Publication: Dynamic learning from multiple examples for semantic object segmentation and search
dc.contributor.coauthor | Xu, Yaowu | |
dc.contributor.coauthor | Saber, Eli | |
dc.contributor.department | Department of Electrical and Electronics Engineering | |
dc.contributor.kuauthor | Tekalp, Ahmet Murat | |
dc.contributor.schoolcollegeinstitute | College of Engineering | |
dc.date.accessioned | 2024-11-09T23:39:41Z | |
dc.date.issued | 2004 | |
dc.description.abstract | We 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.indexedby | WOS | |
dc.description.indexedby | Scopus | |
dc.description.issue | 3 | |
dc.description.openaccess | NO | |
dc.description.publisherscope | International | |
dc.description.sponsoredbyTubitakEu | N/A | |
dc.description.volume | 95 | |
dc.identifier.doi | 10.1016/j.cviu.2004.04.003 | |
dc.identifier.eissn | 1090-235X | |
dc.identifier.issn | 1077-3142 | |
dc.identifier.quartile | Q2 | |
dc.identifier.scopus | 2-s2.0-3843146090 | |
dc.identifier.uri | https://doi.org/10.1016/j.cviu.2004.04.003 | |
dc.identifier.uri | https://hdl.handle.net/20.500.14288/13163 | |
dc.identifier.wos | 223379500004 | |
dc.keywords | Learning by examples | |
dc.keywords | Dynamic learning | |
dc.keywords | Shape matching | |
dc.keywords | Segmentation | |
dc.language.iso | eng | |
dc.publisher | Academic Press Ltd-Elsevier Science Ltd | |
dc.relation.ispartof | Computer Vision and Image Understanding | |
dc.subject | Computer science, artificial intelligence | |
dc.subject | Engineering, electrical and electronic | |
dc.title | Dynamic learning from multiple examples for semantic object segmentation and search | |
dc.type | Journal Article | |
dspace.entity.type | Publication | |
local.contributor.kuauthor | Tekalp, Ahmet Murat | |
local.publication.orgunit1 | College of Engineering | |
local.publication.orgunit2 | Department of Electrical and Electronics Engineering | |
relation.isOrgUnitOfPublication | 21598063-a7c5-420d-91ba-0cc9b2db0ea0 | |
relation.isOrgUnitOfPublication.latestForDiscovery | 21598063-a7c5-420d-91ba-0cc9b2db0ea0 | |
relation.isParentOrgUnitOfPublication | 8e756b23-2d4a-4ce8-b1b3-62c794a8c164 | |
relation.isParentOrgUnitOfPublication.latestForDiscovery | 8e756b23-2d4a-4ce8-b1b3-62c794a8c164 |