Image registration using hierarchical B-splines

Zhiyong Xie, Gerald E. Farin

Research output: Contribution to journalArticle

88 Citations (Scopus)

Abstract

Hierarchical B-splines have been widely used for shape modeling since their discovery by Forsey and Bartels. In this paper, we present an application of this concept, in the form of free-form deformation, to image registration by matching two images at increasing levels of detail. Results using MRI brain data are presented that demonstrate high degrees of matching while unnecessary distortions are avoided. We compare our results with the nonlinear ICP (Iterative Closest Point) algorithm (used for landmark-based registration) and optical flow (used for intensity-based registration).

Original languageEnglish (US)
Pages (from-to)85-94
Number of pages10
JournalIEEE Transactions on Visualization and Computer Graphics
Volume10
Issue number1
DOIs
StatePublished - Jan 2004

Fingerprint

Optical flows
Image registration
Splines
Magnetic resonance imaging
Brain

Keywords

  • Free form deformation
  • Hierarchical B-splines
  • Image registration
  • Iterative closest point
  • Optical flow
  • Scattered data approximation

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Software

Cite this

Image registration using hierarchical B-splines. / Xie, Zhiyong; Farin, Gerald E.

In: IEEE Transactions on Visualization and Computer Graphics, Vol. 10, No. 1, 01.2004, p. 85-94.

Research output: Contribution to journalArticle

Xie, Zhiyong ; Farin, Gerald E. / Image registration using hierarchical B-splines. In: IEEE Transactions on Visualization and Computer Graphics. 2004 ; Vol. 10, No. 1. pp. 85-94.
@article{0bcc3a24c8ad4897a46bf18cd7028004,
title = "Image registration using hierarchical B-splines",
abstract = "Hierarchical B-splines have been widely used for shape modeling since their discovery by Forsey and Bartels. In this paper, we present an application of this concept, in the form of free-form deformation, to image registration by matching two images at increasing levels of detail. Results using MRI brain data are presented that demonstrate high degrees of matching while unnecessary distortions are avoided. We compare our results with the nonlinear ICP (Iterative Closest Point) algorithm (used for landmark-based registration) and optical flow (used for intensity-based registration).",
keywords = "Free form deformation, Hierarchical B-splines, Image registration, Iterative closest point, Optical flow, Scattered data approximation",
author = "Zhiyong Xie and Farin, {Gerald E.}",
year = "2004",
month = "1",
doi = "10.1109/TVCG.2004.1260760",
language = "English (US)",
volume = "10",
pages = "85--94",
journal = "IEEE Transactions on Visualization and Computer Graphics",
issn = "1077-2626",
publisher = "IEEE Computer Society",
number = "1",

}

TY - JOUR

T1 - Image registration using hierarchical B-splines

AU - Xie, Zhiyong

AU - Farin, Gerald E.

PY - 2004/1

Y1 - 2004/1

N2 - Hierarchical B-splines have been widely used for shape modeling since their discovery by Forsey and Bartels. In this paper, we present an application of this concept, in the form of free-form deformation, to image registration by matching two images at increasing levels of detail. Results using MRI brain data are presented that demonstrate high degrees of matching while unnecessary distortions are avoided. We compare our results with the nonlinear ICP (Iterative Closest Point) algorithm (used for landmark-based registration) and optical flow (used for intensity-based registration).

AB - Hierarchical B-splines have been widely used for shape modeling since their discovery by Forsey and Bartels. In this paper, we present an application of this concept, in the form of free-form deformation, to image registration by matching two images at increasing levels of detail. Results using MRI brain data are presented that demonstrate high degrees of matching while unnecessary distortions are avoided. We compare our results with the nonlinear ICP (Iterative Closest Point) algorithm (used for landmark-based registration) and optical flow (used for intensity-based registration).

KW - Free form deformation

KW - Hierarchical B-splines

KW - Image registration

KW - Iterative closest point

KW - Optical flow

KW - Scattered data approximation

UR - http://www.scopus.com/inward/record.url?scp=4243157500&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=4243157500&partnerID=8YFLogxK

U2 - 10.1109/TVCG.2004.1260760

DO - 10.1109/TVCG.2004.1260760

M3 - Article

C2 - 15382700

AN - SCOPUS:4243157500

VL - 10

SP - 85

EP - 94

JO - IEEE Transactions on Visualization and Computer Graphics

JF - IEEE Transactions on Visualization and Computer Graphics

SN - 1077-2626

IS - 1

ER -