Performance Evaluation of Neural Networks in Road Sign Recognition

Abstract

This paper presents an in-depth study of road sign recognition techniques leveraging neural networks. Road sign recognition stands as a critical component of intelligent transportation systems, contributing to enhanced road safety and efficient traffic management. The paper focuses on exploring various neural network architectures for example, backpropagation neural network and hybrid neural network which is a combination of two neural network (backpropagation neural network and bidirectional associative memory), training methodologies, dataset considerations, and performance evaluations for accurate and real-time recognition of road signs. The experimental result shows that the hybrid neural network is faster than the backpropagation neural network in the completion of the training process with higher recognition accuracy.