Publication:
Object-based image labeling through learning by example and multi-level segmentation

dc.contributor.coauthorXu, Y
dc.contributor.coauthorDuygulu, P
dc.contributor.coauthorSaber, E
dc.contributor.coauthorYarman-Vural, FT
dc.contributor.departmentDepartment of Electrical and Electronics Engineering
dc.contributor.kuauthorTekalp, Ahmet Murat
dc.contributor.schoolcollegeinstituteCollege of Engineering
dc.date.accessioned2024-11-09T22:55:57Z
dc.date.issued2003
dc.description.abstractWe propose a method for automatic extraction and labeling of semantically meaningful image objects using "learning by example" and threshold-free multi-level image segmentation. The proposed method scans through images, each of which is pre-segmented into a hierarchical uniformity tree, to seek and label objects that are similar to an example object presented by the user. By representing images with stacks of multi-level segmentation maps, objects can be extracted in the segmentation map level with adequate detail. Experiments have shown that the proposed multi-level image segmentation results in significant reduction in computation complexity for object extraction and labeling (compared to a single fine-level segmentation) by avoiding unnecessary tests of combinations in finer levels. The multi-level segmentation-based approach also achieves better accuracy in detection and labeling of small objects.
dc.description.indexedbyWOS
dc.description.indexedbyScopus
dc.description.issue6
dc.description.openaccessNO
dc.description.publisherscopeInternational
dc.description.sponsoredbyTubitakEuN/A
dc.description.volume36
dc.identifier.doi10.1016/S0031-3203(02)00250-9
dc.identifier.issn0031-3203
dc.identifier.quartileQ1
dc.identifier.scopus2-s2.0-0242600663
dc.identifier.urihttps://doi.org/10.1016/S0031-3203(02)00250-9
dc.identifier.urihttps://hdl.handle.net/20.500.14288/7277
dc.identifier.wos181591400013
dc.keywordsObject-based image labeling
dc.keywordsMulti-level segmentation
dc.keywordsHierarchical content description
dc.keywordsLearning by example retrieval
dc.keywordsColor
dc.keywordsDatabases
dc.keywordsInformation
dc.keywordsSemantics
dc.language.isoeng
dc.publisherPergamon-Elsevier Science Ltd
dc.relation.ispartofPattern Recognition
dc.subjectComputer Science
dc.subjectArtificial intelligence
dc.subjectElectrical electronics engineering
dc.titleObject-based image labeling through learning by example and multi-level segmentation
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