Digital Image Halftoning Using Neural Networks

Dimitris Anastassiou; Stefanos Kollias

doi:10.1117/12.969059

Translator Disclaimer

25 October 1988 Digital Image Halftoning Using Neural Networks

Dimitris Anastassiou; Stefanos Kollias

Author Affiliations +

Proceedings Volume 1001, Visual Communications and Image Processing '88: Third in a Series; (1988) https://doi.org/10.1117/12.969059
Event: Visual Communications and Image Processing III, 1988, Cambridge, MA, United States

Abstract

A novel technique for digital image halftoning is presented, performing nonstandard quantization subject to a fidelity criterion. Massively parallel artificial symmetric neural networks are used for this purpose, minimizing a frequency weighted mean squared error between the continuous-tone input and the bilevel output image. The weights of these networks can be selected, so that the generated halftoned images are of good quality. A symmetric formulation of the error diffusion halftoning technique is also presented in the form of a massively parallel network. This network contains a nonmonotonic nonlinearity in lieu of the sigmoid function and is shown to be appropriate for effective halftoning of images.

Citation Download Citation

Dimitris Anastassiou and Stefanos Kollias "Digital Image Halftoning Using Neural Networks", Proc. SPIE 1001, Visual Communications and Image Processing '88: Third in a Series, (25 October 1988); https://doi.org/10.1117/12.969059