Paper Details: Downloads: 801
Serial Number: P1150847509
Title: A Fast Medical Image Registration using Feature Points
Authors: G. Khaissidi and H. Tairi and A. Aarab
Abstract: In feature-based registration approach, the feature matching step and transform model estimation step are associated and usually conducted in a sequential way. In this paper, we propose a fully non supervised methodology dedicated to the fast registration of medical images. We adopt a method that integrates the both steps into one. First, the points of interest are automatically extracted from both images. Then, an algorithm based on Hough transform gives directly a rigid transformation, which allows information transfer between both modalities. Validation study is conducted under a series of controlled experiments and test on IRM images and a comparison study where the matching of the extracted points is established with a correlation technique combined to a relaxation technique. The LMS method is then used to estimate the registration parameters.
Keywords: registration, medical imagery, interest points, matching, ZNCC, SSD.
Journal/Conference: International Journal of Graphics, Vision and Image Processing
Volume: 9
Issue: 3
Submission Date: 11/21/2008 12:00:00 AM
Review Date: 1/9/2009 12:00:00 AM
Publishing Date: 2/24/2009 12:00:00 AM
Article Downloads: 801
Download:

Facebook