Paper
21 May 1993 Magneto-optical neural network image processing system
Bruce E. Rosen, James M. Goodwin
Author Affiliations +
Proceedings Volume 1902, Nonlinear Image Processing IV; (1993) https://doi.org/10.1117/12.144767
Event: IS&T/SPIE's Symposium on Electronic Imaging: Science and Technology, 1993, San Jose, CA, United States
Abstract
This paper describes the operation and construction of a magneto-optical neural network image processing system, together with a discussion of the physical basis for its operation. We discuss the behavior of the model under simulated annealing in light of statistical physics. This paper also presents results of large scale simulations of the physical system performed on CM- 2 Connection Machine. The system is capable of image recognition, reconstruction, and processing by use of massive parallelism in a physical thin film. A spin glass thin film material, in conjunction with magneto-optical control, implements a Boltzmann Machine like neural network. The thin film provides the units and connective weights of the neural network, and the magneto-optical system controls the image learning and recall by accessing the units and weights, and allowing their modification, using physical annealing in the film. Images are learned sequentially via stochastic minimization of the system energy, a function of all spin orientations and of interspin distances. Images can be recalled later when a similar, corrupted, or noisy version of a learned prototype image is presented. Our Monte Carlo style computer simulations of this system show its feasibility and practicality for real time image recognition.
© (1993) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Bruce E. Rosen and James M. Goodwin "Magneto-optical neural network image processing system", Proc. SPIE 1902, Nonlinear Image Processing IV, (21 May 1993); https://doi.org/10.1117/12.144767
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Annealing

Monte Carlo methods

Image processing

Glasses

Neural networks

Nonlinear image processing

Computer simulations

Back to Top