Share Email Print

Proceedings Paper

Neural structures in digital halftoning
Author(s): Thomas Tuttass; Manfred Broja; Olof Bryngdahl
Format Member Price Non-Member Price
PDF $17.00 $21.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

In digital halftoning various local and global methods have been suggested. The structure of neural networks allows a new interpretation of these procedures. For global processing the use of the Hopfield net was examined for the binarization problem. We show that the constraints concerning this model influences the binary result. The numerical description leads to a basic parallelism to the well known iterative Fourier transform algorithm (IFTA), applied in digital halftoning.

Paper Details

Date Published: 21 May 1993
PDF: 7 pages
Proc. SPIE 1902, Nonlinear Image Processing IV, (21 May 1993); doi: 10.1117/12.144768
Show Author Affiliations
Thomas Tuttass, Univ. Essen (Germany)
Manfred Broja, Univ. Essen (Germany)
Olof Bryngdahl, Univ. Essen (Germany)

Published in SPIE Proceedings Vol. 1902:
Nonlinear Image Processing IV
Edward R. Dougherty; Jaakko T. Astola; Harold G. Longbotham, Editor(s)

© SPIE. Terms of Use
Back to Top