CONSTRUCTING A 3D INDIVIDUALIZED HEAD MODEL FROM 2 ORTHOGONAL VIEWS

A new scheme for constructing a 3D individualized head model automatic ally from only a side view and the front view of the face is presented . The approach instantiates a generic 3D head model based on a set of the individual's facial features extracted by a local maximum-curvatur e tracking (LMCT) algorithm that we have developed. A distortion vecto r field that deforms the generic model to that of the individual is co mputed by correspondence matching and interpolation. The input of the two facial images are blended and texture-mapped onto the 3D head mode l. Arbitrary views of a person can be generated from two orthogonal im ages and can be implemented efficiently on a low-cost, PC-based platfo rm.