License plate detection optimization based on YOLO algorithm

Abstract

In order to improve the recognition ability of license plates, this paper proposes an end-to-end license plate optimization recognition algorithm based on YOLOv3 algorithm, and proposes a method based on detection dewarping convolutional neural network (DU-CNN). Based on YOLOv3 model, the Darknet-31 network is proposed. This structure not only improves the extraction ability of the network but also speeds up the extraction speed. According to the characteristics of small license plate characters, a network prediction scale is added to improve the detection ability of license plate characters. Experimental results show that the proposed method has better recognition accuracy, outperforms some commercial systems in difficult data sets, and has better stability.