Vectorial Total Variation-Based Regularization for Variational Image Registration

To use interdependence between the primary components of the deformation field for smooth and non-smooth registration problems, the channel-by-channel total variation- or standard vectorial total variation (SVTV)-based regularization has been extended to a more flexible and efficient technique, allo...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on image processing 2013-11, Vol.22 (11), p.4551-4559
Main Author: Chumchob, N.
Format: Article
Language:English
Subjects:
Algorithms
Applied sciences
Approximation methods
Artificial Intelligence
Deformable image registration
Exact sciences and technology
Image Enhancement - methods
Image Interpretation, Computer-Assisted - methods
Image processing
Image registration
Imaging
Information, signal and communications theory
inverse problems
Materials
Minimization
nonlinear multigrid
Pattern Recognition, Automated - methods
regularization
Reproducibility of Results
Sensitivity and Specificity
Signal processing
Telecommunications and information theory
variational image registration
vectorial total variation
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:To use interdependence between the primary components of the deformation field for smooth and non-smooth registration problems, the channel-by-channel total variation- or standard vectorial total variation (SVTV)-based regularization has been extended to a more flexible and efficient technique, allowing high quality regularization procedures. Based on this method, this paper proposes a fast nonlinear multigrid (NMG) method for solving the underlying Euler-Lagrange system of two coupled second-order nonlinear partial differential equations. Numerical experiments using both synthetic and realistic images not only confirm that the recommended VTV-based regularization yields better registration qualities for a wide range of applications than those of the SVTV-based regularization, but also that the proposed NMG method is fast, accurate, and reliable in delivering visually-pleasing registration results.
ISSN:1057-7149
1941-0042
DOI:10.1109/TIP.2013.2274749