A motion correction system for brain tomography based on biologically motivated models

A motion correction system for brain tomography is presented, which employs two calibrated video cameras and three vision models (CIECAM'97, RETINA, and BMV). The system is evaluated on the pictures monitoring a subjects head while simulating PET scanning (n=12) and on the face images of subjects with different skin colours (n=31). The results on 2D images with known moving parameters show that motion parameters of rotation and translation along X, Y, and Z directions can be obtained very accurately via the method of facial landmark detection. A feasibility study of the developed algorithms is evaluated by a computer simulation of brain scanning procedures.