Image registration by normalized mapping

Qi Wang, Cuiming Zou, Yuan Yuan, Hongbing Lu, Pingkun Yan

Research output: Contribution to journalArticlepeer-review

16 Scopus citations

Abstract

A new non-rigid registration method is proposed for the bladder magnetic resonance (MR) images. The key point is normalized mapping, which transforms any image into an intermediate space. Under the uniform space, those anatomical feature points of different images are corresponded by rotating and scaling. In addition, the non-rigid registration is utilized under the application of groupwise registration. By registering a set of images, an unbiased template can be obtained. Based on this template, the analysis towards the group of images can be easily conducted. Experimental results demonstrate that the proposed method can register accurately the target image to the reference image.

Original languageEnglish
Pages (from-to)181-189
Number of pages9
JournalNeurocomputing
Volume101
DOIs
StatePublished - 4 Feb 2013
Externally publishedYes

Keywords

  • Groupwise registration
  • MR image
  • Manifold learning
  • Non-rigid registration
  • Normalized mapping

Fingerprint

Dive into the research topics of 'Image registration by normalized mapping'. Together they form a unique fingerprint.

Cite this