Aplikacija za kontinuiranu procjenu emocija iz izraza lica osoba u videosignalu

undergraduate thesis

• Title (english): An application for continuous assessment of emotions from facial expressions in a video signal
• Author: Luka Pranjić
• Mentor: Marko Horvat (mentor)
• Committee member: Marko Horvat (predsjednik povjerenstva)
• Committee member: Vedran Mornar (član povjerenstva)
• Committee member: Melita Fertalj (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2021-07-06, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovom radu je objašnjena softversko hijerarhijska percepcijska biblioteka Perception for Autonomous Systems ili skraćeno PAZ, ukratko elaborirani korišteni Python moduli (sqlite3, PySimpleGUI OpenCV i TensorFlow) i skup podataka FER-2013-mini, implementirana računalna aplikacija za automatsku klasifikaciju emocije dobivenih iz videosignala koristeći FER-2013-mini skup podataka i provjera točnosti klasifikacije pomoću NimStim baze izraza lica. Također je elaborirana NimStim baza izraza lica s pratećim meta podatcima. Navedene su i potencijalne primjene ove tehnologije u stvarnom svijetu. Ustanovljeno je da je klasifikacija emocija složen problem u kojem su potrebni daljnja unaprjeđenja.

Abstract (english)

In this thesis, the software hierarchical perception library Perception for Autonomous Systems (PAZ) is explained, together with the used Python modules (sqlite3, PySimpleGUI OpenCV and TensorFlow), as well as the dataset FER-2013-mini. Also, the NimStim database was explained and its supplementary metadata. A computer application for automatic classification of emotions from a video signal using the FER-2013-mini dataset and asserted the classification using the NimStim database was implemented and thoroughly described. A few real-world examples of this technology were also presented. The conclusion is that emotional classification from facial expressions is a complex practical problem that needs further advances.

• Keywords: računalni vid; strojno učenje; umjetna inteligencija; PAZ; Python; NimStim; FER-2013-mini
• Keywords (english): computer vision; machine learning; artificial intelligence; PAZ; Python; NimStim; FER-2013-mini
• Language: croatian
• URN:NBN: urn:nbn:hr:168:943876
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-13 09:19:14