Show simple item record

dc.contributor.authorZamalieva, D.en_US
dc.contributor.authorAksoy, S.en_US
dc.contributor.authorTilton J.C.en_US
dc.date.accessioned2016-02-08T12:25:20Z
dc.date.available2016-02-08T12:25:20Z
dc.date.issued2009en_US
dc.identifier.urihttp://hdl.handle.net/11693/28621
dc.description.abstractWe present an unsupervised method for discovering compound image structures that are comprised of simpler primitive objects. An initial segmentation step produces image regions with homogeneous spectral content. Then, the segmentation is translated into a relational graph structure whose nodes correspond to the regions and the edges represent the relationships between these regions. We assume that the region objects that appear together frequently can be considered as strongly related. This relation is modeled using the transition frequencies between neighboring regions, and the significant relations are found as the modes of a probability distribution estimated using the features of these transitions. Experiments using an Ikonos image show that subgraphs found within the graph representing the whole image correspond to parts of different high-level compound structures. ©2009 IEEE.en_US
dc.language.isoEnglishen_US
dc.source.titleInternational Geoscience and Remote Sensing Symposium (IGARSS)en_US
dc.relation.isversionofhttp://dx.doi.org/10.1109/IGARSS.2009.5417683en_US
dc.subjectGraph-based analysisen_US
dc.subjectImage segmentationen_US
dc.subjectObject detectionen_US
dc.subjectCompound imagesen_US
dc.subjectCompound structuresen_US
dc.subjectGraph-baseden_US
dc.subjectGraph-based analysisen_US
dc.subjectIKONOS imagesen_US
dc.subjectImage regionsen_US
dc.subjectInitial segmentationen_US
dc.subjectKnowledge Discoveryen_US
dc.subjectObject Detectionen_US
dc.subjectRelational graphen_US
dc.subjectSpectral contenten_US
dc.subjectSubgraphsen_US
dc.subjectTransition frequenciesen_US
dc.subjectUnsupervised methoden_US
dc.subjectDigital image storageen_US
dc.subjectGeologyen_US
dc.subjectImage analysisen_US
dc.subjectProbability distributionsen_US
dc.subjectRemote sensingen_US
dc.subjectImage segmentationen_US
dc.titleFinding compound structures in images using image segmentation and graph-based knowledge discoveryen_US
dc.typeConference Paperen_US
dc.departmentDepartment of Computer Engineering
dc.citation.spageV252en_US
dc.citation.epageV255en_US
dc.citation.volumeNumber5en_US
dc.identifier.doi10.1109/IGARSS.2009.5417683en_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record