Title :
A novel hierarchical medical image registration method based on multiscale and contour line
Author :
Hu, Jinyan ; Yang, Yunfeng ; Su, Zhixun
Author_Institution :
Sch. of Math. Sci. & Technol., Northeast Pet. Univ., Daqing, China
Abstract :
Medical image registration is the key technology in the modern medical images processing field. A rapid and effective hierarchical registration method of the medical images based on multiscale transform and contour line is proposed in the paper, and it can be accomplished automatically. Firstly, edge features of the couple images are extracted by Canny operator. Then the contour lines of the couple images are extracted based on the edge features. Secondly, Principal Axis method is used to accomplish the rough registration based on the contour lines. Thirdly, multiscale image sets which obtained by a new multiscale transform are used to accomplish the couple images´ accurate registration based on the rough registration. Experiment results show that this method not only can achieve more accurate registration results, but also can reduce the computational time greatly. The accurate registration results also can be achieved in the noisy environment.
Keywords :
image registration; medical image processing; transforms; Canny operator; contour line; edge features; hierarchical registration method; medical image registration method; medical images processing field; multiscale image sets; multiscale line; multiscale transform; principal axis method; rough registration; Biomedical imaging; Educational institutions; Feature extraction; Image edge detection; Image registration; Mutual information; Transforms; Contour line; Hierarchical; Multiscale Transform; Registration;
Conference_Titel :
Systems and Informatics (ICSAI), 2012 International Conference on
Conference_Location :
Yantai
Print_ISBN :
978-1-4673-0198-5
DOI :
10.1109/ICSAI.2012.6223401