A unified neural network approach to digital image halftoning

Kollias, Stefanos; Anastassiou, Dimitris

dc.contributor.author	Kollias, Stefanos	en
dc.contributor.author	Anastassiou, Dimitris	en
dc.date.accessioned	2014-03-01T01:08:14Z
dc.date.available	2014-03-01T01:08:14Z
dc.date.issued	1991	en
dc.identifier.issn	1053-587X	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/10356
dc.subject	Digital Image	en
dc.subject	Neutral Network	en
dc.subject	Neural Network	en
dc.subject	Weighted Mean Squared Error	en
dc.subject.classification	Engineering, Electrical & Electronic	en
dc.subject.other	Neural Networks--Applications	en
dc.subject.other	Digital Image Halftoning	en
dc.subject.other	Error Diffusion Halftoning Method	en
dc.subject.other	Image Processing	en
dc.title	A unified neural network approach to digital image halftoning	en
heal.type	journalArticle	en
heal.identifier.primary	10.1109/78.80930	en
heal.identifier.secondary	http://dx.doi.org/10.1109/78.80930	en
heal.language	English	en
heal.publicationDate	1991	en
heal.abstract	A technique for digital halftoning of images that is based on a symmetric parallel formulation of the error diffusion halftoning method is developed. Appropriately trained or designed near-neighbor-connected symmetric neural networks are used to generate halftoned images in an efficient parallel way, based on the minimization of a frequency-weighted mean-squared error criterion. Image halftoning by symmetric networks is described using an appropriate image distortion measure. The problem of determining the network interconnection weights is examined. Examples which illustrate the performance of the proposed technique compared to that of conventional or more complex methods are given.	en
heal.publisher	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC	en
heal.journalName	IEEE Transactions on Signal Processing	en
dc.identifier.doi	10.1109/78.80930	en
dc.identifier.isi	ISI:A1991FD67500033	en
dc.identifier.volume	39	en
dc.identifier.issue	4	en
dc.identifier.spage	980	en
dc.identifier.epage	984	en