Published Paper Details:

The accident rate due to negligence of observing traffic signs and not obeying traffic rules has been increasing drastically. By utilization of synthesized training data, which are created from road traffic sign images allows us to overcome the problems of traffic sign detection databases, which vary for countries and regions. This method is used for the generation of a database which consists of synthesized pictures to detect traffic signs under different view-light conditions. With this data set and a perfect Convolutional Neural Network (CNN), we can develop a data driven, traffic sign recognition and detection system which has high detection accuracy and also has high performance ability in training and recognition processes. This ensures less occurrence of accidents and also helps the driver to concentrate on driving rather than observing each and every traffic sign. The purpose of this paper is to provide an efficient method for detection and recognition of traffic signs in India. We proposed methods like neural network and feature extraction which overcome the limitations of existing methods and improve the efficiency in detecting traffic signs and also reduce the road accidents.