Road Sign Recognition Using Convolution Neural Network

Abstract

Traffic sign recognition is a crucial part of autonomous vehicles. It is the major factor in ensuring the safety and efficiency of autonomous vehicles. Many artificial intelligence approaches contribute in developing traffic sign recognition systems. Mostly Convolutional Neural Networks (CNNs) have shown remarkable performance in image classification tasks for traffic sign recognition process. Training deep CNNs for traffic sign recognition requires a significant amount of labeled data, which can be time consuming and resource intensive to obtain. In this project we built the basic CNN model from scratch, while the Transfer learning model use pretrained network that is MobileNet. The result demonstrate that while the basic CNN model performs adequately, the MobileNet model significantly outperform in terms of accuracy and efficiency. This project brings out the potential of deep learning in enhancing the reliability and efficiency of road sign recognition systems, contributing to safer and more intelligent transportation solutions.