ABSTRACT
This chapter presents a global and elastic shape registration technique using the iterative closest point algorithm. It discusses the registration between two different surface models based on explicit point mappings. Medical shapes registration and alignment is an important complex problem in medical imaging. Mutual information measures the amount of information matching between the source and target shape images. Global motion parameters were estimated by maximizing the mutual information. The derived energy function is required to be minimized by moving the grid positions to get the correct mapping over shape boundaries. The iterative closest point algorithm is a widely applied method for the registration of some data sets of points. The teeth dataset is first segmented by a variational model for surface evolution based on region statistics. Image registration is of great interest and will be considered for future research. Principal component analysis can be performed to handle the modeling process.
