Show simple item record

dc.contributor.authorÖzdemir, B.en_US
dc.contributor.authorAksoy, S.en_US
dc.contributor.authorEckert, S.en_US
dc.contributor.authorPesaresi, M.en_US
dc.contributor.authorEhrlich, D.en_US
dc.date.accessioned2016-02-08T09:57:46Z
dc.date.available2016-02-08T09:57:46Z
dc.date.issued2010en_US
dc.identifier.issn0167-8655
dc.identifier.urihttp://hdl.handle.net/11693/22267
dc.description.abstractWe propose a new procedure for quantitative evaluation of object detection algorithms. The procedure consists of a matching stage for finding correspondences between reference and output objects, an accuracy score that is sensitive to object shapes as well as boundary and fragmentation errors, and a ranking step for final ordering of the algorithms using multiple performance indicators. The procedure is illustrated on a building detection task where the resulting rankings are consistent with the visual inspection of the detection maps. © 2009 Elsevier B.V. All rights reserved.en_US
dc.language.isoEnglishen_US
dc.source.titlePattern Recognition Lettersen_US
dc.relation.isversionofhttp://dx.doi.org/10.1016/j.patrec.2009.10.016en_US
dc.subjectMulti - criteria rankingen_US
dc.subjectObject detectionen_US
dc.subjectObject matchingen_US
dc.subjectPerformance evaluationen_US
dc.subjectShape modelingen_US
dc.subjectBuilding detectionen_US
dc.titlePerformance measures for object detection evaluationen_US
dc.typeArticleen_US
dc.departmentDepartment of Computer Engineeringen_US
dc.citation.spage1128en_US
dc.citation.epage1137en_US
dc.citation.volumeNumber31en_US
dc.citation.issueNumber10en_US
dc.identifier.doi10.1016/j.patrec.2009.10.016en_US
dc.publisherElsevier BVen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record