Principal Warps: Thin-Plate Splines and the Decomposition of Deformations
IEEE Transactions on Pattern Analysis and Machine Intelligence
An adaptive method for image registration
Pattern Recognition
Image warping by radial basis functions: applications to facial expressions
CVGIP: Graphical Models and Image Processing
Deformations incorporating rigid structures
Computer Vision and Image Understanding
CBMS '95 Proceedings of the Eighth Annual IEEE Symposium on Computer-Based Medical Systems
A locally constrained radial basis function for registration and warping of images
Pattern Recognition Letters
Diffeomorphic nonlinear transformations: a local parametric approach for image registration
IPMI'05 Proceedings of the 19th international conference on Information Processing in Medical Imaging
Diffeomorphic registration using b-splines
MICCAI'06 Proceedings of the 9th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part II
Topology preserving deformable image matching using constrained hierarchical parametric models
IEEE Transactions on Image Processing
IEEE Transactions on Image Processing
A comparative study of transformation functions for nonrigid image registration
IEEE Transactions on Image Processing
Hi-index | 0.10 |
Many Radial Basis Function (RBF)-based transformations are used to model the deformations in image registration, and they have different topology preservation properties. This paper compares analytically and experimentally the topology preservation performance of compact-support thin-plate Spline (CSTPS), locally constrained cosine (Cos), Wendland, Gaussian, Buhmann and Wu functions in landmark-based image registration. In addition, the topology preservation characteristics of thin-plate Spline (TPS) and elastic body Spline (EBS)-based transformations are compared for global-support deformations. The comparative results show that, for local deformation CSTPS and Buhmann preserve topology better than others. The Cos and Gaussian functions could easily produce topology violations for relatively dense-landmark matching. For global-support transformations, CSTPS, Wendland @j"3","1, Buhmann, Wu and TPS outperformed others because they preserve topology better. The Cos, Gaussian and EBS functions perform poorly because folds and tears of the deformation surface occur easily. With very large support, CSTPS produces similar results as TPS, and Wendland @j"3","1 has similar performance with Wu functions. Also, Cos and Gaussian performed similarly in this case. In the experiments, these theoretical results are evaluated extensively using transformations on random point sets, artificial images, and medical images.