Zamalieva, DaniyaAksoy, SelimTilton J. C.2016-02-082016-02-082009-07http://hdl.handle.net/11693/28621Date of Conference: 12-17 July 2009Conference name: IEEE International Geoscience and Remote Sensing Symposium, 2009We 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.EnglishGraph-based analysisImage segmentationObject detectionCompound imagesCompound structuresGraph-basedGraph-based analysisIKONOS imagesImage regionsInitial segmentationKnowledge DiscoveryObject DetectionRelational graphSpectral contentSubgraphsTransition frequenciesUnsupervised methodDigital image storageGeologyImage analysisProbability distributionsRemote sensingConference Paper10.1109/IGARSS.2009.5417683