In recent decades, a vehicle has become the most popular transportation mechanism in the world. High accuracy and success rate are key factors in automatic vehicle detection and identification. As the most important label on vehicles, the license plate serves as a mean of public identification for them. However, it can be stolen and affixed to different vehicles by criminals to conceal their identities. Furthermore, in some cases, the plate numbers can be the same for two vehicles coming from different countries. In this thesis, we propose a new vehicle identification system that provides high degree of accuracy and success rates. The proposed system consists of four stages: license plate detection, license plate recognition, license plate province detection and vehicle shape detection. In the proposed system, the features are converted into local binary pattern (LBP) and histogram of oriented gradients (HOG) as training dataset. To reach high accuracy in real-time application, a novel method is used to update the system. Meanwhile, via the proposed system, we can store the vehicles features and information in the database. Additionally, with the database, the procedure can automatically detect any discrepancy between license plate and vehicles.
Automatic Vehicle Detection and Identification using Visual Features
2018-01-01
Electronic Theses and Dissertations
Hochschulschrift
Elektronische Ressource
Englisch
ALPR , HOG , LBP , machine learning , pattern recognition
DDC: | 629 |
Vehicle detection fusing 2D visual features
IEEE | 2004
|MPP1.01 Vehicle Detection Fusing 2D Visual Features
British Library Conference Proceedings | 2004
|Fusing multiple 2D visual features for vehicle detection
IEEE | 2006
|Fusing Multiple 2D Visual Features for Vehicle Detection
British Library Conference Proceedings | 2006
|Automatic Vehicle Detection Using Local Features -- A Statistical Approach
Online Contents | 2008
|