prikaz prve stranice dokumenta Autentifikacija korisnika raspoznavanjem uzoraka na Android platformi
  Download
PDF 1.54 MB
master's thesis
Autentifikacija korisnika raspoznavanjem uzoraka na Android platformi
2019. urn:nbn:hr:200:736077
Kordić, Luka
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Software Engineering
Chair of Programming Languages and Systems

Cite this document

Kordić, L. (2019). Autentifikacija korisnika raspoznavanjem uzoraka na Android platformi (Master's thesis). Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek. Retrieved from https://urn.nsk.hr/urn:nbn:hr:200:736077

Kordić, Luka. "Autentifikacija korisnika raspoznavanjem uzoraka na Android platformi." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2019. https://urn.nsk.hr/urn:nbn:hr:200:736077

Kordić, Luka. "Autentifikacija korisnika raspoznavanjem uzoraka na Android platformi." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2019. https://urn.nsk.hr/urn:nbn:hr:200:736077

Kordić, L. (2019). 'Autentifikacija korisnika raspoznavanjem uzoraka na Android platformi', Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 26 October 2024, https://urn.nsk.hr/urn:nbn:hr:200:736077

Kordić L. Autentifikacija korisnika raspoznavanjem uzoraka na Android platformi [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2019 [cited 2024 October 26] Available at: https://urn.nsk.hr/urn:nbn:hr:200:736077

L. Kordić, "Autentifikacija korisnika raspoznavanjem uzoraka na Android platformi", Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2019. Available at: https://urn.nsk.hr/urn:nbn:hr:200:736077

Please login to the repository to save this object to your list.
Metadata
TitleAutentifikacija korisnika raspoznavanjem uzoraka na Android platformi
Title (english)Pattern recognition based user authentication on the Android platform
AuthorLuka Kordić
MentorGoran Martinović (mentor)
MentorBruno Zorić (mentor)
Committee memberGoran Martinović (predsjednik povjerenstva)
Committee memberAlfonzo Baumgartner (član povjerenstva)
Committee memberZdravko Krpić (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
(Department of Software Engineering)
(Chair of Programming Languages and Systems)
Osijek
Defense date and country2019-10-10, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Program Engineering
Abstract
U teorijskom dijelu ovog diplomskog rada opisuju se moderne metode raspoznavanja i autentifikacije korisnika u računalnim sustavima. Objašnjena je važnost i načini raspoznavanja korisnika. Obrađena je biometrijska identifikacija, neki njeni tipovi i njihove specifičnosti. Naglasak je stavljen na metode zasnovane na postupcima strojnog učenja i raspoznavanja uzoraka. Posebno je obrađena metoda raspoznavanja korisnika na temelju potpisa. Opisani su neki postupci strojnog učenja, algoritmi za klasifikaciju, dubinsko učenje i istražena su postojeća rješenja autentifikacije korisnika na Android platformi. U praktičnom dijelu rada ostvareno je programsko rješenje za raspoznavanje korisnika na mobilnoj platformi na temelju potpisa. Programsko rješenje izrađeno je za Android platformu i koristi fotoaparat za slikanje potpisa. Fotografija se prosljeđuje istreniranom modelu koji određuje je li potpis originalan. Ukoliko je uspješno autentificiran, korisnik je u mogućnosti pristupiti sadržaju aplikacije. U protivnom mu se pristup zabranjuje.
Abstract (english)
In the first part of this thesis, modern user authentication and recognition methods in computer systems are described. It is described how important user recognition can be and which ways of recognizing users exist. Biometric identification and its types are explained. Methods based on machine learning and classification methods are given emphasis in this paper, especially signature recognition methods. Furthermore, some important classification algorithms and machine learning techniques are explained and existing solutions to these topics are explored for Android platform. An Android application has been developed as a practical part of this thesis. Application is using phone’s camera for capturing photos of user’s signature and then forwards taken photo to machine learning model which determines whether the signature is original or fake. If successfully authenticated, user is able to access application’s content.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:736077
Study programmeTitle: Graduate University Study Programme in Computer Engineering
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2019-12-17 09:44:40