A Survey On Non-Rigid Image Registration

PhD Qualifying Examination


Title: "A Survey On Non-Rigid Image Registration"

by

Mr. Wai-King So


Abstract:

Image registration is widely used in different areas. It plays an 
important role in medical image analysis, group analysis and statistical 
parametric mapping. In this survey, the previous approaches for non-rigid 
medical image registration are reviewed and analyzed. They are divided 
into three major classes. First, the landmark based methods use prior 
knowledge obtained from manually located landmark points on the input 
images. Features from these landmark points are extracted to determine the 
optimal transformation. Second, the intensity based methods use similarity 
measure function to guide the registration process, based on the intensity 
distributions of the input images. Third, the feature based methods use 
feature vectors as signatures for each voxel. Hence, the registration 
problem is formulated as a feature matching and optimization problem.

Together with the advantages and disadvantages of each class of methods, 
some possible directions in non-rigid medical image registration will be 
discussed in this survey.


Date:                   Thursday, 19 August 2010

Time:                   10:00am - 12:00 noon

Venue:                  Room 3501
                         lifts 25/26

Committee Members:      Dr. Albert Chung (Supervisor)
                         Dr. Huamin Qu (Chairperson)
                         Dr. Raymond Wong
 			Prof. Dit-Yan Yeung


**** ALL are Welcome ****