Sustav za generiranje proširene stvarnosti korištenjem dubokih modela

master's thesis

• Title (english): System for Generating Augmented Reality Using Deep Models
• Author: Ante Miličević
• Mentor: Tomislav Hrkać (mentor)
• Committee member: Tomislav Hrkać (predsjednik povjerenstva)
• Committee member: Dejan Škvorc (član povjerenstva)
• Committee member: Zoran Kalafatić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2022-07-11, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovom radu opisan je postupak kreiranja sadržaja proširene stvarnosti u slikama
koje sadrže lica ugrad̄ivanjem umjetnih dodataka, poput virtualnih naočala, na lice
osobe. Za modele detekcije lica uspored̄eni su modeli kaskadnog klasifikatora (Viola
i Jones) i histograma orijentiranih gradijenata (McConnell) u kombinaciji sa strojem
potpornih vektora (Cortes i Vapnik). Kod lokalizacije ključnih točaka lica korišten je
duboki model konvolucijske neuronske mreže, a za sami izračun homografije dekompozicija matrice na singularne vrijednosti.

Abstract (english)

This thesis describes the process of creating augmented reality in images containing faces by embedding artificial accessories, such as virtual glasses, on a person’s
face. Described and compared models for face detection are cascade classifier (Vi-
ola and Jones) and histogram of oriented gradients (McConnell) in combination with
support vector machine (Cortes and Vapnik). Deep convolutional network was used
for localisation of facial landmarks, and homography was computed via singular value
decomposition of matrix.

• Keywords: detekcija lica; lokalizacija ključnih točaka lica; kaskadni klasifikator; histogram orijentiranih gradijenata; konvolucijska neuronska mreža; duboko učenje
• Keywords (english): face detection; facial landmark localisation; cascade classifier; histogram of oriented gradients; convolutional neural network; deep learning
• Language: croatian
• URN:NBN: urn:nbn:hr:168:163888
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-14 09:33:51