Traffic sign recognition (TSR) is a key component of advanced driver assistance systems (ADAS) and autonomous vehicles. It assists in real-time detection, classification, and interpretation of traffic signs for enhanced road safety and navigation. In this project, we compared two widely used tools for traffic sign recognition on object detection: a convolution neural network (CNN) model and the state-of-the-art YOLOv8 object detection algorithm. A CNN model was created and trained with traffic sign images, and it performed well in recognizing and classifying various traffic signs. Following this, the YOLOv8 algorithm was used to improve the accuracy and speed of the system. Features of YOLOv, it is one of the successors of leading YOLO architecture and it provides much better performance for real-time object detection with high precision and high recall rates.