marching with an artificial time t, Euler-Lagrange (EL) equations with homogeneous Neumann boundary conditions are obtained. These EL equations are approximately solved by the explicit Petrov-Galerkin scheme. The method is applied to the registration of brain MR images of size 257x257. Computational results indicate that all these regularization terms produce similarly good registration quality but that the cost associated with the AIMCM approach is, on average, less than that for the others.

Keywords:

sum of squared differences

inverse problems

computational modeling

Petrov-Galerkin scheme

image registration

Curvature-driven diffusion-based mathematical image registration models

Abstract

Journal

Organization