Identifikacija korisnika uporabom Fisherovih i svojstvenih dlanova

scientific master's theses

• Title (english): User Identification Based on Fisherpalms and Eigenpalms
• Author: Ivan Krevatin; VIAF: 305697760
• Mentor: Slobodan Ribarić (mentor)
• Committee member: Zoran Kalafatić (predsjednik povjerenstva)
• Committee member: Slobodan Ribarić (član povjerenstva)
• Committee member: Nikola Pavešić (član povjerenstva); VIAF: 305473372
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; (Department of Electronics, Microelectronics, Computer and Intelligent Systems); Zagreb
• Defense date and country: 2006-12-11, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing; Data Processing
• Universal decimal classification (UDC): 004 - Computer science and technology. Computing. Data processing

Abstract

U ovom radu dana je analiza sustava za raspoznavanje dlanova koji se temelje na Fisherovim i svojstvenim dlanovima. Provedene su dvije skupine eksperimenata. U prvoj skupini analizirani su i uspoređeni sustavi koji koriste standardan pristup po kojemu su prostori Fisherovih i svojstvenih dlanova izračunati iz slika dlanova kojima se korisnici uvode u sustav. U drugoj skupini eksperimenata analizirana je robusnost sustava u odnosu na izbor uzoraka koji se koriste za konstrukciju Fisherovih i svojstvenih dlanova. Rezultati ukazuju na mogućnosti izrade univerzalnih prostora Fisherovih i svojstvenih dlanova, potpuno neovisnih o skupu uzoraka za unos korisnika u sustav. U radu su analizirane prednosti takvog pristupa.

Abstract (english)

In this thesis, palmprint-recognition systems based on Fisherpalms and eigenpalms are analyzed. Two groups of experiments were conducted. In the first group of experiments, systems based on the “classical” approach, where eigenpalms and Fisherpalms are calculated from the set of images that are used for the enrolment, were tested and compared. In the second group of experiments in order to test the robustness of the system, the eigenpalms and Fisherpalms were constructed from an independent set of images. The results suggest that there is a possibility of constructing universal Fisherpalm and eigenpalm spaces, completely independent of the set of samples used for the enrolment. The advantages of this approach are analyzed.

• Keywords: biometrijski sustav; verifikacija korisnika; identifikacija korisnika; Fisherovi dlanovi; svojstveni dlanovi
• Keywords (english): biometric system; User verification; User identification; Fisherpalms; Eigenpalms
• Language: croatian
• URN:NBN: urn:nbn:hr:168:068803
• Promotion: 2006
• Study programme: Title: Postgraduate master programe in computing; Study programme type: university; Study level: postgraduate; Academic / professional title: magistar inženjer računarstva (magistar inženjer računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2019-12-19 13:29:02