Learning based coarse-to-fine image registration

This paper describes a coarse-to-fine learning based im-age registration algorithm which has particular advantages in dealing with multi-modality images. Many existing im-age registration algorithms [18] use a few designed terms or mutual information to measure the similarity between image pairs. Instead, we push the learning aspect by se-lecting and fusing a large number of features for measur-ing the similarity. Moreover, the similarity measure is car-ried in a coarse-to-fine strategy: global similarity mea-sure is first performed to roughly locate the component, we then learn/compute similarity on the local image patches to capture the fine level information. When estimating the transformation parameters, we also engage a coarse-to-fine strategy. Off-the-shelf interest point detectors such as SIFT [12] have degraded results on medical images. We further push the learning idea to extract the main struc-tures/landmarks. Our algorithm is illustrated on three ap-plications: (1) registration of mouse brain images of differ-ent modalities, (2) registering human brain image of MRI T1 and T2 images, (3) faces of different expressions. We show greatly improved results over the existing algorithms based on either mutual information or geometric structures. 1