Full metadata record
DC FieldValueLanguage
dc.contributor.authorJan, SRen_US
dc.contributor.authorHsueh, YCen_US
dc.date.accessioned2014-12-08T15:45:16Z-
dc.date.available2014-12-08T15:45:16Z-
dc.date.issued2000-05-15en_US
dc.identifier.issn0262-8856en_US
dc.identifier.urihttp://dx.doi.org/10.1016/S0262-8856(99)00066-9en_US
dc.identifier.urihttp://hdl.handle.net/11536/30517-
dc.description.abstractSpatial relations between objects or regions in an image play important roles in scene understanding. However, it is difficult to define these relations for automation. Most existing methods for defining spatial relations depend on angle measurements between points of the two objects of interest. In this study, we propose a new approach based on the concept of skeleton by zones of influence (SKIZ) for recognizing the primitive spatial relations between objects or regions in a segmented image. The approach is compared with the aggregation and compatibility methods. The experimental result shows the proposed approach is effective and fast. (C) 2000 Elsevier Science B.V. All rights reserved.en_US
dc.language.isoen_USen_US
dc.subjectspatial relationsen_US
dc.subjectaggregation methoden_US
dc.subjectcompatibility methoden_US
dc.subjectskeleton by zones of influenceen_US
dc.subjectwatersheden_US
dc.titlePrimitive spatial relations based on SKIZen_US
dc.typeArticleen_US
dc.identifier.doi10.1016/S0262-8856(99)00066-9en_US
dc.identifier.journalIMAGE AND VISION COMPUTINGen_US
dc.citation.volume18en_US
dc.citation.issue8en_US
dc.citation.spage597en_US
dc.citation.epage605en_US
dc.contributor.department資訊工程學系zh_TW
dc.contributor.departmentDepartment of Computer Scienceen_US
dc.identifier.wosnumberWOS:000086846400003-
dc.citation.woscount1-
Appears in Collections:Articles


Files in This Item:

  1. 000086846400003.pdf

If it is a zip file, please download the file and unzip it, then open index.html in a browser to view the full text content.