prikaz prve stranice dokumenta Praćenje smjera pogleda
No public access
master's thesis
Praćenje smjera pogleda
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2017. urn:nbn:hr:168:694571
Aleksa, Antun
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Aleksa, A. (2017). Praćenje smjera pogleda (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:694571

Aleksa, Antun. "Praćenje smjera pogleda." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2017. https://urn.nsk.hr/urn:nbn:hr:168:694571

Aleksa, Antun. "Praćenje smjera pogleda." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2017. https://urn.nsk.hr/urn:nbn:hr:168:694571

Aleksa, A. (2017). 'Praćenje smjera pogleda', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 27 November 2024, https://urn.nsk.hr/urn:nbn:hr:168:694571

Aleksa A. Praćenje smjera pogleda [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2017 [cited 2024 November 27] Available at: https://urn.nsk.hr/urn:nbn:hr:168:694571

A. Aleksa, "Praćenje smjera pogleda", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2017. Available at: https://urn.nsk.hr/urn:nbn:hr:168:694571

Metadata
TitlePraćenje smjera pogleda
Title (english)Gaze Tracking
AuthorAntun Aleksa
MentorIgor Sunday Pandžić (mentor)
Committee memberIgor Sunday Pandžić (predsjednik povjerenstva)
Committee memberŽeljka Car (član povjerenstva)
Committee memberMarin Vuković (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2017-07-06, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Ovaj rad analizira moderne pristupe rješavanja problema praćenja pogleda i javno dostupnih baza podataka u svrhu testiranja metode koja je trenutno implementirana u sklopu razvojnog alata VisageSDK i stvaranja nove metode korištenjem pojačanih regresijskih stabala i linearne regresije temeljene na strojnom učenju. Rad opisuje proceduru skupljanja vlastite baze podataka sastavljene od 126 subjekata različite dobi i spola. Uz pomoć tog skupa podataka bilo je moguće testirati i usporediti rezultate dvije navedene metode.
Abstract (english)
This thesis analyses state-of-the-art gaze estimation methods and publicly free datasets in the purpose of testing a method currently implemented in VisageSDK and creating a new appearance-based method based on boosted regression trees and linear regression. It covers the procedure of collecting a completely new dataset consisted of 126 subjects of different gender and age. By using this dataset it was possible to test and compare the results of the two methods.
Keywords
Keywords (english)
Languageenglish
URN:NBNurn:nbn:hr:168:694571
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 on2019-03-13 18:35:24