Comparative Study of Machine Learning Algorithms for Traffic Sign Recognition

Abstract

The increasing integration of intelligent transportation systems has brought forth a critical need for accurate and efficient traffic sign detection algorithms. In this research, we conduct a comprehensive comparative analysis of four prominent convolutional neural network (CNN) architectures—LeNet, ResNet, VGG, and a standard CNN model—for their performance in traffic sign detection. The evaluation is conducted on a diverse dataset, utilizing the German Traffic Signs Recognition Benchmark (GTSRB). Our study encompasses an in-depth examination of accuracy metrics and performance under varying conditions, such as challenging lighting, occlusion, and environmental complexities. The results demonstrate nuanced differences in accuracy and computational efficiency among the algorithms. LeNet exhibits notable improvements in real-time processing, while ResNet showcases enhanced accuracy, and VGG demonstrates robustness in challenging conditions. The findings provide valuable insights into the strengths and weaknesses of each algorithm, aiding researchers and practitioners in selecting the most suitable model for specific traffic sign detection applications. This research contributes to advancing the field of computer vision in intelligent transportation systems, with implications for enhancing road safety and efficiency. Key Words: traffic sign recognition, deep learning, Res-Net, VGG19, CNN, LeNet.