3D face synthesis based on the information of words expressing facial features

Abstract

Our aim is to synthesize faces based on freely-elicited expressions by expanding the range of words describing the shape of facial elements to include abstract or metaphorical expressions. We realize this by defining the synthesizing process of a human face as a mapping from a word space to a physical model space. The use of whole words existing in the word space has made it possible to synthesize a human face based on freely-elicited expressions.

A Method to Synthesize Three Dimensional Face Models by Mapping from a Word Space to a Physical Model Space and the Inspection of the Mapping Function

“…Introducing the concept of mapping enables us to synthesize the 3-dimensional physical models corresponding to diverse words [5], [6], [7], [8]. We adopted GMDH (Group Method of Data Handling) [9] to identify a mapping function in this method.…”