Multimodal Medical Image Registration using Geometric Flow and Gabor Filter

Q. Zhang, Y. Wang, J. Yu, and S. Yang (PRC)


Image registration, multimodal medical images, geometric flow, Gabor filter


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.

Important Links:

Go Back