Sign Board Recognition and Driver Alert System Using Machine Learning

Abstract

ABSTRACT

Sign board recognition and driver alert system which has a number of important application areas that include advance driver assistance systems, road surveying and autonomous vehicles. This system uses image processing technique to isolate relevant data which is captured from the real time streaming video. The proposed method is divided in two stages: the candidate extraction stage and the recognition stage .In first stage i.e in extraction stage area of interest is extracted and the undesired backgrounds suppressed to highlight desired information and in recognition stage, based on shape captured image is verified as traffic light or sign board. The proposed system is evaluated on video sequence, using a camera that runs at a speed of 2 frames per second. Each frame will be process and classification by using machine learning like convolution neural network .Depending upon the sign detected by system it sends the voice signal to the driver. There are more than thousands of traffic sign boards in India. This System initially train for 300 Indian traffic signs board.