Face Reconstruction from Skull Shapes and Physical Attributes

Reconstructing a person’s face from its skeletal remains is a task thathas over many decades fascinated artist and scientist alike. In this paper we treatfacial reconstruction as a machine learning problem. We use separate statisticalshape models to represent the skull and face morphology. We learn the relationshipbetween the parameters of the models by fitting them to a set of MR imagesof the head and using ridge regression on the resulting model parameters. Sincethe facial shape is not uniquely defined by the skull shape, we allow to specifytarget attributes, such as age or weight. Our experiments show that the reconstructionresults are generally close to the original face, and that by specifyingthe right attributes the perceptual and measured difference between the originaland the predicted face is reduced.