prikaz prve stranice dokumenta Prepoznavanje emocija na ljudskom licu
  Download
PDF 1.44 MB
master's thesis
Prepoznavanje emocija na ljudskom licu
Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2023. urn:nbn:hr:200:986309
Radić, Igor
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Computer Engineering and Automation
Chair of Automation and Robotics

Institutional repository: Faculty of Electrical Engineering, Computer Science and Information Technology Osijek

Cite this document

Radić, I. (2023). Prepoznavanje emocija na ljudskom licu (Master's thesis). Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek. Retrieved from https://urn.nsk.hr/urn:nbn:hr:200:986309

Radić, Igor. "Prepoznavanje emocija na ljudskom licu." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2023. https://urn.nsk.hr/urn:nbn:hr:200:986309

Radić, Igor. "Prepoznavanje emocija na ljudskom licu." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2023. https://urn.nsk.hr/urn:nbn:hr:200:986309

Radić, I. (2023). 'Prepoznavanje emocija na ljudskom licu', Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 21 May 2024, https://urn.nsk.hr/urn:nbn:hr:200:986309

Radić I. Prepoznavanje emocija na ljudskom licu [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2023 [cited 2024 May 21] Available at: https://urn.nsk.hr/urn:nbn:hr:200:986309

I. Radić, "Prepoznavanje emocija na ljudskom licu", Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:200:986309

Metadata
TitlePrepoznavanje emocija na ljudskom licu
Title (english)Facial emotion recognition
AuthorIgor Radić
MentorEmmanuel Karlo Nyarko (mentor)
Committee memberEmmanuel Karlo Nyarko (predsjednik povjerenstva)
Committee memberRatko Grbić (član povjerenstva)
Committee memberIvan Vidović (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
(Department of Computer Engineering and Automation)
(Chair of Automation and Robotics)
Osijek
Defense date and country2023-09-19, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Artificial Intelligence
Abstract
Emocionalno stanje čovjeka može se prepoznati iz izraza čovjekova lica. Iako čovjek može doživjeti puno različitih emocija, sve se one mogu svrstati u neke od glavnih kao što su ljutnja, gađenje, strah, radost, tuga, iznenađenost te neutralnost. Problem prepoznavanja emocija sa ljudskog lica u računarstvu moguće je riješiti uporabom strojnog učenja gdje će istrenirani model za sliku čovjekova lica izreći emociju koja prevladava. Ovo područje je zanimljivo zato što može poboljšati interakciju čovjeka i računala. U isto vrijeme je i vrlo izazovno zbog različitih uvjeta u kojima se uzorkuju slike na kojima je potrebno prepoznati emociju, sličnosti između nekih emocija te subjektivnog dojma koji kod ljudi utječe na prepoznavanje emocija. U ovome radu reproducirano je pet postojećih state-ofthe-art rješenja koja se temelje na konvolucijskoj neuronskoj mreži. Najbolje rješenje korišteno je za konačnu aplikaciju koja prepoznaje emocije sa ljudskog lica u stvarnom vremenu. Uspješnost pojedinih rješenja evaluirana je na FER-2013 skupu podataka.
Abstract (english)
The emotional state of a person can be recognized from the expression on their face. Even though a person can experience a wide range of different emotions, these emotions can be classified into several main classes such as anger, disgust, fear, joy, sadness, surprise, and neutrality. The problem of recognizing emotions from human face in computer science can be solved by using machine learning, where a trained model for facial images can identify the predominant emotion in a person's picture. This field is intriguing because it can enhance human-computer interaction, but at the same time, it is quite challenging due to the various conditions under which images are sampled for emotion recognition, the similarities between some emotions, and the subjective impression that affects human's recognition of emotions. In this master thesis, five existing state-of-the-art solutions based on convolutional neural networks were reproduced, and the best solution was used for the final application that recognizes emotions from human face in real-time. The performance of each solution was evaluated using the FER-2013 dataset.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:986309
Study programmeTitle: Graduate University Study Programme in Computer Engineering
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 conditionsOpen access
Terms of useLicence In copyright icon
Created on2023-10-06 11:13:21