prikaz prve stranice dokumenta Prepoznavanje znakova ograničenja brzine iz postojećih baza podataka
  Download
PDF 1.47 MB
undergraduate thesis
Prepoznavanje znakova ograničenja brzine iz postojećih baza podataka
Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2018. urn:nbn:hr:200:928216
Matoš, Ivona
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

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

Cite this document

Matoš, I. (2018). Prepoznavanje znakova ograničenja brzine iz postojećih baza podataka (Undergraduate 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:200:928216

Matoš, Ivona. "Prepoznavanje znakova ograničenja brzine iz postojećih baza podataka." Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2018. https://urn.nsk.hr/urn:nbn:hr:200:928216

Matoš, Ivona. "Prepoznavanje znakova ograničenja brzine iz postojećih baza podataka." Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2018. https://urn.nsk.hr/urn:nbn:hr:200:928216

Matoš, I. (2018). 'Prepoznavanje znakova ograničenja brzine iz postojećih baza podataka', Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 26 December 2024, https://urn.nsk.hr/urn:nbn:hr:200:928216

Matoš I. Prepoznavanje znakova ograničenja brzine iz postojećih baza podataka [Undergraduate thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2018 [cited 2024 December 26] Available at: https://urn.nsk.hr/urn:nbn:hr:200:928216

I. Matoš, "Prepoznavanje znakova ograničenja brzine iz postojećih baza podataka", Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2018. Available at: https://urn.nsk.hr/urn:nbn:hr:200:928216

Metadata
TitlePrepoznavanje znakova ograničenja brzine iz postojećih baza podataka
Title (english)The speed limit road signs recognition using existing road sign image databases
AuthorIvona Matoš
MentorZdravko Krpić (mentor)
MentorKrešimir Romić (mentor)
Committee memberZdravko Krpić (predsjednik povjerenstva)
Committee memberTomislav Matić (član povjerenstva)
Committee memberAlfonzo Baumgartner (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 country2018-09-12, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Data Processing
Abstract
Metoda potpornih vektora jedna je od najučinkovitijih za rješavanje problema prepoznavanja prometnih znakova. U ovom radu predstavljena je aplikacija za prepoznavanje znakova ograničenja brzine iz baze slike znakova. Aplikacija koristi standardni medijan i Gaussov filtar za uklanjanje šuma iz slika, Houghovu transformaciju za detekciju kružnog objekta i metodu potpornih vektora za prepoznavanje znaka. Prilikom implementacije metode potpornih vektora, bilo je potrebno klasificirati i istrenirati set slika iz baze rMASTIF. Analizom algoritma, uspostavljeni su prikladni parametri svih upotrijebljenih funkcija za postizanje optimalnih rezultata u većini slučajeva. Isto tako, prilikom detekcije pronađeni su primjeri gdje je nužno promijeniti parametre za postizanje točnih rezultata. Također, utvrđeni su primjeri iznimno loše kvalitete slike nad kojima je nemoguće obaviti detekciju. Usprkos tome, trening nad bazom uspješno je proveden te je testiranjem implementirane metode utvrđeno kako u većini slučajeva algoritam pravilno predviđa zadani prometni znak.
Abstract (english)
A support vector machine is one of the most efficient methods used for traffic sign recognition. In this paper application for speed limit traffic sign recognition from a traffic sign image database is presented. The application uses standard median filter and Gaussian filter for removing noise in corrupted images, Hough transformation for detection of a circular object within an image and a support vector machine for sign recognition. During the implementation of the support vector machine, it is necessary to classify and train a set of images taken from the rMASTIF database. While analyzing the algorithm adequate parameters are established for every function used, in order to achieve as optimal results as possible. Also, a few examples are found where changing the parameters is necessary to obtain accurate results. In addition, there are a few images in which it is impossible to detect a circle due to images’ bad quality. Despite identifying significant amount of problems, the support vector machine is successfully trained and tested. In most cases, the algorithm accurately predicting a speed sign in the tested images is established.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:928216
Study programmeTitle: Undergraduate University Study Programme in Computer Engineering
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2018-09-26 13:15:55