Traffic-Sign Classification Using Machine Learning Concepts

Abstract

Traffic signs are an important part of road infrastructure to provide information about the current state of the road, restrictions, prohibitions, warnings, and other helpful information for navigation. Traffic sign classification is the process of automatically recognizing traffic signs along the road, including speed limit signs, yield signs, merge signs, etc. Being able to automatically recognize traffic signs enables us to build “smarter cars”.  Traffic sign recognition is a two-stage process. Localization and recognition. Localization is detection and localizing where in an input image/frame a traffic sign is. Recognition is taking the localized ROI (Region Of interest) and recognize and classify the traffic sign. With deep learning, we can localize and recognize traffic sign by using convolution neural networks (CNN). The dataset used to train the traffic sign classification is German Traffic Sign Recognition Benchmark (GTSRB). It consists of several pre-cropped and manually labelled traffic signs in the images. Therefore, the proposed approach is used to detect the traffic signs and then classify and recognize different signs with 95% accuracy.