prikaz prve stranice dokumenta Identifikacija osoba pomoću računalnog vida
  Download
PDF 3.16 MB
master's thesis
Identifikacija osoba pomoću računalnog vida
Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2017. urn:nbn:hr:200:513941
Adamčević, Matej
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Computer Engineering and Automation
Chair of Automation and Robotics

Institutional repository: Faculty of Electrical Engineering, Computer Science and Information Technology Osijek

Cite this document

Adamčević, M. (2017). Identifikacija osoba pomoću računalnog vida (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:200:513941

Adamčević, Matej. "Identifikacija osoba pomoću računalnog vida." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2017. https://urn.nsk.hr/urn:nbn:hr:200:513941

Adamčević, Matej. "Identifikacija osoba pomoću računalnog vida." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2017. https://urn.nsk.hr/urn:nbn:hr:200:513941

Adamčević, M. (2017). 'Identifikacija osoba pomoću računalnog vida', Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 05 November 2024, https://urn.nsk.hr/urn:nbn:hr:200:513941

Adamčević M. Identifikacija osoba pomoću računalnog vida [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2017 [cited 2024 November 05] Available at: https://urn.nsk.hr/urn:nbn:hr:200:513941

M. Adamčević, "Identifikacija osoba pomoću računalnog vida", Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2017. Available at: https://urn.nsk.hr/urn:nbn:hr:200:513941

Metadata
TitleIdentifikacija osoba pomoću računalnog vida
Title (english)Person idetification using computer vision
AuthorMatej Adamčević
MentorRatko Grbić (mentor)
Committee memberRatko Grbić (predsjednik povjerenstva)
Committee memberEmmanuel Karlo Nyarko (član povjerenstva)
Committee memberRobert Cupec (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
(Department of Computer Engineering and Automation)
(Chair of Automation and Robotics)
Osijek
Defense date and country2017-12-14, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Process Computing
Abstract
U ovom radu opisan je razvoj sustava za identifikaciju i kontrolu pristupa osoba zasnovan na analizi uzorka šarenice metodama računalnog vida. Programsko rješenje u obliku aplikacije ostvareno je koristeći Qt razvojno okruženje i openCV biblioteku za implementaciju funkcija računalnog vida. Predloženo je rješenje za dohvaćanje fotografija dodavanjem sustava leća ispred kamere. Detaljno je opisan razvoja programskog rješenja za analizu šarenice, od predobrade slike, preko određivanja unutarnje i vanjske granice šarenice do generiranja i uspoređivanja binarnog koda za potrebe identifikacije korisnika. Sličnost dva binarna koda određuje se računanjem Hammingove udaljenosti između kodova. Omogućen je sustav za kontrolu pristupa te nadzor i upravljanje korisnicima zasnovan na SQL bazi podataka i aplikaciji izrađenoj u Qt razvojnom okruženju. Programsko rješenje testirano je na osobnom računalu (Windows 10 OS) i mikroračunalu Raspberry Pi (Raspbian Linux OS) sa ukupno 355 fotografija, pri čemu je uspoređeno 355 parova istih i 8875 parova različitih očiju. Rezultati uspoređivanja binarnih kodova istih i različitih parova očiju pokazali su da je uzorak šarenice vrlo pogodno svojstvo za identifikaciju osoba. Predloženi sustav postiže stopu lažnog prepoznavanja od 0%, a stopu lažnog odbijanja od 3.66%.
Abstract (english)
This paper describes the process of developing a person identification and access control system based on iris pattern analysis, using computer vision. The application is developed using the Qt framework and the openCV computer vision library. A solution for acquiring good quality images of the eye was proposed by stacking macro lenses in front of the camera lens. The process of developing a software solution for iris pattern analysis is described in detail, from image preprocessing, inner and outer iris boundary approximation to generating and comparing binary iris codes for user identification. The similarity between two codes is determined by calculating the Hamming distance between the two codes. An access management and supervision system has been implemented using an SQL database and the Qt based application. The software has been implemented and tested on both a PC running Windows and a Raspberry Pi microcomputer running Raspbian Linux, using a set of 355 images, resulting in 355 same eye comparisons and 8875 different eye comparisons. The results of comparing identical and different pairs of eyes have shown that the pattern of the iris is a suitable basis for person identification. The proposed system achieves an ideal 0% false recognition rate and a satisfying 3.66% false rejection rate.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:513941
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 on2018-01-29 16:25:02