A new image registration scheme based on curvature scale space curve matching

Ming Cui, Peter Wonka, Anshuman Razdan, Jiuxiang Hu

Research output: Contribution to journalArticle

22 Citations (Scopus)

Abstract

We propose a new image registration scheme for remote sensing images. This scheme includes three steps in sequence. First, a segmentation process is performed on the input image pair. Then the boundaries of the segmented regions in two images are extracted and matched. These matched regions are called confidence regions. Finally, a non-linear optimization is performed in the matched regions only to obtain a global set of transform parameters. Experiments show that this scheme is more robust and converges faster than registration of the original image pair. We also develop a new curve-matching algorithm based on curvature scale space to facilitate the second step.

Original languageEnglish (US)
Pages (from-to)607-618
Number of pages12
JournalVisual Computer
Volume23
Issue number8
DOIs
StatePublished - Aug 2007

Fingerprint

Image registration
Remote sensing
Experiments

Keywords

  • Curvature scale space
  • Curve matching
  • Image registration

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Software

Cite this

A new image registration scheme based on curvature scale space curve matching. / Cui, Ming; Wonka, Peter; Razdan, Anshuman; Hu, Jiuxiang.

In: Visual Computer, Vol. 23, No. 8, 08.2007, p. 607-618.

Research output: Contribution to journalArticle

Cui, Ming ; Wonka, Peter ; Razdan, Anshuman ; Hu, Jiuxiang. / A new image registration scheme based on curvature scale space curve matching. In: Visual Computer. 2007 ; Vol. 23, No. 8. pp. 607-618.
@article{7ef38fb65a2044e4ab4d439005a0021f,
title = "A new image registration scheme based on curvature scale space curve matching",
abstract = "We propose a new image registration scheme for remote sensing images. This scheme includes three steps in sequence. First, a segmentation process is performed on the input image pair. Then the boundaries of the segmented regions in two images are extracted and matched. These matched regions are called confidence regions. Finally, a non-linear optimization is performed in the matched regions only to obtain a global set of transform parameters. Experiments show that this scheme is more robust and converges faster than registration of the original image pair. We also develop a new curve-matching algorithm based on curvature scale space to facilitate the second step.",
keywords = "Curvature scale space, Curve matching, Image registration",
author = "Ming Cui and Peter Wonka and Anshuman Razdan and Jiuxiang Hu",
year = "2007",
month = "8",
doi = "10.1007/s00371-007-0164-1",
language = "English (US)",
volume = "23",
pages = "607--618",
journal = "Visual Computer",
issn = "0178-2789",
publisher = "Springer Verlag",
number = "8",

}

TY - JOUR

T1 - A new image registration scheme based on curvature scale space curve matching

AU - Cui, Ming

AU - Wonka, Peter

AU - Razdan, Anshuman

AU - Hu, Jiuxiang

PY - 2007/8

Y1 - 2007/8

N2 - We propose a new image registration scheme for remote sensing images. This scheme includes three steps in sequence. First, a segmentation process is performed on the input image pair. Then the boundaries of the segmented regions in two images are extracted and matched. These matched regions are called confidence regions. Finally, a non-linear optimization is performed in the matched regions only to obtain a global set of transform parameters. Experiments show that this scheme is more robust and converges faster than registration of the original image pair. We also develop a new curve-matching algorithm based on curvature scale space to facilitate the second step.

AB - We propose a new image registration scheme for remote sensing images. This scheme includes three steps in sequence. First, a segmentation process is performed on the input image pair. Then the boundaries of the segmented regions in two images are extracted and matched. These matched regions are called confidence regions. Finally, a non-linear optimization is performed in the matched regions only to obtain a global set of transform parameters. Experiments show that this scheme is more robust and converges faster than registration of the original image pair. We also develop a new curve-matching algorithm based on curvature scale space to facilitate the second step.

KW - Curvature scale space

KW - Curve matching

KW - Image registration

UR - http://www.scopus.com/inward/record.url?scp=34547253244&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34547253244&partnerID=8YFLogxK

U2 - 10.1007/s00371-007-0164-1

DO - 10.1007/s00371-007-0164-1

M3 - Article

AN - SCOPUS:34547253244

VL - 23

SP - 607

EP - 618

JO - Visual Computer

JF - Visual Computer

SN - 0178-2789

IS - 8

ER -