Show simple item record

Large Scale Object Detection

dc.contributor.advisorMatas Jiří
dc.contributor.authorNovotný David
dc.date.accessioned2015-03-20T06:03:20Z
dc.date.available2015-03-20T06:03:20Z
dc.identifierKOS-541574131105
dc.identifier.urihttp://hdl.handle.net/10467/61273
dc.description.abstractThis thesis focuses on the problem of large scale visual object detection and classification in digital images. A new type of image features that are derived from state-of-the-art convolutional neural networks is proposed. It is further shown that the newly proposed image signatures bare a strong resemblance to the Fisher Kernel classifier, that recently became popular in the object category retrieval field. Because this new method suffers from having a large memory footprint, several feature compression / selection techniques are evaluated and their performance is reported. The result is an image classifier that is able to surpass the performance of the original convolutional neural network, from which it was derived. The new feature extraction method is also used for the object detection task with similar results.cze
dc.description.abstractThis thesis focuses on the problem of large scale visual object detection and classification in digital images. A new type of image features that are derived from state-of-the-art convolutional neural networks is proposed. It is further shown that the newly proposed image signatures bare a strong resemblance to the Fisher Kernel classifier, that recently became popular in the object category retrieval field. Because this new method suffers from having a large memory footprint, several feature compression / selection techniques are evaluated and their performance is reported. The result is an image classifier that is able to surpass the performance of the original convolutional neural network, from which it was derived. The new feature extraction method is also used for the object detection task with similar results.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://www.cvut.cz/sites/default/files/content/d1dc93cd-5894-4521-b799-c7e715d3c59e/cs/20160901-metodicky-pokyn-c-12009-o-dodrzovani-etickych-principu-pri-priprave-vysokoskolskych.pdf.eng
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://www.cvut.cz/sites/default/files/content/d1dc93cd-5894-4521-b799-c7e715d3c59e/cs/20160901-metodicky-pokyn-c-12009-o-dodrzovani-etickych-principu-pri-priprave-vysokoskolskych.pdf.cze
dc.subjectDetekce objektů, Fisher Kernel, výběr příznaků, SVM, klasifikace obrazu, konvoluční neuronová síťcze
dc.titleDetekce objektů z mnoha třídcze
dc.titleLarge Scale Object Detectioneng
dc.typediplomová prácecze
dc.typemaster's thesiseng
dc.date.accepted2015-01-20
dc.contributor.refereeZitová Barbara
theses.degree.disciplinePočítačové vidění a digitální obrazcze
theses.degree.grantorkatedra kybernetikycze
theses.degree.programmeOtevřená informatikacze


Files in this item





This item appears in the following Collection(s)

Show simple item record