prikaz prve stranice dokumenta Prepoznavanje registarskih oznaka u videu primjenom OpenALPR biblioteke
Access restricted to students and staff of home institution
undergraduate thesis
Prepoznavanje registarskih oznaka u videu primjenom OpenALPR biblioteke
2021. urn:nbn:hr:179:468788
Sanković, Josip
University of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
Department of Electronics and Computing

Cite this document

Sanković, J. (2021). Prepoznavanje registarskih oznaka u videu primjenom OpenALPR biblioteke (Undergraduate thesis). Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture. Retrieved from https://urn.nsk.hr/urn:nbn:hr:179:468788

Sanković, Josip. "Prepoznavanje registarskih oznaka u videu primjenom OpenALPR biblioteke." Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2021. https://urn.nsk.hr/urn:nbn:hr:179:468788

Sanković, Josip. "Prepoznavanje registarskih oznaka u videu primjenom OpenALPR biblioteke." Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2021. https://urn.nsk.hr/urn:nbn:hr:179:468788

Sanković, J. (2021). 'Prepoznavanje registarskih oznaka u videu primjenom OpenALPR biblioteke', Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, accessed 18 November 2024, https://urn.nsk.hr/urn:nbn:hr:179:468788

Sanković J. Prepoznavanje registarskih oznaka u videu primjenom OpenALPR biblioteke [Undergraduate thesis]. Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture; 2021 [cited 2024 November 18] Available at: https://urn.nsk.hr/urn:nbn:hr:179:468788

J. Sanković, "Prepoznavanje registarskih oznaka u videu primjenom OpenALPR biblioteke", Undergraduate thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, Split, 2021. Available at: https://urn.nsk.hr/urn:nbn:hr:179:468788

Please login to the repository to save this object to your list.
Metadata
TitlePrepoznavanje registarskih oznaka u videu primjenom OpenALPR biblioteke
Title (english)License plate recognition in video using OpenALPR library
AuthorJosip Sanković
MentorMatko Šarić (mentor)
GranterUniversity of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
(Department of Electronics and Computing)
Split
Defense date and country2021-09-27, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Basic Technical Sciences
Automatics
Abstract
U ovom radu opisana je implementacija aplikacije za prepoznavanje registarskih oznaka temeljena na OpenALPR biblioteci. Početna faza obrade je zaslužna za otkrivanje registarske oznake tako da se stvori LBP histogram vrijednosti i uspoređuje se s histogramom istreniranog algoritma. Nakon što je pronađena registarska oznaka vrši se binarizacija slike tako što svaki piksel koji ima veću vrijednost od granične vrijednosti stavlja u 1 odnosno crnu boju, a svaki piksel manji od granične vrijednosti u bijelu boju. Pomoću binarizacije smanjena je sveukupna količina podataka na slici te je jasnije prikazana registarska oznaka tako da je u fazi analize znakova lakše prepoznati područja gdje su znakovi. U sljedećoj fazi otkrivamo područje gdje bi mogla biti registarska oznaka tako što pronalazimo horizontalne i vertikalne rubove te na tom području iskrivljujemo i rotiramo sliku ako je potrebno da bi imali veću vjerojatnost otkrivanja znakova unutar OCR faze koja koristi Tesseract OCR engine. Na kraju se vraća lista najvjerojatnijih registarskih oznaka.
Abstract (english)
This paper describes the implementation of license plate recognition applications based on the OpenALPR library. The initial processing phase is credited with detecting the license plates by creating LBP histogram values and comparing it to the histogram of the trained algorithm. After the license plate is found, the images are binary so that each pixel that has a higher value than the limit values is placed in one or black, and each pixel smaller than the limit values in white. With the help of binarization, the overall amount of data in the image is reduced and the license plate is more clearly displayed, so that in the analysis phase it is easier to identify the areas where the characters are. In the next phase, we detect the area where the license plate could be by finding the horizontal and vertical edges, and in that area we distort and rotate the image if necessary to make it more likely to detect characters within the OCR phase using the Tesseract OCR engine. Finally, a list of the most likely license plates is returned.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:179:468788
Study programmeTitle: Electrical Engineering and Information Technology
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka elektrotehnike i informacijske tehnologije (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka elektrotehnike i informacijske tehnologije)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to students and staff of home institution
Terms of useLicence In copyright icon
Created on2021-12-09 12:15:55