Paper
4 March 1996 Target classification in an optical/digital hybrid neural processor
YanXin Zhang, Zhanbing Feng, Yuhua Li, Jianwen Yang, Shengquan Gao
Author Affiliations +
Proceedings Volume 2664, Applications of Artificial Neural Networks in Image Processing; (1996) https://doi.org/10.1117/12.234252
Event: Electronic Imaging: Science and Technology, 1996, San Jose, CA, United States
Abstract
A programmable and reconfigurable optical/digital hybrid neural processor with 1024 neurones is described. The relatively large scale and flexibility of the processor benefit by the mutual complement of the optics and an on-line microcomputer. As an example of application, a target classification of 4 kinds of aircraft based on their binary images rotated in a plane by arbitrary angles is performed. The model is a cascaded neural network consisting of three subnets. The principle of the classifier and computer simulation are outlined. In the preliminary experiments, more than 89% of the unlearned images and imperfect ones can be classified correctly.
© (1996) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
YanXin Zhang, Zhanbing Feng, Yuhua Li, Jianwen Yang, and Shengquan Gao "Target classification in an optical/digital hybrid neural processor", Proc. SPIE 2664, Applications of Artificial Neural Networks in Image Processing, (4 March 1996); https://doi.org/10.1117/12.234252
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Hybrid optics

Neurons

Neural networks

Binary data

Computer simulations

Image classification

Control systems

RELATED CONTENT


Back to Top