Medical Image Registration Based on Wavelet Transform Using Hausdorff Distance

Image registration is the process of overlaying two or more images of the same scene taken at different time, from different viewpoints, and/or by different sensors. We propose a new method of medical image registration based on wavelet transform using Hausdorff Distance. Firstly, the image was decomposed by wavelet transform. Secondly, using gradient vector flow detects feature points. Finally, using Hausdorff Distance matching sets of feature points. Theories and experiments indicated that this method has some advantages such as high precision and good robust.

[1]  Pedro F. Felzenszwalb.  Learning models for object recognition , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[2]  Jan Flusser,et al.  Image registration methods: a survey , 2003, Image Vis. Comput..

[3]  M.A. Tinati,et al.  2-step wavelet-based edge detection using gabor and cauchy directional wavelets , 2005, The 7th International Conference on Advanced Communication Technology, 2005, ICACT 2005..

[4]  Jiang Xiu-hua,et al.  Image registration based on Hausdorff distance , 2010, 2010 International Conference on Networking and Information Technology.