Traffic Sign Recognition and Classification using Deep Neural Networks

Abstract

Deep Neural Networks such as Recurrent Neural Networks (RNNs) and Convolutional Neural Networks (CNNs), have been applied in various applications, including machine vision and computer vision. One of the most notable emerging applications of deep neural networks is Advanced Driver Assistance System (ADAS). In ADAS model, the deep neural networks have outperformed the manual human performance in terms of traffic sign recognition and classification. to the problem of traffic sign recognition, with promising results. This study has proposed a novel Convolutional Neural Network (CNN) architecture for recognizing and classifying traffic signs. The German Traffic Sign Recognition Benchmark dataset is used for experimental analysis. The outcome shows that the proposed model performs comparatively better. The results also indicate that the implemented CNN model with Adam optimizer and RankMax activation performs well for recognizing and classifying traffic sign images.