Medical Image Registration Algorithm Based on Fourier-Mellin Transformation

doi:DOI:10.3969/j.cnki.jdxb.2017.01.007

Abstract

Abstract:

The mutual information-based registration (RMI) technology is widely used in medical image registration, but it requires heavy calculation and is time consuming, and since it is greatly influenced by initial rotation and translation parameters, the objective function has the problem of local minimum.In this paper，medical image registration using Fourier-Mellin transformation (RTMT) is proposed.The relative translation values between the reference and floating images are obtained by computing the inverse Fourier transformation of the power spectrum between them to find the corresponding peak value position.In basically similar method，the relative rotation angle between them is acquired by imposing Log-polar transformation on the amplitude spectrums of the images，thus the registration parameters have been collected and finally the registering process between the two medical images are performed.Although RTMT can accomplish fast image registration，the registration accuracy needs to be further boosted.In this paper，therefore，the combination of RTMT with RMI is used to align the medical images.Namely，the translation and rotation values created by RTMT are taken as the initial registration parameters of RMI to deal with the alignment. This method is simple and has less amount of computation, and it can achieve precise and fast registration.It can be applied in single modality image registration and multi modality registration as well.It also solves the problem of local optimum.

Key words: Fourier-Mellin transformation, medical image, image registration, mutual information

LEI Chaoyang，LIU Junhua，LI Qiao. Medical Image Registration Algorithm Based on Fourier-Mellin Transformation[J]. Journal of Jishou University（Natural Sciences Edition), DOI: DOI:10.3969/j.cnki.jdxb.2017.01.007.

References

[1] NEJATI MANSOUR，POURGHASSEM HOSSEIN.Multiresolution Image Registration in Digital X-Ray Angiography with Intensity Variation Modeling[J].Journal of Medical Systems，2014，38(1):10-18.
[2] PAN Meisen，JIANG Jianjun，RONG Qiusheng.A Modified Medical Image Registration[J].Multimedia Tools and Applications，2014，70(3):1 585-1 615.
[3] ANTOINE MAINTZ J B，VIERGEVER MAX A．A Survey of Medical Image Registration[J]．Medical Image Analysis，1998，2(1):1-36．
[4] PARK HYUNJIN，BLAND PEYTON H，BROCK KRISTY K，et a1.Adaptive Registration Using Local Information Measures[J].Medical Image Analysis，2004，8(4):465-473.
[5] CAN A，STEWART C，ROYSAM B．A Feature-Based，Robust，Hierarchical Algorithm for Registration Palm of Images of the Curved Human Retina[J]．IEEE Transactions on Pattern Analysis and Machine Intelligence，2002，24(3):347-363.
[6] LIU Yan，CHENG H D，HUANG Jianhua.An Effective Non-Rigid Registration Approach for Ultrasound Image Based on "Demons" Algorithm[J].Journal of Digital Imaging，2013，26(3)：521-529.
[7] LIU Wei，RIBEIRO ERALDO.Incremental Variations of Image Moments for Nonlinear Image Registration[J].Signal，Image and Video Processing，2014，8(3)：423-432.
[8] CHEN Shengqin，DEFRISE M，DECONINCK F.Symmetric Phase-Only Matched Filtering of Fourier-Mellin Transforms for Image Registration and Recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，1994，16(12):1 156-1 168.
[9] SRINIVASA REDDY B，CHATTERJI B N.An FFT-Based Technique for Translation，Rotation，and Scale-Invariant Image Registration[J].IEEE Transactions on Image Processing，1996，5(8):1 266-1 271.
[10] BIN T J， LEI Ao，CUI Jiwen，et al.Subpixel Edge Location Based on Orthogonal Fourier-Mellin Moments[J].Image and Vision Computing，2008，26(4)：563-569.
[11] GUO Liqiang，ZHU Ming.Quaternion Fourier-Mellin Moments for Color Images[J].Pattern Recognition，2011，44(2)：187-195.