WCSE 2020 Summer
ISBN: 978-981-14-4787-7 DOI: 10.18178/wcse.2020.06.022

Research on License Plate Recognition of Chinese Vehicle Based on GWO-SVM Algorithm

Hao Ding, Jianguo Shen

Abstract— License Plate Recognition (LPR) technology has been widely used in traffic management system. In order to improve the efficiency of traditional LPR, this paper proposes a lightweight LPR algorithm based on Support Vector Machine (SVM) model with Grey Wolf Optimization (GWO) algorithm. GWO algorithm is used to seek the optimal parameters of the penalty factor and kernel parameter of SVM, which improves the accuracy of license plate character recognition. Besides, Gaussian filtering and grey level stretching are introduced for image preprocessing to enhance the quality of the gray level license plate image. Experiment results show that the recognition accuracy of the proposed character recognition model can reach more than 95%. Compared with state-of-the-art LPR models using SVM, this algorithm is much faster on iteration.

Index Terms—license plate recognition; Support Vector Machine; Grey Wolf Optimization algorithm; character recognition

Hao Ding, Jianguo Shen
College of Physics and Electronic Information Engineering , Zhejiang Normal University, CHINA

[Download]


Cite: Hao Ding, Jianguo Shen , " Research on License Plate Recognition of Chinese Vehicle Based on GWO-SVM Algorithm " Proceedings of 2020 the 10th International Workshop on Computer Science and Engineering (WCSE 2020), pp. 132-137, Shanghai, China, 19-21 June, 2020.