![](bg9.png)
it does not seem possible to make a precise comparison of the accuracy of Hough
detector and color shape regular expressions. As shown in many papers the accuracy
of Hough transform is 90-95% for traffic sign detection. Accuracy of our detection
algorithm is quite less, but all the errors are false positive detections which can be
eliminated in recognition stage. Detailed accuracy comparison of Hough transform
and color shape regular expressions is a challenge for further research.
Acknowledgements
Authors are grateful to Professor Vladimir Fursov for many helpful discussions and
the constructive criticism concerning the evaluations. This work was partially
supported by Russian Foundation of Basic Research (Project No. 11-07-12051-ofi-m,
12-07-00581-a, 12-07-31208).
References
1. Shneier, M.: Road sign detection and recognition. Proc. IEEE Computer Society Int. Conf.
on Computer Vision and Pattern Recognition. (2005) 215 – 222.
2. Hopcroft, John E.; Motwani, Rajeev; Ullman, Jeffrey D. (2001). Introduction to Automata
Theory, Languages, and Computation (2 ed.). Addison Wesley. ISBN 0-201-44124-1. 551
p.
3. Aho, Alfred V. Algorithms for finding patterns in strings, In van Leeuwen, Jan. Handbook
of Theoretical Computer Science, volume A: Algorithms and Complexity. The MIT Press.
pp. 255–300, 1990.
4. Cascarano N., Rolando P., Risso F., R. Sisto. 2010. iNFAnt: NFA pattern matching on
GPGPU devices. SIGCOMM Comput. Commun. Rev. 40, 5, (2010). 20-26.
5. Freund Y., Schapire R.E. A Decision-Theoretic Generalization of on-Line Learning and an
Application to Boosting. 1995,34pp.
6. Shneier, M.: Road sign detection and recognition. Proc. IEEE Computer Society Int. Conf.
on Computer Vision and Pattern Recognition. (2005) 215 – 222.
7. Ruta A., Y. Li, X. Liu: Towards Real-Time Traffic Sign Recognition by Class-Specific
Discriminative Features. British Machine Vision Conf. (2007).
8. Torresen, J. A., W. Bakke, Y. Yang: Camera Based Speed Limit Sign Recognition System.
13th ITS World Congress and Exhibition. (2006) 115 – 129.
9. Ren, F., J. Huang, R. Jiang, R. Klette: General traffic sign recognition by feature matching.
IEEE 24th Int. Conf. Image and Vision Computing. (2009) 409 – 414.
10. Oh, J.-T., H.-W. Kwak, Y.-H. Sohn, W.-H. Kim: Segmentation and Recognition of Traffic
Signs Using Shape Information. Lecture Notes in Computer Science, Springer
Berlin/Heidelberg. Vol. 3804. (2005) 519 – 526.
11. Ballard, D.: Computer vision. Englewood Cliffs, N.J., USA. (1982).
12. Hardzeyeu, V., Klefenz, F.: On using the hough transform for driving assistance
applications. 4th International Conference on Intelligent Computer Communication and
Processing, (2008) 91-98.
13. Christoph Gustav Keller, Christoph Sprunk, Claus Bahlmann, Jan Giebeland, Gregory
Baratoff: Real-time Recognition of U.S. Speed Signs. Intelligent Vehicles Symposium,
IEEE. (2008) 518-523.
71