Year: 2014
Journal of Fiber Bioengineering and Informatics, Vol. 7 (2014), Iss. 3 : pp. 409–418
Abstract
Image registration is a vital research branch in medical image processing and analysis. In this paper, we proposed a new framework for rigid medical image registration. It can also be regarded as a pre-processing of non-rigid image registration algorithms. The interest of the algorithm lies in its simplicity and high effciency. In the registration algorithm, we firstly segmented the reference image and float image into two parts: tissue parts and background parts. Then the centers of the two images were located through performing distance transform on the two segmented tissue images. Finally, we detected the longest radius of the two tissue regions, by which we determined the rotating angle. We tested the registration algorithm on dozens of medical images, and the experimental results show us that the algorithm is competent for medical image registration.
You do not have full access to this article.
Already a Subscriber? Sign in as an individual or via your institution
Journal Article Details
Publisher Name: Global Science Press
Language: English
DOI: https://doi.org/10.3993/jfbi09201410
Journal of Fiber Bioengineering and Informatics, Vol. 7 (2014), Iss. 3 : pp. 409–418
Published online: 2014-01
AMS Subject Headings:
Copyright: COPYRIGHT: © Global Science Press
Pages: 10
Keywords: Image Registration