Kontrola pristupa vozila pomoću računalnog vida

Rukavina, Dominik-Martin

Download
PDF 2.19 MB

master's thesis

124 64

Kontrola pristupa vozila pomoću računalnog vida

Dominik-Martin Rukavina (2017)

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

Cite this document

APA 6th Edition

Rukavina, D. M. (2017). Kontrola pristupa vozila pomoću računalnog vida (Master's thesis). Retrieved from https://urn.nsk.hr/urn:nbn:hr:200:282184

MLA 8th Edition

Rukavina, Dominik Martin. "Kontrola pristupa vozila 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:200:282184

Chicago 17th Edition

Harvard

Rukavina, D. M. (2017). 'Kontrola pristupa vozila pomoću računalnog vida', Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 10 April 2020, https://urn.nsk.hr/urn:nbn:hr:200:282184

Vancouver

Rukavina DM. Kontrola pristupa vozila 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 2020 April 10] Available at: https://urn.nsk.hr/urn:nbn:hr:200:282184

IEEE

D. M. Rukavina, "Kontrola pristupa vozila 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:200:282184

Cite this item: https://urn.nsk.hr/urn:nbn:hr:200:282184

Islandora Bookmark - Please login to use this feature

Metadata

Title	Kontrola pristupa vozila pomoću računalnog vida
Title (english)	Vehicle access control using computer vision
Author	Dominik-Martin Rukavina
Mentor	Ratko Grbić (mentor)
Committee member	Ratko Grbić (predsjednik povjerenstva)
Committee member	Emmanuel Karlo Nyarko (član povjerenstva)
Committee member	Ivan Vidović (član povjerenstva)
Granter	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) Osijek
Defense date and country	2017-12-14, Croatia
Scientific / art field, discipline and subdiscipline	TECHNICAL SCIENCES Computing Process Computing
Abstract	Rad se bavi izradom ANPR sustava za automatsku identifikaciju vozila na temelju jedinstvene registracijske oznake. U radu je dano rješenje zasnovano na računalnom vidu. Sustav se sastoji od Raspberry Pi 3B mikroračunala, Raspberry Pi NOIR kamere, te programske podrške napisane u C++ programskom jeziku i implementirane u QT okruženju pomoću OpenCV biblioteke. Implementirano programsko rješenje je predstavljeno kao niz algoritama koji se slijedno izvode. Algoritmi za prepoznavanje registracijske oznake su: algoritam za predobradu ulazne fotografije, algoritam za pronalaženje i lokalizaciju registracijske pločice, algoritam za pronalazak znakova na registracijskoj pločici, algoritam za izdvajanje i optičko prepoznavanje znakova. U radu se koristi Tesseract biblioteka kao sustav za optičko prepoznavanje znakova. Na posljetku se izvodi provjera prava pristupa korisnika. Predstavljeno je potpuno rješenje s SQLite bazom podataka. Prikazani sustav ima točnost od 99%.
Abstract (english)	This paper deals with implementing ANPR system for automatic vehicle identification based on number plates. This paper shows approach based on computer vision. The system consists of a Raspberry Pi microcomputer, Raspberry Pi NOIR camera and accompanying software. The software is written using C++ programming language and implemented in QT environment with the OpenCV computer vision library. The application is presented as a series of algorithms which are performed in sequential matter. Algorithms include: algorithm for data preprocesing, algorithm for number plate identification and localization, character segmentation and optical character recognition. Tesseract library is used for optical character recognition. Last step is access control. Application uses integrated SQLite database. Application has accuracy of approximately 99%.
Keywords
Keywords (english)
Language	croatian
URN:NBN	urn:nbn:hr:200:282184
Study programme	Title: 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 resource	Text
File origin	Born digital
Access conditions	Open access
Terms of use
Created on	2018-01-29 16:30:28