TRAFFIC SIGN DETECTION AND RECOGNITION USING DEEP LEARNING

TRAFFIC SIGN DETECTION AND RECOGNITION USING DEEP LEARNING

K.Uma Venkatesh¹, K.Geetha Sri², K.Hari Krishna³ , M.Gowri Mani Kanta⁴

^1,2,3,4 Students, Dept. of Electronics & Communication Engineering, R.V.R & J.C College of Engineering, Guntur, Andhra Pradesh, India

---------------------------------------------------------------------***---------------------------------------------------------------------

Abstract - Traffic sign detection and recognition is an important task for autonomous vehicles and intelligent transportation systems. This task involves detecting and recognizing traffic signs from camera images in real-time. Convolutional Neural Networks (CNN) have shown to be effective in achieving high accuracy in various computer vision tasks. In this paper, we propose a CNN-based approach for traffic sign detection and recognition. Our approach involves using a deep CNN architecture that can detect and classify traffic signs simultaneously. We train the CNN model on a large dataset of traffic sign images and evaluate its performance on a real-world dataset. Our experimental results demonstrate that the proposed approach achieves high accuracy and can detect and recognize traffic signs in real-time with low computational cost. This approach can be utilized in various applications such as advanced driver assistance systems, traffic management, and autonomous driving.

Key Words:  Traffic sign detection, Traffic sign recognition, Deep Learning, Convolutional Neural Network (CNN), Graphical User Interface  (GUI)