Multimodal medical image registration using geometric flow and Gabor filter

Authors:
Qi Zhang;Yuanyuan Wang;Jinhua Yu;Su Yang
Affiliations:
Fudan University, Shanghai, P.R. China;Fudan University, Shanghai, P.R. China;Fudan University, Shanghai, P.R. China;Fudan University, Shanghai, P.R. China
Venue:
BioMED '08 Proceedings of the Sixth IASTED International Conference on Biomedical Engineering
Year:
2008

Citing 8
Cited 0

A survey of image registration techniques

ACM Computing Surveys (CSUR)
Automatic Classification of Single Facial Images

IEEE Transactions on Pattern Analysis and Machine Intelligence
Rotation invariant texture classification using even symmetric Gabor filters

Pattern Recognition Letters
An approach to multimodal biomedical image registration utilizing particle swarm optimization

IEEE Transactions on Evolutionary Computation
Parameter selection and adaptation in Unified Particle Swarm Optimization

Mathematical and Computer Modelling: An International Journal
Gabor feature based classification using the enhanced fisher linear discriminant model for face recognition

IEEE Transactions on Image Processing
Sparse geometric image representations with bandelets

IEEE Transactions on Image Processing
Image registration using the Walsh transform

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Image registration is an important step in medical image processing. In this paper, a new correlation-based method using the geometric flow and Gabor filter is proposed for multimodal medical image registration. Firstly, the geometric flow is employed to take advantage of the image regularity. Then the Gabor filter is adopted along different directions to yield a family of filtered images. A feature image, i.e. a weighted combination of these filtered images, is calculated according to the geometric flow. After computing the correlation coefficient between the feature images, the optimal transformation will be found using the particle swarm optimization. The scheme is verified on both simulated and real images. The experimental results demonstrate that this method can accurately register the multimodal medical images. Compared with the up-to-date Walsh transform method, this scheme can reduce translation error by 1.58 pixels, and rotation error by 1.36 degrees.