A novel dynamic multilevel technique for image registration

Yue Jia, Yongjie Zhang, Timon Rabczuk

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

We present a novel dynamic multilevel technique for solving image registration problems. The development is carried out to construct a spatial transformation based on cubic B-spline basis functions and determine the control points dynamically. Unlike FEM-based image registration methods, we do not have the difficulty of solving a complicated matrix system. In addition, the presented method is enhanced by a multilevel technique, which makes it more efficient and flexible. The numerical results and several comparison studies on real bio-medical images show our technique is stable, accurate and fast, especially for large deformation registration problems.

Original languageEnglish
Pages (from-to)909-925
Number of pages17
JournalComputers and Mathematics with Applications
Volume69
Issue number9
DOIs
Publication statusPublished - 2015 May 1
Externally publishedYes

Fingerprint

Image registration
Image Registration
Splines
Cubic B-spline
B-spline Function
Control Points
Large Deformation
Medical Image
Finite element method
Registration
Basis Functions
Numerical Results

Keywords

  • Bio-medical images
  • Cubic B-splines
  • Dynamical multilevel modeling
  • Image registration
  • Large deformation

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Modelling and Simulation
  • Computational Mathematics

Cite this

A novel dynamic multilevel technique for image registration. / Jia, Yue; Zhang, Yongjie; Rabczuk, Timon.

In: Computers and Mathematics with Applications, Vol. 69, No. 9, 01.05.2015, p. 909-925.

Research output: Contribution to journalArticle

Jia, Yue ; Zhang, Yongjie ; Rabczuk, Timon. / A novel dynamic multilevel technique for image registration. In: Computers and Mathematics with Applications. 2015 ; Vol. 69, No. 9. pp. 909-925.
@article{74c88325f9074f64a92643f9f0ca86c0,
title = "A novel dynamic multilevel technique for image registration",
abstract = "We present a novel dynamic multilevel technique for solving image registration problems. The development is carried out to construct a spatial transformation based on cubic B-spline basis functions and determine the control points dynamically. Unlike FEM-based image registration methods, we do not have the difficulty of solving a complicated matrix system. In addition, the presented method is enhanced by a multilevel technique, which makes it more efficient and flexible. The numerical results and several comparison studies on real bio-medical images show our technique is stable, accurate and fast, especially for large deformation registration problems.",
keywords = "Bio-medical images, Cubic B-splines, Dynamical multilevel modeling, Image registration, Large deformation",
author = "Yue Jia and Yongjie Zhang and Timon Rabczuk",
year = "2015",
month = "5",
day = "1",
doi = "10.1016/j.camwa.2015.02.010",
language = "English",
volume = "69",
pages = "909--925",
journal = "Computers and Mathematics with Applications",
issn = "0898-1221",
publisher = "Elsevier Limited",
number = "9",

}

TY - JOUR

T1 - A novel dynamic multilevel technique for image registration

AU - Jia, Yue

AU - Zhang, Yongjie

AU - Rabczuk, Timon

PY - 2015/5/1

Y1 - 2015/5/1

N2 - We present a novel dynamic multilevel technique for solving image registration problems. The development is carried out to construct a spatial transformation based on cubic B-spline basis functions and determine the control points dynamically. Unlike FEM-based image registration methods, we do not have the difficulty of solving a complicated matrix system. In addition, the presented method is enhanced by a multilevel technique, which makes it more efficient and flexible. The numerical results and several comparison studies on real bio-medical images show our technique is stable, accurate and fast, especially for large deformation registration problems.

AB - We present a novel dynamic multilevel technique for solving image registration problems. The development is carried out to construct a spatial transformation based on cubic B-spline basis functions and determine the control points dynamically. Unlike FEM-based image registration methods, we do not have the difficulty of solving a complicated matrix system. In addition, the presented method is enhanced by a multilevel technique, which makes it more efficient and flexible. The numerical results and several comparison studies on real bio-medical images show our technique is stable, accurate and fast, especially for large deformation registration problems.

KW - Bio-medical images

KW - Cubic B-splines

KW - Dynamical multilevel modeling

KW - Image registration

KW - Large deformation

UR - http://www.scopus.com/inward/record.url?scp=84926417828&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84926417828&partnerID=8YFLogxK

U2 - 10.1016/j.camwa.2015.02.010

DO - 10.1016/j.camwa.2015.02.010

M3 - Article

VL - 69

SP - 909

EP - 925

JO - Computers and Mathematics with Applications

JF - Computers and Mathematics with Applications

SN - 0898-1221

IS - 9

ER -