ABSTRACT
This paper describes a computer vision based system for real time traffic sign detection & recognition. Traffic signs provide drivers with very valuable information about the road, in order to make driving more safer and easier. They are designed to be easily recognized by human drivers mainly because their color and shapes are very different from the environment. The algorithm described in this paper takes advantage of these features It has two parts. The first one for the detection using shape and color information threshold to detect the Region of Interest (ROI). The second one for classification uses pattern matching. Some results on natural scene are shown.
Keywords: Color or shape processing, Computer vision, Pattern matching, Thresholding, Traffic sign recognition.
