A YOLO-Based Method for Oblique Car License Plate Detection and Recognition

Abstract

In recent years, automatic license plate recognition (ALPR) system is applied in some traffic-related applications based on deep learning. However, the new ALPR is very difficult to obtain high detection and recognition rates for oblique car license plate (LP). Recently, Silva et al. [5] proposed a warped planar object detection (WPOD) based on deep convolutional neural network (CNN) to overcome the oblique views of LP. Although the WPOD network can achieve the location and rectification of LPs, the loss function of WPOD renders the confidence parameter due to high computational complexity. This also leads to WPOD network cannot locate the optimal LP bounding box. In order to further improve the accuracy of ALPR system, we develop a simple intersection over union (IOU) algorithm to speed up the calculating process of confidence. In this paper, the four-vertex coordinates of the label bounding box and prediction bounding box of oblique LP are used to generate two rectangular boxes, and then a simple IOU algorithm is used to fast calculate the approximate value of IOU. Simulation results show that the proposed ALPR system can arrive a high accuracy of LP recognition about 95.7% on an average. In addition, the proposed system also can achieve higher recognition rate about 1% when compared to the Silva’s ALPR system.