Multichannel Image Registration using Gabor Wavelet Transform

This paper proposes a multichannel image registration method which combines information from different modalities/channels to produce a unified joint registration. Multichannel images are created by coregistering multimodality images of the same subject to utilize information across modalities comprehensively. The existing methods combine the information at the image/intensity level.But the proposed method uses feature-level information fusion method to combine the complementary information from different modalities that characterize different tissue types. This is through Gabor wavelets transformation and Independent Component Analysis (ICA), to produce an inter-subject registration. Experiments on both simulated and real multichannel images illustrate the applicability and robustness of the proposed registration method that combines information across modalities.