The traffic sign identification and recognition system are the process of detecting the traffic signs present on the roadside. At present, the world is developing with new technologies but the accident rate is highly increasing. The main cause is driver’s failure in interpreting the traffic sign boards. In this paper, a new method of traffic sign identification and recognition system is proposed to reduce the accident rate. The implementation of the proposed system uses Deep Neural Network (DNN) and an object detection algorithm called YOLO V5 (You Only Look Once) algorithm. This method is trained with dataset from Kaggle called traffic signs dataset in YOLO format. This system enhances the driver interactivity while driving a vehicle. As a result, it improves the attentiveness of the driver by displaying signs by producing alarm sound with improved precision rate compared to the traditional methods. A comparison of simulation results shows the effectiveness of the system.

Traffic sign identification and recognition system, Object detection algorithm, DNN, YOLO V5 algorithm, Kaggle.