prikaz prve stranice dokumenta Prepoznavanje svjetskih znamenitosti iz slika
No public access
master's thesis
Prepoznavanje svjetskih znamenitosti iz slika
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2020. urn:nbn:hr:168:018313
Gulan, Marko
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Gulan, M. (2020). Prepoznavanje svjetskih znamenitosti iz slika (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:018313

Gulan, Marko. "Prepoznavanje svjetskih znamenitosti iz slika." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2020. https://urn.nsk.hr/urn:nbn:hr:168:018313

Gulan, Marko. "Prepoznavanje svjetskih znamenitosti iz slika." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2020. https://urn.nsk.hr/urn:nbn:hr:168:018313

Gulan, M. (2020). 'Prepoznavanje svjetskih znamenitosti iz slika', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 02 July 2024, https://urn.nsk.hr/urn:nbn:hr:168:018313

Gulan M. Prepoznavanje svjetskih znamenitosti iz slika [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2020 [cited 2024 July 02] Available at: https://urn.nsk.hr/urn:nbn:hr:168:018313

M. Gulan, "Prepoznavanje svjetskih znamenitosti iz slika", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2020. Available at: https://urn.nsk.hr/urn:nbn:hr:168:018313

Metadata
TitlePrepoznavanje svjetskih znamenitosti iz slika
Title (english)Recognition of World Landmarks form Photographies
AuthorMarko Gulan
MentorGoran Delač (mentor)
Committee memberGoran Delač (predsjednik povjerenstva)
Committee memberMarin Šilić (član povjerenstva)
Committee memberKlemo Vladimir (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2020-07-07, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Prepoznavanje znamenitosti iz slika godinama je bio nerješiv problem za računala. No, u posljednjih nekoliko godina, računala postaju sve bolja u rješavanja istoga. U ovom radu je opisano što su umjetne neuronske mreže te kako ih iskoristiti za rješavanje navedenog problema. Poseban naglasak stavljen je na konvolucijske neuronske mreže koje daju odlične rezultate na sličnim problemima računalnog vida. Na kraju se u prikazani i ocijenjeni rezulati učenja četiriju konvolucijskih mreža nad skupom podataka Google Landmarks Dataset.
Abstract (english)
Landmark recognition from images had been a problem computers couldn’t solve for ages. However, in last few years, they are getting better at solving it. In this thesis, it is described what artificial neural networks are and how to use them to solve given problem. The main emphasis is on convolutional neural networks that give excellent results on similar computer vision problems. At the end, results of training four convolutional neural network on dataset called Google Landmarks Dataset are shown and evaluated.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:018313
Study programmeTitle: Computing
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2023-01-13 12:23:01