Zobrazit minimální záznam

Selection of Representative Landmark Images



dc.contributor.advisorMatas Jiří
dc.contributor.authorPavel Gramovich
dc.date.accessioned2020-09-04T13:59:53Z
dc.date.available2020-09-04T13:59:53Z
dc.date.issued2020-09-02
dc.identifierKOS-986690838005
dc.identifier.urihttp://hdl.handle.net/10467/90337
dc.description.abstractThe diversity of image retrieval results is an important feature that allows users to explore different aspects of the queried object. However, most of the works in this area are focused more on relevance rather than diversity. In this thesis, we are ameliorating this situation by proposing a new method for retrieving a diverse set of landmark images, which is based on recent advances in image retrieval area. The proposed approach consists of three phases. On the first one, irrelevant images are deleted from the input set using two detector networks. Then, the clustering phase follows, where landmark images are divided into groups by visual similarity based on distances between state-of-the-art image descriptors. Finally, from each cluster, a single representative located in the densest area of the cluster is chosen. For each phase, several alternative options are proposed, and the best combination is determined on the MediaEval dataset. Conducted experiments show that the proposed approach is superior to the current state-of-the-art, both in terms of diversity of the retrieved set and in terms of relevance.cze
dc.description.abstractThe diversity of image retrieval results is an important feature that allows users to explore different aspects of the queried object. However, most of the works in this area are focused more on relevance rather than diversity. In this thesis, we are ameliorating this situation by proposing a new method for retrieving a diverse set of landmark images, which is based on recent advances in image retrieval area. The proposed approach consists of three phases. On the first one, irrelevant images are deleted from the input set using two detector networks. Then, the clustering phase follows, where landmark images are divided into groups by visual similarity based on distances between state-of-the-art image descriptors. Finally, from each cluster, a single representative located in the densest area of the cluster is chosen. For each phase, several alternative options are proposed, and the best combination is determined on the MediaEval dataset. Conducted experiments show that the proposed approach is superior to the current state-of-the-art, both in terms of diversity of the retrieved set and in terms of relevance.eng
dc.publisherČeské vysoké učení technické v Praze. Vypočetní a informační centrum.cze
dc.publisherCzech Technical University in Prague. Computing and Information Centre.eng
dc.rightsA university thesis is a work protected by the Copyright Act. Extracts, copies and transcripts of the thesis are allowed for personal use only and at one?s own expense. The use of thesis should be in compliance with the Copyright Act http://www.mkcr.cz/assets/autorske-pravo/01-3982006.pdf and the citation ethics http://knihovny.cvut.cz/vychova/vskp.htmleng
dc.rightsVysokoškolská závěrečná práce je dílo chráněné autorským zákonem. Je možné pořizovat z něj na své náklady a pro svoji osobní potřebu výpisy, opisy a rozmnoženiny. Jeho využití musí být v souladu s autorským zákonem http://www.mkcr.cz/assets/autorske-pravo/01-3982006.pdf a citační etikou http://knihovny.cvut.cz/vychova/vskp.htmlcze
dc.subjectdiversitycze
dc.subjectimage retrievalcze
dc.subjectclusteringcze
dc.subjectimage descriptorscze
dc.subjectdiversityeng
dc.subjectimage retrievaleng
dc.subjectclusteringeng
dc.subjectimage descriptorseng
dc.titleVýběr reprezentativních obrazových prototypůcze
dc.titleSelection of Representative Landmark Imageseng
dc.typediplomová prácecze
dc.typemaster thesiseng
dc.contributor.refereeŠroubek Filip
theses.degree.disciplinePočítačové vidění a digitální obrazcze
theses.degree.grantorkatedra kybernetikycze
theses.degree.programmeOpen Informaticscze


Soubory tohoto záznamu




Tento záznam se objevuje v následujících kolekcích

Zobrazit minimální záznam