Recognition of Road Signs with Mixture of Neural Networks and Arbitration Modules

  • Bogusław Cyganek
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3973)


The automatic detection and recognition of road signs play important role in the driver assistance systems and can increase the safety on the roads. In this paper we propose a system of a road signs classifier which is based on ensemble of the non Euclidean distance neural networks and an arbitration unit. The input to this system comes from the sign detection module which supplies a normalized, binarized and resampled pictogram of a detected sign. The system performs classification on deformable models. The classifier is composed of a mixture of experts (binary distance neural networks) operating on slightly tilted or shifted versions of pictograms. This ensemble of experts is orchestrated by an arbitration module which operates in the winner-takes-all mode with a novel modification of promoting the most populated group of unanimous experts. The experimental results showed great robustness of the system and very fast response time which is an important factor in the driving assistance systems.


Input Pattern Deformable Model Road Sign Driver Assistance System Real Scene 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Amit, Y.: 2D Object Detection and Recognition. MIT Press, Cambridge (2002)Google Scholar
  2. 2.
    Chen, X., Yang, J., Zhang, J., Waibel, A.: Automatic Detection and Recognition of Signs From Natural Scenes. IEEE Trans. on Image Proc. 13(1), 87–99 (2004)Google Scholar
  3. 3.
    Cyganek, B.: Object Detection in Multi-Channel and Multi-Scale Images Based on the Structural Tensor. In: Gagalowicz, A., Philips, W. (eds.) CAIP 2005. LNCS, vol. 3691, pp. 570–578. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  4. 4.
    Escalera, A., Armingol, J.A.: Visual Sign Information Extraction and Identification by Deformable Models. IEEE Trans. On Int. Transportation Systems 5(2), 57–68 (2004)CrossRefGoogle Scholar
  5. 5.
    Floréen, P.: Computational Complexity Problems in Neural Associative Memories. PhD Thesis, University of Helsinki, Department of Computer Science, Finland (1992)Google Scholar
  6. 6.
    Lippman, R.: An Introduction to Computing with Neural Nets. IEEE Transactions on Acoustic, Speech, and Signal Processing 3 ASSP-4, 4–22 (1987)Google Scholar
  7. 7.
    Luo, R.C., Potlapalli, H.: Landmark Recognition Using Projection Learning for Mobile Robot Navigation. In: Proc. IEEE Int. Conf. Neural Networks, vol. 4, pp. 2703–2708 (1994)Google Scholar
  8. 8.
    Nagel, H.H.: Computer Vision for Support of Road Vehicle Driver, Institut für Algorithmen und Kognitive Systeme, Karlsruhe (2003)Google Scholar
  9. 9.
    Piccioli, G., Micheli, E.D., Parodi, P., Campani, M.: Robust Method for Road Sign Detection and Recognition. Image and Vision Computing 14, 209–223 (1996)CrossRefGoogle Scholar
  10. 10.
    Road Signs and Signalization. Directive of the Polish Ministry of Infrastructure, Internal Affairs and Administration (Dz. U. Nr 170, poz. 1393) (2002)Google Scholar
  11. 11.
    Aoyagi, Y., Asakura, T.: A Study on Traffic Sign Recognition in Scene Using Genetic Algorithms and Neural Networks. IEEE Conf. Electronics, Control, 1838–1843 (1996)Google Scholar
  12. 12.
    Zheng, Y.J., Ritter, W., Janssen, R.: An Adaptive System for Traffic Sign Recognition. In: Proc. IEEE Intelligent Vehicles Symp., pp. 165–170 (1994)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Bogusław Cyganek
    • 1
  1. 1.AGHUniversity of Science and TechnologyKrakówPoland

Personalised recommendations