Two frontiers in morphological image analysis: differential evolution models and hybrid morphological/linear neural networks

Maragos, P; Butt, M; Pessoa, L

dc.contributor.author	Maragos, P	en
dc.contributor.author	Butt, M	en
dc.contributor.author	Pessoa, L	en
dc.date.accessioned	2014-03-01T02:48:39Z
dc.date.available	2014-03-01T02:48:39Z
dc.date.issued	1998	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/33986
dc.subject	backpropagation algorithm	en
dc.subject	Character Recognition	en
dc.subject	Curve Evolution	en
dc.subject	Differential Evolution	en
dc.subject	Handwritten Character Recognition	en
dc.subject	Image Analysis	en
dc.subject	Morphological Operation	en
dc.subject	Multilayer Feedforward Neural Network	en
dc.subject	Multiscale Analysis	en
dc.subject	Partial Differential Equation	en
dc.subject	Pattern Recognition	en
dc.subject	Ranking Function	en
dc.subject	Watershed Segmentation	en
dc.subject	Neural Net	en
dc.subject	Neural Network	en
dc.title	Two frontiers in morphological image analysis: differential evolution models and hybrid morphological/linear neural networks	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/SIBGRA.1998.722726	en
heal.identifier.secondary	http://dx.doi.org/10.1109/SIBGRA.1998.722726	en
heal.publicationDate	1998	en
heal.abstract	We briefly describe advancements in two broad areas of morphological image analysis. Part I deals with differential morphology and curve evolution. The partial differential equations (PDEs) that model basic morphological operations are first presented. The resulting dilation PDE, numerically implemented by curve evolution algorithms, improves the accuracy of morphological multiscale analysis by Euclidean disks and (its anisotropic/heterogeneous version) is the	en
heal.journalName	Brazilian Symposium on Computer Graphics and Image Processing	en
dc.identifier.doi	10.1109/SIBGRA.1998.722726	en