Edge Features and Geometrical Properties Based Approach for Vehicle License Plate Detection and Localization

Abstract

Frequently, a need exists to identify vehicle license plates (VLP) for security. The extracted information from VLP is used for enforcement, access-control, and flow management, e.g., to keep a time record for automatic payment calculations or fight crime, making license plate detection crucial and inevitable in the VLP recognition system. This paper presents a robust method to detect and localize license plates in images. Specifically, the authors examine Moroccans’ VLPs. The proposed approach is based on edge features and characteristics of license plate characters. Various images including Moroccans’ VLPs were used to evaluate the proposed method. The experimental results show that the authors’ system can efficiently detect and localize the VLP in the images. Indeed, the recall/precision curve proves that 95% precision rate is obtained for recall rate value equals to 81%. In addition, the standard measure of quality is equal to 87.44%.