Traffic Sign Detection via Graph Based Ranking and Segmentation Algorithm

The majority of the existing traffic sign detection systems to utilize color or shape information, but the methods of remain limited in regard to detecting and segmenting traffic signs from a complex background. In this paper, we propose a novel graph-based traffic sign detection for an approach that consists of a saliency measure stage, a graph-based ranking stage, a multi threshold segmentation stage. Because the graph-based ranking algorithm with their specified color and saliency combines the information of color, saliency, spatial, and contextual relationship of the nodes, and more discriminative and robust than the other systems in terms of their handling various illumination conditions, and shape rotations, and scale changes from traffic sign images.