prikaz prve stranice dokumenta Metode strojnog učenja za prepoznavanje objekata
  Download
PDF 1.3 MB
master's thesis
Metode strojnog učenja za prepoznavanje objekata
Diplomski rad
Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Economics in Osijek, 2021. urn:nbn:hr:145:222398
Terzić, Alen
Josip Juraj Strossmayer University of Osijek
Faculty of Economics and Business in Osijek
Chair of Quantitative Methods and Informatics

Institutional repository: EFOS REPOSITORY

Cite this document

Terzić, A. (2021). Metode strojnog učenja za prepoznavanje objekata : Diplomski rad (Master's thesis). Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Economics and Business in Osijek. Retrieved from https://urn.nsk.hr/urn:nbn:hr:145:222398

Terzić, Alen. "Metode strojnog učenja za prepoznavanje objekata : Diplomski rad." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Economics and Business in Osijek, 2021. https://urn.nsk.hr/urn:nbn:hr:145:222398

Terzić, Alen. "Metode strojnog učenja za prepoznavanje objekata : Diplomski rad." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Economics and Business in Osijek, 2021. https://urn.nsk.hr/urn:nbn:hr:145:222398

Terzić, A. (2021). 'Metode strojnog učenja za prepoznavanje objekata : Diplomski rad', Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Economics and Business in Osijek, accessed 23 November 2024, https://urn.nsk.hr/urn:nbn:hr:145:222398

Terzić A. Metode strojnog učenja za prepoznavanje objekata : Diplomski rad [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Economics and Business in Osijek; 2021 [cited 2024 November 23] Available at: https://urn.nsk.hr/urn:nbn:hr:145:222398

A. Terzić, "Metode strojnog učenja za prepoznavanje objekata : Diplomski rad", Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Economics and Business in Osijek, Osijek, 2021. Available at: https://urn.nsk.hr/urn:nbn:hr:145:222398

Metadata
TitleMetode strojnog učenja za prepoznavanje objekata : Diplomski rad
Title (english)Machine learning methods for object recognition : Graduate paper
AuthorAlen Terzić
MentorSlobodan Jelić (mentor)
Committee memberJosip Mesarić (predsjednik povjerenstva)
Committee memberSlobodan Jelić (član povjerenstva)
Committee memberMartina Briš Alić (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Economics and Business in Osijek
(Chair of Quantitative Methods and Informatics)
Osijek
Defense date and country2021-09-16, Croatia
Scientific / art field,
discipline and subdiscipline		SOCIAL SCIENCES
Economics
Business Informatics
Abstract
Svrha ovog rada je istražiti potencijale strojnog učenja i računalnog vida te pomoću tih tehnologija omogućiti računalu da raspoznaje objekte koji će u slučaju ovog rada biti novčanice iz zemalja Europe. Kao rezultat rada nastaje aplikacija za Microsoft Windows u kojoj korisnik učitava sliku naličja svoje novčanice, a program mu govori o kojoj se valuti radi i kolika je kunska protuvrijednost novčanice. Teorijski dio rada će se pozabaviti konceptima strojnog učenja i računalnog vida, pripremom podataka te pojašnjavanjem načina rada ORB i FLANN algoritama, koji će se koristiti u praktičnom dijelu rada. U rezultatima istraživanja, odnosno praktičnom dijelu, bit će prikazan proces izrade aplikacije koji započinje prikupljanjem i pripremom podataka, zatim se pojašnjava kako se učitavaju slike i prepoznaju i uspoređuju njihove značajke, a na kraju se govori o pripremi aplikacije za izvoz.
Abstract (english)
The purpose of this paper is to explore the potential of machine learning and computer vision and use those technologies to give machines the ability of object recognition. The objects in question for this paper will be banknotes from European countries. An application for Microsoft Windows will be made as a result of this paper. In the application, the user will load an image of the banknote’s face and the application will inform the user about the name of the currency and its value in Croatian Kuna. The theoretical part of the paper will further explore the concepts of machine learning, computer vision and data preparation, as well as explain the way ORB and FLANN algorithms work. The practical part of the paper will show the process of building the aforementioned application, from data collection and preparation, to loading, reading and comparing images and finally, exporting the application.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:145:222398
Study programmeTitle: Business economy; specializations in: Trade and logistics, Management, Logistic management , Business informatics
Course: Business informatics
Study programme type: university
Study level: graduate
Academic / professional title: Magistar/magistra ekonomije (Magistar/magistra ekonomije)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2022-04-22 09:20:32