Analiza sustava za raspoznavanje izraza lica

master's thesis

• Title (english): Analysis of a facial expressions system
• Author: Marija Eljuga
• Mentor: Damir Seršić (mentor)
• Committee member: Damir Seršić (predsjednik povjerenstva)
• Committee member: Davor Petrinović (član povjerenstva)
• Committee member: Ana Sović Kržić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2015-07-07, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Prepoznavanje emocionalnog stanja čovjeka igra značajnu ulogu u razvoju inteligentne interakcije između čovjeka i računala. Ovaj rad bavi se implementacijom sustava za raspoznavanje 6 osnovnih izraza lica. Sustav se sastoji od dva podsustava: detekcije lica i koordinata 15 orijentirnih točaka na njemu, a potom primjene metoda strojnog učenja za treniranje i testiranje klasifikatora izraza lica. Korištene su različite varijante vektora značajki u svrhu analize rada sustava i poboljšavanja rezultata. Prikazani su dobiveni rezultati za sve korištene postupke i napravljena njihova usporedba. Na kraju rada dani su prijedlozi za unaprijeđenje točnosti sustava.

Abstract (english)

Emotional state recognition plays an important role in development of intelligent human-computer interaction. This paper focuses on implementation of a system for classification of 6 basic human facial expressions. The system is composed of two subsystems: face detection and detection of 15 landmark facial points followed by application of machine learning methods for training and testing of facial expression classifier. Different versions of feature vectors were used in oder to analyse the system funcionality and enhance results. Obtained results were presented and comparison was made for each of the procedures that were used. To conclude, suggestions for improvement of the system accuracy were given.

• Keywords: detekcija lica; detekcija karakterističnih točaka lica; strojno učenje; prepoznavanje izraza lica
• Keywords (english): face detection; characteristic facial points detection; machine learning; facial expression recognition
• Language: croatian
• URN:NBN: urn:nbn:hr:168:233324
• Study programme: Title: Information and Communication Technology; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka informacijske i komunikacijske tehnologije (magistar/magistra inženjer/inženjerka informacijske i komunikacijske tehnologije)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2018-02-06 08:40:11