support vector machine learning based traffic sign detection and shape classification using Distance to Borders and Distance from Center features

A vision based vehicle guidance system deals with the detection and recognition of traffic signs. Traffic sign recognition system collects information ahead on the road and helps the driver to make timely decisions, making driving safer and easier. This paper deals with the detection and shape classification of traffic signs from image sequences using color information. Color based segmentation techniques are employed for traffic sign detection. In this work, hue and saturation components are enhanced using look up tables. In order to improve the performance of segmentation, we used the product of enhanced hue and saturation components. Shape classification is performed using linear support vector machine. Better shape classification performance is obtained using Distance to Border and Distance from Center features of the segmented blobs.