A new approach to the generation of a feature-point-driven facial animation
is presented. In the proposed approach, a hypothetical face is used to con
trol the animation of a face model. The hypothetical face is constructed by
connecting some predefined facial feature points to create a net so that e
ach facet of the net is represented by a Coon's surface. Deformation of the
face model is controlled by changing the shape of the hypothetical face, w
hich is performed by changing the locations of feature points and their tan
gents. Experimental results show that this hypothetical-face-based method c
an generate facial expressions which are visually almost identical to those
of a real face.