Automatsko raspoznavanje lica

master's thesis

• Title (english): Automatic face recognition
• Author: Ivan Renić
• Mentor: Igor Sunday Pandžić (mentor)
• Committee member: Igor Sunday Pandžić (predsjednik povjerenstva)
• Committee member: Lea Skorin-Kapov (član povjerenstva)
• Committee member: Aleksandra Čereković (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2015-02-17, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Ovaj rad daje pregled trenutnog stanja područja automatskog raspoznavanja lica uz fokus na nekoliko najpopularnijih metoda koje omogućavaju računalnu identifikaciju lica – vektorska udaljenost između značajki, shape units, normalized cross correllation, PCA te LBP metoda. Metode su predstavljene na teorijskoj razini, nakon čega su prikazane i neke od dostupnih baza slika lica. Implementacija je izvedena u C++ programskom jeziku uz korištenje OpenCV i VisageSDK programskih alata te Labeled Faces in the Wild bazu podataka, a koraci implementacije prikazani su u sklopu ovog rada. Rezultati testiranja opisanih metoda također su prikazani i komentirani.

Abstract (english)

This paper provides an overview of the state in the field of facial recognition, with focus on some of the more popular methods used in the field – vector distance between facial features, shape units, normalized cross correllation, principal component analysis and local binary pattern methods. The methods are described on a theoretical level, followed by an overview of some of the available databases related to facial recognition. The described methods have been tested against the Labeled Faces in the Wild database by developing a test environment in C++ with the use of OpenCV and VisageSDK tools. Development steps have been presented, as well as the results.

• Keywords: automatsko raspoznavanje lica; vektorska udaljenost značajki lica; značajke lica; normalizirana križna korelacija; PCA; LBP; svojstveno lice; OpenCV; VisageSDK; LFW
• Keywords (english): automatic face recognition; vector distance between facial features; facial features; normalized cross correllation; principal component analysis; local binary patterns; eigenface; OpenCV; VisageSDK; labeled faces in the wild
• Language: croatian
• URN:NBN: urn:nbn:hr:168:688706
• 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: 2019-03-14 00:25:51