Author(s):  
Andrew Adinetz ◽  
Jiri Kraus ◽  
Markus Axer ◽  
Marcel Huysegoms ◽  
Stefan Köhnen ◽  
...  

2013 ◽  
Vol 427-429 ◽  
pp. 1610-1613
Author(s):  
Xing Wei Yan ◽  
Jie Min Hu ◽  
Jun Zhang ◽  
Jian Wei Wan

Image registration is widely used in applications for mapping one image to another. As it is often formulated as a point matching problem, in this paper, a novel method, called the Geometric Inference (GI) algorithm, is proposed for feature point based image registration. Firstly, according to affine distance invariant, the global geometric relationship between collinear correspondences is deduced and used for collinear point matching. Secondly, utilizing affine area invariant, geometric relationship between noncollinear correspondences is inferred and used for noncollinear point matching. Finally, the best affine transformation can be discovered from the correspondences composed of the collinear and noncollinear corresponding point pairs. Experiments on synthesized and real data demonstrate that GI is well-adapt to image registration as it is fast and robust to missing points, outliers, and noise.


2015 ◽  
Vol 60 (22) ◽  
pp. 8767-8790 ◽  
Author(s):  
Bicao Li ◽  
Guanyu Yang ◽  
Jean Louis Coatrieux ◽  
Baosheng Li ◽  
Huazhong Shu

2011 ◽  
Author(s):  
Yong Li ◽  
Robert L. Stevenson

3D image registration of CT and MRI data is carried out using DTCWT sub bands by considering the features from all 64 bands. The features are selected by considering Mattes Mutual Information Metric and the optimizer algorithm estimates the optimum transformation parameters from all the 64 bands. Transformation parameters from eight low pass bands from each octave are averaged to identify optimum registration parameters. Similarly, for registration of high pass bands mean of transformation parameters from 56 bands are identified. The proposed registration algorithm is suitable for register multimodal medical images and the proposed algorithm is validated for more than 20 3D images. Mutual information and joint entropy is estimated to demonstrate the advantages of proposed algorithm overt that of intensity based algorithm. With features identified from 56 bands with six orientations the registered image is found to consist of features from both input images with closeness level measured to be within 12%.


Sign in / Sign up

Export Citation Format

Share Document