prikaz prve stranice dokumenta Prepoznavanje registarskih oznaka metodama računalnog vida
Access restricted to students and staff of home institution
master's thesis
Prepoznavanje registarskih oznaka metodama računalnog vida
Split: University of Split, University of Split, Faculty of science, 2018. urn:nbn:hr:166:815658
Selak, Marija
University of Split
Faculty of Science
Department of Informatics

Institutional repository: Repository of Faculty of Science

Cite this document

Selak, M. (2018). Prepoznavanje registarskih oznaka metodama računalnog vida (Master's thesis). Split: University of Split, Faculty of Science. Retrieved from https://urn.nsk.hr/urn:nbn:hr:166:815658

Selak, Marija. "Prepoznavanje registarskih oznaka metodama računalnog vida." Master's thesis, University of Split, Faculty of Science, 2018. https://urn.nsk.hr/urn:nbn:hr:166:815658

Selak, Marija. "Prepoznavanje registarskih oznaka metodama računalnog vida." Master's thesis, University of Split, Faculty of Science, 2018. https://urn.nsk.hr/urn:nbn:hr:166:815658

Selak, M. (2018). 'Prepoznavanje registarskih oznaka metodama računalnog vida', Master's thesis, University of Split, Faculty of Science, accessed 17 July 2024, https://urn.nsk.hr/urn:nbn:hr:166:815658

Selak M. Prepoznavanje registarskih oznaka metodama računalnog vida [Master's thesis]. Split: University of Split, Faculty of Science; 2018 [cited 2024 July 17] Available at: https://urn.nsk.hr/urn:nbn:hr:166:815658

M. Selak, "Prepoznavanje registarskih oznaka metodama računalnog vida", Master's thesis, University of Split, Faculty of Science, Split, 2018. Available at: https://urn.nsk.hr/urn:nbn:hr:166:815658

Metadata
TitlePrepoznavanje registarskih oznaka metodama računalnog vida
Title (english)Licence plate recognition based on computer vision
AuthorMarija Selak
MentorVladimir Pleština (mentor)
Committee memberVladimir Pleština (predsjednik povjerenstva)
Committee memberTomislav Matić (član povjerenstva)
Committee memberHrvoje Turić (član povjerenstva)
GranterUniversity of Split
Faculty of Science
(Department of Informatics)
Split
Defense date and country2018-12-05, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
U ovom diplomskom radu napravljen je pregled područja te su analizirani radovi koji se bave prepoznavanjem i izdvajanjem registarskih oznaka. Temeljem pregleda područja opisana je struktura ALPR sustava koja je podijeljena na tri dijela: način akvizicije slike, metode lokalizacije tablica te metode prepoznavanja znakova. Uspoređene su i testirane metode za lokalizaciju te prepoznavanje znakova registarskih oznaka. Cilj rada je da se na temelju analizirane literature i testiranih metoda da prijedlog ALPR sustava za slike prikupljene za izradu ovog diplomskog rada. Važno je voditi računa o položaju kamere prilikom akvizicije slike. Da bi se riješio problem osvjetljenja, potrebno je koristiti dobre metode predobrade. Ono u čemu se metode lokalizacije registarske oznake najviše razlikuju je način pretrage oznake na slici. Ono što se pokazalo najuspješnije je pretraga znakova. Kod prepoznavanja znakova najviše grešaka se javljalo zbog loše kvalitete slika, nagiba i kuta. Najčešće greške su zamjena sličnih znakova.
Abstract (english)
This thesis reviews the field of ALPR and analyses the literature published on it. Based on the area overview, the structure of the ALPR system is divided into three parts: image acquisition, localization methods, and character recognition methods. Methods for localization and character recognition were tested and compared. The aim of this paper is to use the analyzed literature and tested methods to propose an ALPR system for the image collection of this thesis. Camera position is important when capturing the image. To solve the problem of brightness, good pre-processing methods should be used. The way in which the licence plate localization methods most differ is the way the licence plate is searched. The most successful method was the search for characters. The majority of mistakes in identifying the characters were due to poor quality images, inclines, and angles. The most common mistake was the of similar characters replacement.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:166:815658
Study programmeTitle: Mathematics and Computer Science; specializations in: major in teaching
Course: major in teaching
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra edukacije matematike i informatike (magistar/magistra edukacije matematike i informatike)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to students and staff of home institution
Terms of useLicence In copyright icon
Created on2019-02-22 15:44:32