Neural networks with hybrid morphological/rank/linear nodes: a unifying framework with applications to handwritten character recognition

Pessoa, LFC; Maragos, P

dc.contributor.author	Pessoa, LFC	en
dc.contributor.author	Maragos, P	en
dc.date.accessioned	2014-03-01T01:15:44Z
dc.date.available	2014-03-01T01:15:44Z
dc.date.issued	2000	en
dc.identifier.issn	0031-3203	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/13693
dc.subject	morphological systems	en
dc.subject	MRL-filters	en
dc.subject	neural networks	en
dc.subject	back-propagation algorithm	en
dc.subject	handwritten character recognition	en
dc.subject.classification	Computer Science, Artificial Intelligence	en
dc.subject.classification	Engineering, Electrical & Electronic	en
dc.subject.other	SYSTEMS	en
dc.subject.other	FILTERS	en
dc.subject.other	DESIGN	en
dc.title	Neural networks with hybrid morphological/rank/linear nodes: a unifying framework with applications to handwritten character recognition	en
heal.type	journalArticle	en
heal.identifier.primary	10.1016/S0031-3203(99)00157-0	en
heal.identifier.secondary	http://dx.doi.org/10.1016/S0031-3203(99)00157-0	en
heal.language	English	en
heal.publicationDate	2000	en
heal.abstract	In this paper, the general class of morphological/rank/linear (MRL) multilayer feed-forward neural networks (NNs) is presented as a unifying signal processing tool that incorporates the properties of multilayer perceptrons (MLPs) and morphological/rank neural networks (MRNNs). The fundamental processing unit of MRL-NNs is the MRL-filter, where the combination of inputs in every node is formed by hybrid linear and nonlinear (of the morphological/rank type) operations. For its design we formulate a methodology using ideas from the back-propagation algorithm and robust techniques to circumvent the non-differentiability of rank functions. Extensive experimental results are presented from the problem of handwritten character recognition, which suggest that MRL-NNs not only provide better or similar performance when compared to MLPs but also can be trained faster. The MRL-NNs are a broad interesting class of nonlinear systems with many promising applications in pattern recognition and signal/image processing. (C) 2000 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.	en
heal.publisher	PERGAMON-ELSEVIER SCIENCE LTD	en
heal.journalName	PATTERN RECOGNITION	en
dc.identifier.doi	10.1016/S0031-3203(99)00157-0	en
dc.identifier.isi	ISI:000086685000007	en
dc.identifier.volume	33	en
dc.identifier.issue	6	en
dc.identifier.spage	945	en
dc.identifier.epage	960	en