Morphological/rank neural networks and their adaptive optimal design for image processing

Pessoa, L; Maragos, P

dc.contributor.author	Pessoa, L	en
dc.contributor.author	Maragos, P	en
dc.date.accessioned	2014-03-01T02:48:22Z
dc.date.available	2014-03-01T02:48:22Z
dc.date.issued	1996	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/33771
dc.subject	Adaptive Optimization	en
dc.subject	Back Propagation Algorithm	en
dc.subject	Image Processing	en
dc.subject	Internal Structure	en
dc.subject	Signal and Image Processing	en
dc.subject	Training Algorithm	en
dc.subject	Neural Network	en
dc.title	Morphological/rank neural networks and their adaptive optimal design for image processing	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/ICASSP.1996.550607	en
heal.identifier.secondary	http://dx.doi.org/10.1109/ICASSP.1996.550607	en
heal.publicationDate	1996	en
heal.abstract	We formulate a general class of neural network based filters, where each node is a morphological/rank operation. This type of system is computationally efficient since no multiplications are necessary. The introduction of such networks is partially motivated from observations that internal structures of a neuron can generate logic operations. An efficient adaptive optimal design procedure is proposed for these networks,	en
heal.journalName	International Conference on Acoustics, Speech, and Signal Processing	en
dc.identifier.doi	10.1109/ICASSP.1996.550607	en