Prepoznavanje lica iz niza slika

scientific master's theses

• Author: Zdravko Lipošćak
• Mentor: Sven Lončarić (mentor)
• Committee member: Sven Lončarić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; (Department of Electronic Systems and Information Processing); Zagreb
• Defense date and country: 2000, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Electrical Engineering; Electronics
• Universal decimal classification (UDC): 621.3; APPLIED SCIENCES. MEDICINE. TECHNOLOGY; Electrical engineering

Abstract

U ovom radu predstavljena je metoda za automatsko segmentiranje i prepoznavanje lica iz niza slika u boji. Metoda se sastoji od četiri glavna koraka: detekcija područja boje kože lica i detekcija promjena unutar tih područja uzrokovanih kretnjama lica. U slijedeća dva koraka koristi se Karhunen-Loeve (KL) transformacija, a zatim i Fisher Linear Discriminant (FLD) metoda za predviđanje i verificiranje rezultata segmentacije lica i transformiranje slike lica u svojstveni vektor. Provedena je eksperimentalna validacija predložene metode, a dobiveni rezultati su prezentirani i diskutirani. Na kraju rada dan je stupanj prepoznavanja metode i navedeni su zaključci rada.

Abstract (english)

This paper presents a segmentation and recognition scheme for automatically detecting and recognition human face in colour image sequence. The system relies on a process with four steps which first detects regions which are likely to contain human skin in the colour image and then detects differences in this regions produced by motion in the video sequence. In next two steps Karhunen-Loeve (KL) projection and Fisher Linear Discriminant (FLD) technique are used to predict and verified segmentation result and to transform face image in feature vector. Experimental results are presented and discussed. Finally, recognition rate and conclusions are given.

• Keywords: Obrada slike; prepoznavanje lica; niz slika; KL transformacija; FLD transformacija
• Keywords (english): Image processing; face recognition; image sequence; KL projection; Fisher Linear Discriminant
• Language: croatian
• URN:NBN: urn:nbn:hr:168:918196
• Study programme: Title: Postgraduate master programme in electrical engineering; Study programme type: university; Study level: postgraduate; Academic / professional title: Magistar znanosti elektrotehnike (Magistar znanosti elektrotehnike)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2019-04-18 09:13:52