Automatic License Plate Recognition in Kurdistan Region of Iraq (KRI)

Volume 17 , Issue 3 , September 2015 , Pages 235-244

Authors

¹ Software Engineering Department, College of Engineering, Salahadin University

The development of countries increases the number of vehicles on the roads now than

there used to be. Consequently, controlling and managing the congestion of traffic is

virtually difficult without the use of computer technology. This paper aims to identify

automatic license plate recognition (ALPR) of vehicles in Kurdistan Region of Iraq

(KRI). It uses computer vision techniques where a cluster of Gabor feature vectors

using K-means is used, furthermore, the resulted cluster feature is optimized with

Wrapper Sub Eval technique to reduce the dimensionality of features vectors, then, the

optimized features are fed into classification techniques such as Support Vector

Machines (SVMs), K-Nearest neighbors (K-NN) and Radial Basis Function (RBF)

Neural Network in order to examine the recognition rate of the license plate of the

vehicle automatically. The experimental work shows that the proposed technique

produced promising classification results in recognizing license plate of vehicles. The

best optimal accuracy result under various illumination conditions was 96.72

Statistics