Download
PDF 140.78 KB
master's thesis
18   11
Character recognition with the license plates of cars
Matej Damjanović (2015)
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Computer Engineering and Automation
Chair of Computer Engineering
Metadata
TitleRaspoznavanje znakova s registracijskih pločica automobila
AuthorMatej Damjanović
Mentor(s)Željko Hocenski (thesis advisor)
Abstract
Ovaj rad se bavi problematikom automatskog prepoznavanja registarskih tablica. Izloženi su principi detekcije područja registarske tablice s proizvoljne fotografije i algoritmi segmentacije prepoznate tablice. Nakon toga je prikazan princip normalizacije dobivenih znakova te izlučivanja karakterističnih značajki. Pristup se zasniva na binarizaciji slike s tablicom, obradi slike matematičkom morfologijom te traženja povezanih komponenata koje zadovoljavaju zadane kriterije za registarsku tablicu. Predstavlja se razvijena aplikacija koja omogućuje testiranje algoritma i prilagodbu svih korištenih parametara radi proučavanja rada ili poboljšanja. Opisuju se svi koraci i provodi se analiza algoritma nakon testiranja na korištenoj bazi slika. Uspoređuju se rezultati dobiveni pomoću razvijene programske potpore, te se opisuje utjecaj različitih parametara na kvalitetu prepoznavanja. Komentiraju se rezultati. Pruža se uvid u druge pristupe rješavanja ovog problema.
KeywordsNumber plates license plates OCR binarization detection
Parallel title (English)Character recognition with the license plates of cars
Committee MembersŽeljko Hocenski (committee chairperson)
Ivan Aleksi (committee member)
Časlav Livada (committee member)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Lower level organizational unitsDepartment of Computer Engineering and Automation
Chair of Computer Engineering
PlaceOsijek
StateCroatia
Scientific field, discipline, subdisciplineTECHNICAL SCIENCES
Electrical Engineering
Telecommunications and Informatics
Study programme typeuniversity
Study levelgraduate
Study programmeGraduate University Study Programme in Electrical Engineering; branch: Communications and Informatics, Power Engineering
Study specializationbranch: Communications and Informatics
Academic title abbreviationmag.ing.el.
Genremaster's thesis
Language Croatian
Defense date2015-12-22
Parallel abstract (English)
This paper deals with aspects of automatic number plate recognition systems. Principles of number plate area recognition are shown, as well as algorithms for segmentation of detected number plate. They are followed by the analysis of normalization and feature extraction algorithms. Approach is based on binarization of image containing licence plate, processing image using mathematical morphology and finding connected components that satisfy set-up conditions for licence plate. Developed application is presented. Application allows adjusting of all parameters used in detection and testing of algorithm which can be used in further research. All stages in algorithm are described and analysis after testing is pursued. Finally, we compare results obtained from the developed software, and discuss the influence of different parameters on recognition performance and quality. Results are commented. Thesis also presents other approaches to the problem.
Parallel keywords (Croatian)Registracijske pločice OCR binarizacija detekcija
Resource typetext
Access conditionOpen access
Terms of usehttp://rightsstatements.org/vocab/InC/1.0/
URN:NBNhttps://urn.nsk.hr/urn:nbn:hr:200:073572