DOMINANT COLOR TRANSFORM AND CIRCULAR PATTERN VECTOR FOR TRAFFIC SIGNDETECTION AND RECOGNITION

In this paper, a new traffic sign detection algorithm and a symbol rec ognition algorithm are proposed. For a traffic sign detection, a domin ant color transform is introduced, which serves as a tool of highlight ing a dominant primary color, while discarding the other two primary c olors. For a symbol recognition, the curvilinear shape distribution on a circle centered on the centroid of the symbol, called a circular pa ttern vector, is used as a spatial feature of the symbol. The circular pattern vector is invariant to scaling, translation, and rotation. As simulation results, the effectiveness of traffic sign detection and r ecognition algorithms are confirmed.