Face Identification by FG Sensor
Faculty of Science and Technology, Keio University, 3-14-1 Hiyoshi, Kouhoku-ku, Yokohama 223-0061, Japan
In this paper, we propose a new method for human face identification using 3-D shading image which combines 3-D distance information with gray scaled one. This image is acquired by Fiber-grating Visual Sensor. And the method is free from the fluctuation of the direction of the face in face data acquisition, so subjects are required to stand on a footprint and reflect the nose in the square flame at the center of the mirror. We introduce the partial space method for the Identification. And Right identification rate of 96.5% is achieved as a result.
Copyright© 1999 by Fuji Technology Press Ltd. and Japan Society of Mechanical Engineers. All right reserved.