TRAFFIC SIGN BOARD DETECTION AND RECOGNITION FOR AUTONOMOUS VEHICLES AND DRIVER ASSISTANCE SYSTEMS

In the recent year's many approaches have been made that uses image processing algorithms to detect traffic sign boards. Edge detection is used to avoid segmentation problems of the existing method. Color based segmentation faces the challenge of adaptive thresholding which fails in real time scenarios. This proposed algorithm is yet another approach to detect traffic sign boards from video sequences. The first step of this work is the pre-processing of the video frame which is achieved by the gray scale conversion and edge detection and the second step is the extraction of the objects. Hough Transform algorithm is then applied to measure properties of image regions for further analysis. The different feature points which include perimeter, area, filled area, solidity and centroid are extracted for the detection of the traffic sign board. Feature generation and classification are done on the recognition side to get the class of the detected object. The input for the project is video sequences taken from a camera placed on the