Abstract
Vehicle license plate recognition is essential due to the rising number of operational cars, which leads to an increasing difficulty of this task even for humans. Systems for car license recognition normally consist of two branch systems, namely, license plate recognition and license plate detection. The aim of the detection part is to pinpoint the car and the position of its license plate, while the objective of the recognition part is to recognize characters on that plate. In this work, the emphasis is on Arabic car license plates. In this category of plates, there are three lines containing numerals and characters. The information in these lines represents the Arabic license plate group, the English license plate group, and the type of the car, respectively. Unlike a single line license plate, in this research, we propose a two-phase training and recognition technique. First, the three lines are segmented for the purpose of training by means of deep learning (Inception-v3 and MobileNets). The second phase comprises segmenting Arabic letters and numerals in the corresponding line and then training. These trainings result in different models which are then deployed for the whole license plate testing. Training and testing were executed on the license plate image. These models are then used for license plate (LP) image deployment, which has diverse angle positioning. The accuracy rates of this technique for character recognition (CR) and line recognition (LR) were 90.81% and 95.42% respectively.
Recommended Citation
Shuriji, Mushreq Abdulhussain; Al-Behadili, Husam; and Hussain, Hadel A.
(2025)
"Iraqi’s Car License Plate Recognition Based on Deep Learning,"
Iraqi Journal for Computer Science and Mathematics: Vol. 6:
Iss.
3, Article 20.
DOI: https://doi.org/10.52866/2788-7421.1294
Available at:
https://ijcsm.researchcommons.org/ijcsm/vol6/iss3/20
