A Robust Method to Locate License Plates under Diverse Conditions

Abstract

Automatic License Plate Detection (ALPD) is a crucial step, which significantly affects the recognition rate and speed of the Intelligent Transport System (ITS). This paper presents a robust license plate detection method using an intelligent combination of Faster R-CNN and image processing operations. In the proposed method, initially, a vehicle is detected in the input colored RGB images using the Faster R-CNN. Next, the image with detected vehicle is fed to our developed License Plate Localization Module (LPLM) to search the possible existence of the license plate. The LPLM converts the detected vehicle image from RGB to the HSV domain and applies color segmentation along with morphological operations, and finally uses the dimensions analysis to locate the license plate. Simulations on the challenging PKU dataset reveal that the proposed technique outperforms recent state-of-the-art methods in terms of detection accuracy, precision, recall, and execution time.