An Image Registration Method Combing Feature Constraint with Multilevel Strategy

Abstract:

A novel method combing feature constraint with multilevel strategy to improve simultaneously the registration accuracy and speed is proposed for non-parametric image registrations. To images between which the local difference is large, integrating feature constraint constructed with local structure information of images into objective function of image registration improves the registration accuracy. When applying feature constraint under multilevel strategy, parameter searching is prevented from entrapped into local extremum by using the optimization result on coarser levels as the starting points on finer levels; meanwhile traditional optimization methods without demanding intelligent optimization algorithms which consume more time can find the accurate registration parameter on finer levels, so registration speed is improved. Experimental results indicate that this method can finish fast and accurate registration for images between which there exists large local difference.

• Periodical: Applied Mechanics and Materials (Volumes 58-60)
• Pages: 286-291
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.58-60.286
• Online since: June 2011
• Authors: Hong Kui Xu, Ming Yan Jiang, Ming Qiang Yang
• Keywords: Feature Constraint, Multilevel Strategy, Non-Parametric Registration

References

[1] ZITOVA B, FLUSSER: Imag. & Vision Comput . Vol. 21(2003), p.9772.

[2] Gholipour A, Kehtarnavaz N, Briggs R, Devous M and Gopinath K: IEEE Trans Med Imaging Vol. 26(2007) Apr, p.427.

DOI: 10.1109/tmi.2007.892508

[3] SONG Zhenhuan, TANG Lingli and LI Chuanrong: Sience &Technology Review Vol. 25(2007), p.53.

[4] Peter Rogelj, Stanislav Kovačič: Similarity Measures for Non-Rigid Registration, In Boštjan Likar (Ed. ), Proceedings of Sixth Computer Vision Winter Workshop, Bled, Slovenia, February 7-9, 2001, pp.82-91.

[5] A. Roche, G. Malandain, and N. Ayache: Unifying maximum likelihood approaches in medical image registration. Int. J. of Imaging Syst. and Technology: Sp. issue on 3D imaging, Vol. 11(2000), p.71.

DOI: 10.1002/(sici)1098-1098(2000)11:1<71::aid-ima8>3.0.co;2-5

[6] M. Schröter,O. Sauer: Quasi-Newton Algorithms for Medical Image Registration. World Congress on Medical Physics and Biomedical Engineering, September 7 - 12, 2009, Munich, Germany, IFMBE Proceedings, Vol. 25/4(2010), p.433.

DOI: 10.1007/978-3-642-03882-2_115

[7] Jafar Ememipour, M. Mehdi Seyed Nejadr: Introduce a new inertia weight for particle swarm optimization. In: 2009 Fourth International Conference on Computer Sciences and Convergence Information Technology . 2009, p.1650.

DOI: 10.1109/iccit.2009.297

[8] Tom Vercauteren, Xavier Pennec, Aymeric Perchant, Nicholas Ayache: Diffeomorphic demons: efficient non-parametric image registration. NeuroImage (2009) Vol. 45, Issue: 1 Suppl, p. S61-S72.

DOI: 10.1016/j.neuroimage.2008.10.040

[9] Eldad Haber Jan Modersitzki : A Multilevel Method for Image Registration. SIAM Journal. on Scientific Computing / Volume 27 (2006)/ Issue 5 pp.1594-1607.

DOI: 10.1137/040608106

[10] So,R. Chung, A. : Multi-level non-rigid image registration using graph-cuts. 2009 IEEE International Conference on Acoustics, Speech and Signal Processing . On page(s): 397 - 400.

DOI: 10.1109/icassp.2009.4959604

[11] Jan Modersitzki : FAIR : flexible algorithms for image registration, Society for Industrial and Applied Mathematics Publisher (2009).

[12] BrainWeb: online simulated brain database on http: /www. bic. mni. mcgill. ca/brainweb.

[13] Hongkui Xu, Mingyan Jiang, Mingqiang Yang: A New Landmark Selection Method for Non-rigid Registration of Medical Brain Images. In: 2010 10th International Conference on Signal Processing, Vol II, p.920.

DOI: 10.1109/icosp.2010.5655730