Publication:
Dynamic learning from multiple examples for semantic object segmentation and search

dc.contributor.coauthorXu, Yaowu
dc.contributor.coauthorSaber, Eli
dc.contributor.departmentDepartment of Electrical and Electronics Engineering
dc.contributor.kuauthorTekalp, Ahmet Murat
dc.contributor.schoolcollegeinstituteCollege of Engineering
dc.date.accessioned2024-11-09T23:39:41Z
dc.date.issued2004
dc.description.abstractWe present a novel "dynamic learning" approach for an intelligent image database system to automatically improve object segmentation and labeling without user intervention, as new examples become available, for object-based indexing. The proposed approach is an extension of our earlier work on "learning by example," which addressed labeling of similar objects in a set of database images based on a single example. The proposed dynamic learning procedure utilizes multiple example object templates to improve the accuracy of existing object segmentations and labels. Multiple example templates may be images of the same object from different viewing angles, or images of related objects. This paper also introduces a new shape similarity metric called normalized area of symmetric differences (NASD), which has desired properties for use in the proposed "dynamic learning" scheme, and is more robust against boundary noise that results from automatic image segmentation. Performance of the dynamic learning procedures has been demonstrated by experimental results.
dc.description.indexedbyWOS
dc.description.indexedbyScopus
dc.description.issue3
dc.description.openaccessNO
dc.description.publisherscopeInternational
dc.description.sponsoredbyTubitakEuN/A
dc.description.volume95
dc.identifier.doi10.1016/j.cviu.2004.04.003
dc.identifier.eissn1090-235X
dc.identifier.issn1077-3142
dc.identifier.quartileQ2
dc.identifier.scopus2-s2.0-3843146090
dc.identifier.urihttps://doi.org/10.1016/j.cviu.2004.04.003
dc.identifier.urihttps://hdl.handle.net/20.500.14288/13163
dc.identifier.wos223379500004
dc.keywordsLearning by examples
dc.keywordsDynamic learning
dc.keywordsShape matching
dc.keywordsSegmentation
dc.language.isoeng
dc.publisherAcademic Press Ltd-Elsevier Science Ltd
dc.relation.ispartofComputer Vision and Image Understanding
dc.subjectComputer science, artificial intelligence
dc.subjectEngineering, electrical and electronic
dc.titleDynamic learning from multiple examples for semantic object segmentation and search
dc.typeJournal Article
dspace.entity.typePublication
local.contributor.kuauthorTekalp, Ahmet Murat
local.publication.orgunit1College of Engineering
local.publication.orgunit2Department of Electrical and Electronics Engineering
relation.isOrgUnitOfPublication21598063-a7c5-420d-91ba-0cc9b2db0ea0
relation.isOrgUnitOfPublication.latestForDiscovery21598063-a7c5-420d-91ba-0cc9b2db0ea0
relation.isParentOrgUnitOfPublication8e756b23-2d4a-4ce8-b1b3-62c794a8c164
relation.isParentOrgUnitOfPublication.latestForDiscovery8e756b23-2d4a-4ce8-b1b3-62c794a8c164

Files