An Automatic System for Identification of Human Faces Using Fiber Grating Vision Sensor
Kenji Terada*, Junichi Yamaguchi** and Masato Nakajima*
*Keio University, 3-14-1, Hiyoshi, Kouhoku-ku, Yokohama, Kanagawa 223, Japan
**Sogo Security Service Co., Ltd., 1-6-6 Motoakasaka, Minato-ku, Tokyo 107, Japan
In this paper, the authors describe an automatic system for the identification of human faces. In this system, the fiber grating vision sensor which has been developed by the authors is employed for the 3-D shape of the faces. To identify human faces, a multi-layered neural network is used in which the inputs are two component values of normal vector at data spot on the surface of human faces. The experiments using the developed system is performed to demonstrate the efficacy of this system and the experimental results are shown.