A new algorithm for non-rigid point matching
- 7 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2 (10636919) , 44-51
- https://doi.org/10.1109/cvpr.2000.854733
Abstract
We present a new robust point matching algorithm (RPM) that can jointly estimate the correspondence and non-rigid transformations between two point-sets that may be of different sizes. The algorithm utilizes the soft assign for the correspondence and the thin-plate spline for the non-rigid mapping. Embedded within a deterministic annealing framework, the algorithm can automatically reject a fraction of the points as outliers. Experiments on both 2D synthetic point-sets with varying degrees of deformation, noise and outliers, and on real 3D sulcal point-sets (extracted from brain MRI) demonstrate the robustness of the algorithm.Keywords
This publication has 22 references indexed in Scilit:
- Automatic labelling of the human cortical surface using sulcal basinsMedical Image Analysis, 2000
- Registration of Cortical Anatomical Structures via Robust 3D Point MatchingPublished by Springer Nature ,1999
- New algorithms for 2D and 3D point matchingPattern Recognition, 1998
- A robust point-matching algorithm for autoradiograph alignmentMedical Image Analysis, 1997
- Multi-Level Shape Representation Using Global Deformations and Locally Adaptive Finite ElementsInternational Journal of Computer Vision, 1997
- Modal matching for correspondence and recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1995
- The invisible hand algorithm: Solving the assignment problem with statistical physicsNeural Networks, 1994
- Feature-based correspondence: an eigenvector approachImage and Vision Computing, 1992
- An algorithm for associating the features of two imagesProceedings Of The Royal Society B-Biological Sciences, 1991
- Principal warps: thin-plate splines and the decomposition of deformationsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1989