Real-time face recognition system with optical learning neural network

Toyohiko Yatagai; Yutaka Yagai; Masahiko Mori; Masanobu Watanabe

doi:10.1117/12.326785

9 October 1998 Real-time face recognition system with optical learning neural network

Toyohiko Yatagai, Yutaka Yagai, Masahiko Mori, Masanobu Watanabe

Proceedings Volume 3466, Algorithms, Devices, and Systems for Optical Information Processing II; (1998) https://doi.org/10.1117/12.326785
Event: SPIE's International Symposium on Optical Science, Engineering, and Instrumentation, 1998, San Diego, CA, United States

Abstract

We describe an optical learning three-layer neural network that uses a back-propagation algorithm for human face recognition. Learning is performed by two-dimensional optical means for handling images without scanning and pixeling, because a face recognition problem needs a large-scale network. The two-dimensional input image is treated directly without vectorizing so that a recognition process of an unknown facial image is executed in real-time. We demonstrate training and recognition of three human faces using an experimental system.

Citation Download Citation

Toyohiko Yatagai, Yutaka Yagai, Masahiko Mori, and Masanobu Watanabe "Real-time face recognition system with optical learning neural network", Proc. SPIE 3466, Algorithms, Devices, and Systems for Optical Information Processing II, (9 October 1998); https://doi.org/10.1117/12.326785

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available