Road-sign segmentation and recognition in natural scenes

The detection and recognition of road-sign is an important part of achieving intelligent vehicle. In the system, we use the HSI space to detect the road-sign which has been proposed. After detection, we use a method which we proposed for segmentation to get all road-signs in the image. Then we use the ratio of the size of road-sign and the size of the rectangle which is minimal and contain the road-sign to define the shape of the road-sign. Finally, in order to achieve real-time, we abstract hu moment of road-sign and use SVM for recognition in our system. Hundreds of images have been tested, and the system show high ratio of recognition and process rapidly.

[1]  S. Lafuente-Arroyo,et al.  Traffic sign shape classification evaluation I: SVM using distance to borders , 2005, IEEE Proceedings. Intelligent Vehicles Symposium, 2005..

[2]  Dia I. Abu-Al-Nadi,et al.  Road traffic sign detection in color images , 2003, 10th IEEE International Conference on Electronics, Circuits and Systems, 2003. ICECS 2003. Proceedings of the 2003.

[3]  Min Shi,et al.  Support vector machines for traffic signs recognition , 2008, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).

[4]  A. Sreekumar,et al.  support vector machine learning based traffic sign detection and shape classification using Distance to Borders and Distance from Center features , 2008, TENCON 2008 - 2008 IEEE Region 10 Conference.

[5]  Ming-Kuei Hu,et al.  Visual pattern recognition by moment invariants , 1962, IRE Trans. Inf. Theory.

[6]  Marti A. Hearst.  Trends & Controversies: Support Vector Machines , 1998, IEEE Intell. Syst..

[7]  P. Gil-Jim.  Traffic sign shape classification based on Support Vector Machines and the FFT of the signature of blobs , 2007 .

[8]  H. Fleyeh.  Shadow And Highlight Invariant Colour Segmentation Algorithm For Traffic Signs , 2006, 2006 IEEE Conference on Cybernetics and Intelligent Systems.

[9]  H. Fleyeh,et al.  Traffic sign classification using invariant features and Support Vector Machines , 2008, 2008 IEEE Intelligent Vehicles Symposium.

[10]  Francisco López-Ferreras,et al.  Road-Sign Detection and Recognition Based on Support Vector Machines , 2007, IEEE Transactions on Intelligent Transportation Systems.