prikaz prve stranice dokumenta Usporedba algoritama za prepoznavanje lica
  Download
PDF 38.17 MB
master's thesis
Usporedba algoritama za prepoznavanje lica
2022. urn:nbn:hr:137:056358
Jeger, Lorena
University of Pula
Faculty of Informatics in Pula

Cite this document

Jeger, L. (2022). Usporedba algoritama za prepoznavanje lica (Master's thesis). Pula: University of Pula. Retrieved from https://urn.nsk.hr/urn:nbn:hr:137:056358

Jeger, Lorena. "Usporedba algoritama za prepoznavanje lica." Master's thesis, University of Pula, 2022. https://urn.nsk.hr/urn:nbn:hr:137:056358

Jeger, Lorena. "Usporedba algoritama za prepoznavanje lica." Master's thesis, University of Pula, 2022. https://urn.nsk.hr/urn:nbn:hr:137:056358

Jeger, L. (2022). 'Usporedba algoritama za prepoznavanje lica', Master's thesis, University of Pula, accessed 22 November 2024, https://urn.nsk.hr/urn:nbn:hr:137:056358

Jeger L. Usporedba algoritama za prepoznavanje lica [Master's thesis]. Pula: University of Pula; 2022 [cited 2024 November 22] Available at: https://urn.nsk.hr/urn:nbn:hr:137:056358

L. Jeger, "Usporedba algoritama za prepoznavanje lica", Master's thesis, University of Pula, Pula, 2022. Available at: https://urn.nsk.hr/urn:nbn:hr:137:056358

Please login to the repository to save this object to your list.
Metadata
TitleUsporedba algoritama za prepoznavanje lica
Title (english)Comparasion of face recognition algorithms
AuthorLorena Jeger
MentorDarko Etinger (mentor)
Committee memberSnježana Babić (predsjednik povjerenstva)
Committee memberDarko Etinger (član povjerenstva)
Committee memberMirjana Radetić-Paić (član povjerenstva)
GranterUniversity of Pula
(Faculty of Informatics in Pula)
Pula
Defense date and country2022-09-15, Croatia
Scientific / art field,
discipline and subdiscipline		SOCIAL SCIENCES
Information and Communication Sciences
Information Systems and Information Science
Abstract
Prepoznavanje lica označava identifikaciju ili potvrđivanje identiteta pojedinca pomoću njegovog lica. Tehnologija je u zadnjem desetljeću dobila veliku popularnost te se široko primjenjuje u biometriji, sigurnosnim informacijama, u provedbi zakona od strane različitih tijela, tehnologiji nadzora, pametnim karticama i tako dalje. Ovaj rad pruža uvid u sam proces prepoznavanja lica. Kroz rad su nabrojani i opisani različiti algoritmi za prepoznavanje lica. Cilj ovog diplomskog rada je bio usporediti algoritme za prepoznavanje lica na malom skupu podataka. U ovome radu je implementirano i uspoređeno četiri algoritma: Eigenfaces, Fisherfaces, LBPH i SVM. Većina istraživanja temelji svoje rezultate na velikim skupovima podataka. Ovdje je korišten mali skup podataka za treniranje veličine 200 slika i skup podataka za testiranje veličine 40 slika, želeći ispitati vrijedi li visoka točnost prepoznavanja i na manjem skupu podataka.
Abstract (english)
Face recognition refers to the identification or confirmation of the identity of a person using their face. This technology has gained great popularity in the last decade and is widely used in biometrics, security information, law enforcement by various agencies, surveillance technology, smart cards, and so on. This paper provides an insight into the face recognition process itself. Several different algorithms for face recognition are used and described throughout the paper. The aim of this thesis is to compare facial recognition algorithms using a small set of data. In this work four algorithms are implemented and compared: Eigenfaces, Fisherfaces, LBPH and SVM. Most of the research is based on large sets of data. In order to find out whether high recognition accuracy can be achieved on a smaller set of data, a data set for training of 200 photos and a data set for testing of 40 photos are used.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:137:056358
Study programmeTitle: Master in Informatics; specializations in: Master in Informatics, Master in Informatics, specialisation: teaching, Master in Informatics, Master in Informatics, specialisation: teaching
Course: Master in Informatics
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra informatike (magistar/magistra informatike)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2022-09-17 20:32:51