Mobile multi-view object image search

Simple item page
buir.contributor.authorUlusoy, Özgür
buir.contributor.authorGüdükbay, Uğur
dc.citation.epage12456en_US
dc.citation.issueNumber10en_US
dc.citation.spage12433en_US
dc.citation.volumeNumber76en_US
dc.contributor.authorÇalışır, F.en_US
dc.contributor.authorBaştan M.en_US
dc.contributor.authorUlusoy, Özgüren_US
dc.contributor.authorGüdükbay, Uğuren_US
dc.date.accessioned2018-04-12T11:14:10Z
dc.date.available2018-04-12T11:14:10Z
dc.date.issued2017en_US
dc.departmentDepartment of Computer Engineeringen_US
dc.description.abstractHigh user interaction capability of mobile devices can help improve the accuracy of mobile visual search systems. At query time, it is possible to capture multiple views of an object from different viewing angles and at different scales with the mobile device camera to obtain richer information about the object compared to a single view and hence return more accurate results. Motivated by this, we propose a new multi-view visual query model on multi-view object image databases for mobile visual search. Multi-view images of objects acquired by the mobile clients are processed and local features are sent to a server, which combines the query image representations with early/late fusion methods and returns the query results. We performed a comprehensive analysis of early and late fusion approaches using various similarity functions, on an existing single view and a new multi-view object image database. The experimental results show that multi-view search provides significantly better retrieval accuracy compared to traditional single view search. © 2016, Springer Science+Business Media New York.en_US
dc.identifier.doi10.1007/s11042-016-3659-9en_US
dc.identifier.issn1380-7501
dc.identifier.urihttp://hdl.handle.net/11693/37465
dc.language.isoEnglishen_US
dc.publisherSpringer New York LLCen_US
dc.relation.isversionofhttp://dx.doi.org/10.1007/s11042-016-3659-9en_US
dc.source.titleMultimedia Tools and Applicationsen_US
dc.subjectBag of visual wordsen_US
dc.subjectFusionen_US
dc.subjectMobile visual searchen_US
dc.subjectMulti-view searchen_US
dc.subjectFusion reactionsen_US
dc.subjectUser interactionen_US
dc.titleMobile multi-view object image searchen_US
dc.typeArticleen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Mobile multi-view object image search.pdf
Size:
4.82 MB
Format:
Adobe Portable Document Format
Description:
Full printable version
Download
Collections
Department of Computer Engineering