Share Email Print

Proceedings Paper

Optimal binarization of input images for holographic neural networks
Author(s): Oleg Boulanov; Tigran V. Galstian; Roger A. Lessard
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

The optical implementation of neural networks using volume holograms for weighted interconnections requires stable phase relation between input channels. This is particularly important for images with variable illumination. One way to solve this problem is to use binary inputs. The simplest binarization is the direct quantization, but this method has a number of disadvantages. Error diffusion algorithm is more robust under variable illumination since it keeps the original image characteristics.

Paper Details

Date Published: 24 May 2000
PDF: 7 pages
Proc. SPIE 4089, Optics in Computing 2000, (24 May 2000); doi: 10.1117/12.386831
Show Author Affiliations
Oleg Boulanov, COPL/Univ. Laval (Canada)
Tigran V. Galstian, COPL/Univ. Laval (Canada)
Roger A. Lessard, COPL/Univ. Laval (Canada)

Published in SPIE Proceedings Vol. 4089:
Optics in Computing 2000
Roger A. Lessard; Tigran V. Galstian, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?