Self-adaptive parameter computing for deformable registration with gabor transformation
Murong Jiang · Yunnan Daxue xuebao. Shehui kexue ban · 2009
Image Registration is the basic of the image fuses. If the image includes many finer textures,most registered methods based on the intensity similarity measures can not produce the high precision result.This paper discuss a PDE-based image registration method with adaptive parameter computing.This paper present the diffusion PDE model to describe the registration problem,detail the adaptive parameter computing method for searching the weight parameter correspond to the local degrees of variability in the match,use Gabor function to split the image into geometric part and texture part,then register these two parts separately. The experimental results show that this method can improve the registering precision.