Two-stage HOG/SVM for license plate detection and recognition

Lakhdar Djelloul Mazouz (University of Sciences and Technology of Oran)
Abdelkrim Meche (University of Sciences and Technology of Oran)
Abdelaziz Ouamri (University of Sciences and Technology of Oran)
Abdel Wahab Ait Darna (University of Sciences and Technology of Oran)

Indonesian Journal of Electrical Engineering and Computer Science
Vol 34, No 1: April 2024

Automatic license plate recognition (ALPR) is one of the technologies used in intelligent transport systems (ITS) to read vehicle license plates automatically. The extracted information has various potential applications, including but not limited to an electronic payment gateway, a system for paying parking fees, road surveillance, and managing traffic flow. In this paper, we propose an efficient method to detect and identify the Algerian license plate (LP). This method consists of a two-stage algorithm that combines the histogram of oriented gradients (HOG) with the support vector machine (SVM) classifier. The purpose of the first stage of HOG/SVM is the detection of the LP, while the recognition of the digits is accomplished by the second stage of HOG/SVM. As first contribution, a dataset of standard Algerian LP not available elsewhere is built (DZLP dataset), The second is a proposal of a very efficient pre-processing step for LP detection and digit recognition. Experimental results show that the proposed approach yields very high license plate and average digits recognition rates, which of 97.5% and 99.46%, respectively.