24 May 2000 Optimal binarization of input images for holographic neural networks
Author Affiliations +
Proceedings Volume 4089, Optics in Computing 2000; (2000) https://doi.org/10.1117/12.386831
Event: 2000 International Topical Meeting on Optics in Computing (OC2000), 2000, Quebec City, Canada
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.
© (2000) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Oleg Boulanov, Oleg Boulanov, Tigran V. Galstian, Tigran V. Galstian, Roger A. Lessard, Roger A. Lessard, } "Optimal binarization of input images for holographic neural networks", Proc. SPIE 4089, Optics in Computing 2000, (24 May 2000); doi: 10.1117/12.386831; https://doi.org/10.1117/12.386831


Back to Top