14 June 1996 Real-time compact optoelectronic neural networks for face recognition
Author Affiliations +
Abstract
We describe a nonlinear joint transform correlator-based two-layer neural network that uses a supervised learning algorithm for real-time face recognition. The system is trained with a sequence of facial images and is able to classify an input face image in real-time. Computer simulations and optical experimental results are presented. The processor can be manufactured into a compact low-cost optoelectronic system. The use of the nonlinear joint transform correlator provides good noise robustness and good image discrimination.
© (1996) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Bahram Javidi, Bahram Javidi, Jian Li, Jian Li, } "Real-time compact optoelectronic neural networks for face recognition", Proc. SPIE 2749, Photonic Component Engineering and Applications, (14 June 1996); doi: 10.1117/12.243104; https://doi.org/10.1117/12.243104
PROCEEDINGS
12 PAGES


SHARE
RELATED CONTENT

Image processing using BZ reaction
Proceedings of SPIE (September 20 2001)
Holographic Associative Memories
Proceedings of SPIE (May 22 1990)
Modification of boundaries of wigs in HDTV period dramas
Proceedings of SPIE (February 29 2000)

Back to Top