By Topic


Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Jarc, A. ; Fac. of Electr. Eng., Ljubljana Univ. ; Rogelj, P. ; Kovacic, S.

The aim of our research is to analyse the importance of texture information for registration of a DRR (digital reconstructed radiograph) and EPI (electronic portal image) medical images. In our research, texture features are extracted by Laws texture coefficients and used for computing registration criterion functions. The proposed feature based approach is compared to the commonly used approach, where a registration criterion function is computed directly from intensity features, i.e. grey values. For this purpose we observed accuracy of registration, the distinctiveness of local extrema and the distinctiveness of a global extremum of the criterion functions. These parameters are essential to achieve a correct image alignment. Our results show that for the given image modalities we can expect more robust and more correct registration when texture based criterion function instead of intensity based one is used

Published in:

Biomedical Imaging: From Nano to Macro, 2007. ISBI 2007. 4th IEEE International Symposium on

Date of Conference:

12-15 April 2007