Traffic Sign Classification Based on Support Vector Machines and Tchebichef Moments

This paper presents a novel approach to recognize traffic signs using support vector machines and radial Tchebichef moments. More than 3000 real road images were captured by a digital camera under various weather conditions and at different times and locations. After traffic sign is detected from real road images, it is then normalized, and radial Tchebichef moments are computed as the features of traffic sign, with which SVM classifiers are trained for the fine recognition. Experimental results indicate that RBF and Sigmoid kernels combined with C -SVM or v -SVM give the best classification results, and the proposed method shows good robustness and high classification rate.