Back to search

Institutional Repository of Vilnius University

Mašininio mokymosi taikymo efektyuvmas kartu su OCR modeliais kompiuterinėje regoje /

Abstract

dc:description

This bachelor thesis focuses on the development and evaluation of an intelligent vehicle recognition system combining machine learning and optical character recognition (OCR) techniques in the field of computer vision. The main objective is to develop a more accurate, efficient and scalable system for vehicle recognition and access control in car parks. The study starts by analysing the shortcomings of existing OCR-based systems, which are often costly, dependent on constant internet connectivity and have limited flexibility in integrating with additional cameras. These systems also face difficulties in accurately identifying vehicles in different environmental conditions and when number plates are partially covered. A large part of the work has been devoted to the design and implementation of the vehicle recognition system. This includes descriptions of the system architecture, the algorithms used for vehicle recognition and the processes involved in model training. The system database architecture and the method for calculating the Access Authorisation Index (AAI), which is used to decide whether or not to grant access based on the reliability of the recognition, are also discussed. The system has been extensively tested under a variety of conditions to assess its performance. The results show that the new system significantly improves the recognition accuracy compared to traditional OCR systems and achieves a high level of confidence even in complex scenarios. In summary, this work presents a vehicle recognition system that effectively integrates machine learning and OCR technologies, allowing a substantial increase in accuracy, efficiency and operational flexibility in vehicle access control applications. Further research directions are proposed to further extend the capabilities of the system and address remaining limitations.

Degree

thesis:*
Grantor dc:publisher
Institutional Repository of Vilnius University
Year dc:date
2024

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Jacikevičius, Jonas,

Rights

dc:rights
Statement dc:rights
  • info:eu-repo/semantics/openAccess
Language dc:language
lit

Identifiers

dc:identifier.*

Chain of custody

source
Harvested from
Vilnius University
Base URL
epublications.vu.lt/oai
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
related terms
citation

Jacikevičius, Jonas,. Mašininio mokymosi taikymo efektyuvmas kartu su OCR modeliais kompiuterinėje regoje /. Institutional Repository of Vilnius University, 2024. https://repository.vu.lt/VU:ELABAETD210643749&prefLang=en_US