Institutional Repository [SANDBOX]
Technical University of Crete
EN  |  EL

Search

Browse

My Space

Relevance feedback methods for logo and trademark image retrieval on the web

Petrakis Evripidis, Voutsakis Epimenidis, Kontis Klaydios , Milios Evangelos E.

Simple record

URIhttp://purl.tuc.gr/dl/dias/47B4A8F0-2EB9-470E-9D90-834AC7155098-
Identifierhttps://doi.org/10.1145/1141277.1141532-
Languageen-
TitleRelevance feedback methods for logo and trademark image retrieval on the weben
CreatorPetrakis Evripidisen
CreatorΠετρακης Ευριπιδηςel
CreatorVoutsakis Epimenidisen
CreatorKontis Klaydios en
CreatorMilios Evangelos E. en
PublisherAssociation for Computing Machineryen
Content SummaryRelevance feedback is the state-of-the-art approach for adjusting query results to the needs of the users. This work extends the existing framework of image retrieval with relevance feedback on the Web by incorporating text and image content into the search and feedback process. Some of the most powerful relevance feedback methods are implemented and tested on a fully automated Web retrieval system with more than 250,000 logo and trademark images. This evaluation demonstrates that term re-weighting based on text and image content is the most effective approach.en
Type of ItemΠερίληψη Δημοσίευσης σε Συνέδριοel
Type of ItemConference Paper Abstracten
Licensehttp://creativecommons.org/licenses/by/4.0/en
Date of Item2015-11-01-
Date of Publication2006-
Bibliographic CitationEuripides G.M. Petrakis, Klaydios Kontis, Epimenidis Voutsakis, Evangelos Milios, "Relevance Feedback Methods for Logo and Trademark Image Retrieval on the Web", in 21st ACM Symposium on Applied Computing (ACM SAC'2006), 2006, pp. 1084-1088. doi:10.1145/1141277.1141532en

Services

Statistics

 

Copyright © DIAS 2013