Real-time traffic sign detection and classification method for intelligent vehicles

In this paper, a real-time traffic sign detection and classification system with several contributions to improve the different phases of sign detection and classification is introduced. This work is a part of Automatic Driver Evaluation System (ADES) Project. The proposed system uses affine transformation coefficients as genetic algorithm parameters for sign detection. For the classification phase, the results show that neural networks are better than support vector machines for this specific application. The processing times and error rates show that this system can be used as a part of complex real-time applications.