We propose a novel system for the automatic detection and recognition of traffic signs. The proposed system detects candidate regions as maximally stable extremal regions (MSERs), which offers robustness to variations in lighting conditions. Recognition is based on a cascade of SVM classifiers trained using HOG features. The training data is generated from synthetic template images freely available from an online database, thus real footage road signs are not required as training data. The proposed system is accurate at high vehicle speeds, operates under a range of weather conditions, runs at an average speed of 20 fps, and recognises all classes of ideogram based (nontext) traffic symbol from an online road sign database. We present comprehensive comparative results to illustrate the performance of the system.