We are investigating an opto-electronic implementation of a trainable pattern classification system based on a feed-forward neural network model. An architecture with two layers of interconnections is used to transform a large amount of scene information to a small feature space that is, in turn, transformed into classification data. By using two layers of interconnections the number of large inner products that must be calculated may be significantly reduced. Simulations have been performed on a digital computer that demonstrate the performance of a system for the rotation-invariant classification of printed characters. A possible optical implementation is outlined.
Lennart A. Saaf,
G. Michael Morris,
"Filter Synthesis Using Neural Networks", Proc. SPIE 1134, Optical Pattern Recognition II, (25 October 1989); doi: 10.1117/12.961608; https://doi.org/10.1117/12.961608