سال انتشار: ۱۳۸۴

محل انتشار: دوازدهمین کنفرانس مهندسی پزشکی ایران

تعداد صفحات: ۷

نویسنده(ها):

Sabalan Daneshvar – Department of Electrical Engineering, Tarbiat modares University
Hassan Ghassemian – Department of Electrical Engineering, Tarbiat modares University

چکیده:

Medicl images are increasingly being used in healthcare and medical research. There is, consequently, widespread interest in accurately relting information in the different images for diagnosis, treatment and basic science, In thes paper two automated registration algorithms is studied. First method is image registration based on extraction of the most well-known image features-edge and requires no future segmentation. Second method uses a new region-based similarity metric, which enables accurate registration of images of large contrast differences. Experimental results are presented to demonstrate that the algorithm is effective for aligning images from single or multiple imaging modalities without the use of any fiducial markers.