Manipulating facial appearance through shape and color

Abstract

A technique for defining facial prototypes is described which supports transformations along quantifiable dimensions in "face space". Examples illustrate the use of shape and color information to perform predictive gender and age transformations. The processes we describe begin with the creation of a facial prototype. Generally, a prototype can be defined as a representation containing the consistent attributes across a class of objects. Once we obtain a class prototype, we can take an exemplar that has some information missing and augment it with the prototypical information. In effect, this "adds in" the average values for the missing information. We use this notion to transform gray-scale images into full color by including the color information from a relevant prototype. It is also possible to deduce the difference between two groups within a class. Separate prototypes can be formed for each group. These can be used subsequently to define a transformation that will map instances from one group onto the domain of the other. This paper details the procedure we use to transform facial images and shows how it can be used to alter perceived facial attributes.>