Face synthesis using facial trait code and its application to creating suspect's physical profiles

Abstract

In this work, we propose a novel approach to synthesize human faces. The proposed approach is based on the Facial Trait Code, or FTC for short, which is originally proposed for solving the face recognition problem. The FTC decoding transforms codewords into faces. We find that the FTC code space is typically huge and only a very small subset of FTC codewords render smooth faces. We propose an algorithm which extracts codewords that render smooth faces efficiently, and we dub these codewords as legitimate code-words. The extraction of legitimate codewords is accompanied by a coarse-to-fine face synthesis scheme, which renders faces by mosaicking multiple patches of different facial parts. We implement a GUI to demonstrate that the proposed approach is able to help eye-witnesses to create suspect's physical profiles efficiently in the law enforcement environments, without the aid of face painters. ©2009 IEEE.