We use an optoelectronic pattern recognition system to combine multiple image informatíononto a single binary hologram, by compressing the 2D images into near-lD vectors usíng a specíal ring target. These vectors are fed 1n to an optical neural network trained with a learníng rule tbat minimizes the lateral activations that would that Would interfere with recognition. We present optical results showing the usefulness of thís technique.
© 2001-2026 Fundación Dialnet · Todos los derechos reservados