A system for recognizing traffic signs has indeed been developed to ensure autonomous vehicles in adhering to speed limits while also improving security and safety. The major purpose is to make it easier for autonomous driving cars to maintain their attention on the road and avoid accidents in everyday scenarios. Along with the advancement of deep learning, it is now feasible to utilize a deep learning model to detect and recognize traffic lights. In recent years, many high-accuracy computer vision and machine learning models have performed admirably on traffic sign recognition classification problems. However, these models have a restriction in that they can only identify huge objects and their detection speed is slower. This research focuses on using a convolutional neural network (CNN) to train the dataset to create a deep learning model to improve its recognition speed and accuracy. This model improves accuracy and works well during the object recognition process.