AUTOMATED TRAFFIC SIGN DETECTION USING CNN









Abstract

The detection and recognition of road signs is one of the most popular subjects of computer vision and image processing over past few years. They play an important part in independent driving and traffic safety. Traffic regulations are a major concern when we have a look at the increasing number of vehicles. An increase in vehicles directly has an impact on the rate of accidents. Nowadays traffic signs are overlooked by people and they do not follow traffic regulation this can lead to many accidents. The goal of this project is to make the driver aware of these traffic signs and prevent accidents that may be caused. This project proposes a system that will detect and classify different types of traffic signs from images in real world and inform the user with voice instruction about the traffic sign. The number of signs used in this project for classification is 43, which are commonly used in India. Convolutional Neural Networks have been used for detection and recognition purpose. Image Augmentation is used to magnify and clean the image, thus helping to identify the traffic sign.


Modules


Algorithms


Software And Hardware