A volumetric spin-off EGI for registration of volume datasets

A spin-off of the Extended Gaussian Image [1] (EGI) registration technique to volumetric datasets is presented. This spin-off technique directly allows recovery of the rotation (and indirectly may allow recovery of the translation) transformations that aligns one volumetric dataset to another. An extension of the basic EGI's orientation histogram to volumetric datasets is also described. Using this histogram, a volume gradient orientation histogram, enables the registration (i.e., aligning) of two instances of one subject. The spin-off technique can be useful for fully automated registration without extraction of higher level features or markers. Results on multiple types of datasets are also reported.