The Use of Expert System and Supervised Relaxation Techniques to Improve Spot Image Classification Using Spatial Context

Kontoes, C; Rokos, D; Wilkinson, G; Megier, J

dc.contributor.author	Kontoes, C	en
dc.contributor.author	Rokos, D	en
dc.contributor.author	Wilkinson, G	en
dc.contributor.author	Megier, J	en
dc.date.accessioned	2014-03-01T02:47:59Z
dc.date.available	2014-03-01T02:47:59Z
dc.date.issued	1991	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/33489
dc.subject	bayesian theory	en
dc.subject	Image Classification	en
dc.subject	Knowledge Base	en
dc.subject	Land Cover Classification	en
dc.subject	Land Use	en
dc.subject	Spatial Context	en
dc.subject	Thematic Maps	en
dc.subject	dempster shafer	en
dc.subject	Expert System	en
dc.subject	Land Cover	en
dc.title	The Use of Expert System and Supervised Relaxation Techniques to Improve Spot Image Classification Using Spatial Context	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/IGARSS.1991.579607	en
heal.identifier.secondary	http://dx.doi.org/10.1109/IGARSS.1991.579607	en
heal.publicationDate	1991	en
heal.abstract	Two methods have been tested in order to improve land use mapping in a post-classification refinement process: supervised relaxation and an expert system. Both methods use multiple sources of information and return satisfactory results. Statistical measurements of texture have been used to provide ancillary information for land use mapping at a super-class level (general classes) in a land cover classification	en
heal.journalName	Geoscience and Remote Sensing IEEE International Symposium	en
dc.identifier.doi	10.1109/IGARSS.1991.579607	en