%0 Journal Article
%T Registration of the Cone Beam CT and Blue-Ray Scanned Dental Model Based on the Improved ICP Algorithm
%A Xue Mei
%A Zhenhua Li
%A Songsong Xu
%A Xiaoyan Guo
%J International Journal of Biomedical Imaging
%D 2014
%I Hindawi Publishing Corporation
%R 10.1155/2014/348740
%X Multimodality image registration and fusion has complementary significance for guiding dental implant surgery. As the needs of the different resolution image registration, we develop an improved Iterative Closest Point (ICP) algorithm that focuses on the registration of Cone Beam Computed Tomography (CT) image and high-resolution Blue-light scanner image. The proposed algorithm includes two major phases, coarse and precise registration. Firstly, for reducing the matching interference of human subjective factors, we extract feature points based on curvature characteristics and use the improved three pointĄ¯s translational transformation method to realize coarse registration. Then, the feature point set and reference point set, obtained by the initial registered transformation, are processed in the precise registration step. Even with the unsatisfactory initial values, this two steps registration method can guarantee the global convergence and the convergence precision. Experimental results demonstrate that the method has successfully realized the registration of the Cone Beam CT dental model and the blue-ray scanner model with higher accuracy. So the method could provide researching foundation for the relevant software development in terms of the registration of multi-modality medical data. 1. Introduction With the rapid development of the image processing, reverse engineering, computer-aided design, and image guidance play an important role in dental implant surgery [1]. A number of dental and jaw imaging modalities, including video imaging [2], Computed Tomography (CT) [3], and magnetic radiotherapy imaging (MRI) [4], are used in image-aided dental implant surgery. Performing the multimodality image registration from different imaging devices has complementary significance for guiding dental implant surgery. When dentists design schemes, they want to consider the morphology of the soft tissue and the hard tissue together. CT image and visible spectrum image fusion models [5] can multiply various factors and help the dentists achieve the optimal implant scheme. Traditional registrations of Cone Beam Computed Tomography (CBCT) and other three-dimensional scanner models mainly rely on the fiducial markers method, which need to manually select the feature points. In [6¨C8], manual feature selecting methods have been tried for the registration of the mandible CT and plaster cast of the dental models. Because the images are complex and the location accuracy is limited by the experience of the operator and the operating state, the manual feature selecting
%U http://www.hindawi.com/journals/ijbi/2014/348740/