Meticulously detailed eye model and its application to analysis of facial image

We propose a system that is capable of detailed analysis of eye region images including position of the iris, degree of eyelid opening, and shape and texture of the eyelid. The system is based on a generative eye model that defines fine structures and motions of eye. The structure parameters represent structural individuality of the eye, including size and color of the iris, width and boldness of the double-fold eyelid, width of the bulge below the eye and width of the illumination reflection on the bulge. The motion parameters represent movements of the eye, including up-down position of the upper and lower eyelids and 2D position of the iris. The system first registers the eye model to the input in a particular frame and individualizes the model by adjusting the structure parameters. Then, it tracks motion of the eye by estimating the motion parameters across the entire image sequence. Combined with image stabilization to compensate the head motion, the registration and motion recovery of the eye are guaranteed to be robust.