An efficient numerical method for mean curvature-based image registration model

Zhang, Jin and Chen, Ke and Chen, Fang and Yu, Bo (2017) An efficient numerical method for mean curvature-based image registration model. East Asian Journal on Applied Mathematics, 7 (1). pp. 125-142. ISSN 2079-7370 (https://doi.org/10.4208/eajam.200816.031216a)

[thumbnail of Zhang-etal-EAJAM-2017-An-efficient-numerical-method-for-mean-curvature-based-image-registration-model]
Preview
Text. Filename: Zhang-etal-EAJAM-2017-An-efficient-numerical-method-for-mean-curvature-based-image-registration-model.pdf
Accepted Author Manuscript
License: Strathprints license 1.0

Download (1MB)| Preview

Abstract

Mean curvature-based image registration model firstly proposed by Chumchob-Chen-Brito (2011) offered a better regularizer technique for both smooth and nonsmooth deformation fields. However, it is extremely challenging to solve efficiently this model and the existing methods are slow or become efficient only with strong assumptions on the smoothing parameter β. In this paper, we take a different solution approach. Firstly, we discretize the joint energy functional, following an idea of relaxed fixed point is implemented and combine with Gauss-Newton scheme with Armijo's Linear Search for solving the discretized mean curvature model and further to combine with a multilevel method to achieve fast convergence. Numerical experiments not only confirm that our proposed method is efficient and stable, but also it can give more satisfying registration results according to image quality.

ORCID iDs

Zhang, Jin, Chen, Ke ORCID logoORCID: https://orcid.org/0000-0002-6093-6623, Chen, Fang and Yu, Bo;