INDIAN TRAFFIC SIGN DETECTION AND RECOGNITION USING DEEP CONVOLUTION NEURAL NETWORK

Road and traffic sign recognition is an important field of study. It has got its importance in the areas like the development of intelligent transport system (ITS) and road safety norms. It can help the driver to inform about the upcoming signs that can help to navigate and to avoid potential risky traffic violations and situations. Many different techniques were available in the literature that are predominantly based on Hog and SIFT features. In this paper, we propose to use Deep Convolution Neural Networks to build a model that can predict the type of traffic sign. The database of traffic sign is taken from Kaggle website. The implementation is done by using 24 classes. The results are tested for Indian traffic signs and the results are produced with better accuracy.