prikaz prve stranice dokumenta Procjena emocija pomoću dubokog učenja
No public access
master's thesis
Procjena emocija pomoću dubokog učenja
2023. urn:nbn:hr:168:916097
Lukač, Anamarija
University of Zagreb
Faculty of Electrical Engineering and Computing

Cite this document

Lukač, A. (2023). Procjena emocija pomoću dubokog učenja (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:916097

Lukač, Anamarija. "Procjena emocija pomoću dubokog učenja." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. https://urn.nsk.hr/urn:nbn:hr:168:916097

Lukač, Anamarija. "Procjena emocija pomoću dubokog učenja." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. https://urn.nsk.hr/urn:nbn:hr:168:916097

Lukač, A. (2023). 'Procjena emocija pomoću dubokog učenja', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 25 April 2024, https://urn.nsk.hr/urn:nbn:hr:168:916097

Lukač A. Procjena emocija pomoću dubokog učenja [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2023 [cited 2024 April 25] Available at: https://urn.nsk.hr/urn:nbn:hr:168:916097

A. Lukač, "Procjena emocija pomoću dubokog učenja", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:168:916097

Please login to the repository to save this object to your list.
Metadata
TitleProcjena emocija pomoću dubokog učenja
Title (english)Emotion Estimation Based on Deep Learning
AuthorAnamarija Lukač
MentorIgor Sunday Pandžić (mentor)
Committee memberIgor Sunday Pandžić (predsjednik povjerenstva)
Committee memberLea Skorin-Kapov (član povjerenstva)
Committee memberMirko Sužnjević (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2023-07-10, Croatia
Abstract
Ovaj rad daje sveobuhvatan pregled modela procjene emocija, pokrivajući teorijske modele analize emocija i lica pomoću sustava kodiranja radnji lica. Prediktivni modeli, uključujući višeslojni perceptron i konvolucijsku neuronsku mrežu, razvijeni su s različitim konfiguracijama ili prijenosnim tehnikama učenja. Slijedi evaluacija svakog modela korištenjem odgovarajućih metrika i unakrsne provjere. Rad završava prikazom rezultata i demonstracijom predviđanja emocija u stvarnom vremenu pomoću implementiranih modela.
Abstract (english)
This paper provides a comprehensive overview of emotion estimation models, covering theoretical models of emotion and face analysis using facial action coding systems. Predictive models, including multilayer perceptron and convolutional neural networsk, have been developed with different configurations or using transfer learning techniques. This is followed by an evaluation of each model using appropriate metrics and cross-validation. The paper ends with a presentation of the results and a demonstration of emotion prediction in real time using the implemented models.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:916097
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 on2023-10-11 09:35:00