Two and Three Dimensional Image Registration Based on B-Spline Composition and Level Sets

Chiu Ling Chan, Cosmin Anitescu, Yongjie Zhang, Timon Rabczuk

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Amethod for non-rigid image registration that is suitable for large deformations is presented. Conventional registration methods embed the image in a B-spline object, and the image is evolved by deforming the B-spline object. In this work, we represent the image using B-spline and deform the image using a composition approach. We also derive a computationally efficient algorithm for calculating the B-spline coefficients and gradients of the image by adopting ideas from signal processing using image filters. We demonstrate the application of our method on several different types of 2D and 3D images and compare it with existing methods.

Original languageEnglish
Pages (from-to)600-622
Number of pages23
JournalCommunications in Computational Physics
Volume21
Issue number2
DOIs
Publication statusPublished - 2017 Feb 1
Externally publishedYes

Fingerprint

splines
image filters
signal processing
gradients
coefficients

Keywords

  • B-spline
  • free-form deformation
  • Image registration
  • level set

ASJC Scopus subject areas

  • Physics and Astronomy (miscellaneous)

Cite this

Two and Three Dimensional Image Registration Based on B-Spline Composition and Level Sets. / Chan, Chiu Ling; Anitescu, Cosmin; Zhang, Yongjie; Rabczuk, Timon.

In: Communications in Computational Physics, Vol. 21, No. 2, 01.02.2017, p. 600-622.

Research output: Contribution to journalArticle

Chan, Chiu Ling ; Anitescu, Cosmin ; Zhang, Yongjie ; Rabczuk, Timon. / Two and Three Dimensional Image Registration Based on B-Spline Composition and Level Sets. In: Communications in Computational Physics. 2017 ; Vol. 21, No. 2. pp. 600-622.
@article{2d6ad5b6b82149f38ac6a0a23a71ded7,
title = "Two and Three Dimensional Image Registration Based on B-Spline Composition and Level Sets",
abstract = "Amethod for non-rigid image registration that is suitable for large deformations is presented. Conventional registration methods embed the image in a B-spline object, and the image is evolved by deforming the B-spline object. In this work, we represent the image using B-spline and deform the image using a composition approach. We also derive a computationally efficient algorithm for calculating the B-spline coefficients and gradients of the image by adopting ideas from signal processing using image filters. We demonstrate the application of our method on several different types of 2D and 3D images and compare it with existing methods.",
keywords = "B-spline, free-form deformation, Image registration, level set",
author = "Chan, {Chiu Ling} and Cosmin Anitescu and Yongjie Zhang and Timon Rabczuk",
year = "2017",
month = "2",
day = "1",
doi = "10.4208/cicp.OA-2016-0042",
language = "English",
volume = "21",
pages = "600--622",
journal = "Communications in Computational Physics",
issn = "1815-2406",
publisher = "Global Science Press",
number = "2",

}

TY - JOUR

T1 - Two and Three Dimensional Image Registration Based on B-Spline Composition and Level Sets

AU - Chan, Chiu Ling

AU - Anitescu, Cosmin

AU - Zhang, Yongjie

AU - Rabczuk, Timon

PY - 2017/2/1

Y1 - 2017/2/1

N2 - Amethod for non-rigid image registration that is suitable for large deformations is presented. Conventional registration methods embed the image in a B-spline object, and the image is evolved by deforming the B-spline object. In this work, we represent the image using B-spline and deform the image using a composition approach. We also derive a computationally efficient algorithm for calculating the B-spline coefficients and gradients of the image by adopting ideas from signal processing using image filters. We demonstrate the application of our method on several different types of 2D and 3D images and compare it with existing methods.

AB - Amethod for non-rigid image registration that is suitable for large deformations is presented. Conventional registration methods embed the image in a B-spline object, and the image is evolved by deforming the B-spline object. In this work, we represent the image using B-spline and deform the image using a composition approach. We also derive a computationally efficient algorithm for calculating the B-spline coefficients and gradients of the image by adopting ideas from signal processing using image filters. We demonstrate the application of our method on several different types of 2D and 3D images and compare it with existing methods.

KW - B-spline

KW - free-form deformation

KW - Image registration

KW - level set

UR - http://www.scopus.com/inward/record.url?scp=85012914372&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85012914372&partnerID=8YFLogxK

U2 - 10.4208/cicp.OA-2016-0042

DO - 10.4208/cicp.OA-2016-0042

M3 - Article

VL - 21

SP - 600

EP - 622

JO - Communications in Computational Physics

JF - Communications in Computational Physics

SN - 1815-2406

IS - 2

ER -