Advertisement

Neural Edge Detector - A Good Mimic of Conventional One Yet Robuster against Noise

  • Kenji Suzuki
  • Isao Horiba
  • Noboru Sugie
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2085)

Abstract

This paper describes a new edge detector using a multilayer neural network, called a neural edge detector (NED), and its capacity for edge detection against noise. The NED is a supervised edge detector: the NED acquires the function of a desired edge detector through training. The experiments to acquire the functions of the conventional edge detectors were performed. The experimental results have demonstrated that the NED is a good mimic for the conventional edge detectors, moreover robuster against noise: the NED can detect the similar edges to those detected by the conventional edge detector; the NED is robuster against noise than the original one is.

Keywords

Edge Detector Noisy Image Cellular Neural Network Active Contour Model Canny Edge Detector 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Kass, M., Witkin, A. and Terzopoulos, D.: Snakes: Active contour models, Int. Journal Computer Vision, Vol. 1, No. 3, pp. 321–331 (1988).Google Scholar
  2. 2.
    Duda, R. and Hart, P.: Pattern Classification and Scene Analysis, Wiley, pp. 267–272 (1971).Google Scholar
  3. 3.
    Hueckel, M.: A local visual operator which recognizes edges and lines, Journal of ACM, Vol. 20, No. 4, pp. 634–647 (1973).Google Scholar
  4. 4.
    Marr, D. and Hildreth, E.: Theory of edge detection, Proc. Royal Soc. London, Vol. B207, pp. 187–21 (1980).Google Scholar
  5. 5.
    Canny, J.: A computational approach to edge detection, IEEE Trans. Pattern Analysis & Machine Intelligence, Vol. 8, pp. 679–698 (1986).Google Scholar
  6. 6.
    Yin, L., Astola, J. and Neuvo, Y.: A new class of nonlinear filters-neural filters, IEEE Trans. Signal Processing, Vol. 41, No. 3, pp. 1201–1222 (1993).Google Scholar
  7. 7.
    Zhang, Z. and Ansari, N.: Structure and properties of generalized adaptive neural filters for signal enhancement, IEEE Trans. Neural Networks, Vol. 7, No. 4, pp. 857–868 (1996).Google Scholar
  8. 8.
    Suzuki, K., Horiba, I. and Sugie, N.: Efficient approximation of a neural filter for quantum noise removal in X-ray images, Neural Networks for Signal Processing IX, IEEE Press, pp. 370–379 (1999).Google Scholar
  9. 9.
    Suzuki, K., Horiba, I. and Sugie, N.: Edge detection from noisy images using a neural edge detector, Neural Networks for Signal Processing X, IEEE Press, pp. 487–496 (2000).Google Scholar
  10. 10.
    Funahashi, K.: On the approximate realization of continuous mappings by neural networks, Neural Networks, Vol. 2, pp. 183–192 (1989).Google Scholar
  11. 11.
    Suzuki, K., Horiba, I., Ikegaya, K. and Nanki, M.: Recognition of coronary arterial stenosis using neural network on DSA system, Systems and Computers in Japan, Vol. 26, No. 8, pp. 66–74 (1995).Google Scholar
  12. 12.
    Suzuki, K., Horiba, I. and Sugie, N.: Designing the optimal structure of a neural filter, Neural Networks for Signal Processing VIII, IEEE Press, pp. 323–332 (1998).Google Scholar
  13. 13.
    Suzuki, K., Horiba, I. and Sugie, N.: An approach to synthesize filters with reduced structures using a neural network, Quantum Information II, World Scientific Pub., pp. 205–218 (2000).Google Scholar
  14. 14.
    Suzuki, K., Horiba, I. and Sugie, N.: A simple neural network pruning algorithm with application to filter synthesis, Neural Processing Letters, Vol. 13, No. 1, p. 12pages (2001).Google Scholar
  15. 15.
    Aizenberg, I.: Processing of noisy and small-detailed gray-scale image using cellular neural networks, J. Electronic Imaging, Vol. 6, No. 3, pp. 272–285 (1997).Google Scholar
  16. 16.
    Aizenberg, I., Aizenberg, N. and Vandewalle, J.: Precise edge detection: representation by Boolean functions, implementations on the CNN, Proc. IEEE Int. Workshop Cellular Neural Networks & Their Appli., London, pp. 301–306 (1998).Google Scholar
  17. 17.
    Aizenberg, I., Aizenberg, N., Bregin, T., Butakov, C. and Farberov, E.: Image processing using cellular neural networks based on multi-valued and universal binary neurons, Neural Networks for Signal Processing X, IEEE Press, pp. 557–566 (2000).Google Scholar
  18. 18.
    Rekeczky, C., Roska, T. and Ushida, A.: CNN-based difference-controlled adaptive nonlinear image filters, Int. J. Circuit Theory & Appli., Vol. 26, pp. 375–423 (1998).Google Scholar
  19. 19.
    Lu, S. and Shen, J.: Artificial neural networks for boundary extraction, Proc. IEEE Int. Conf. Sys., Man and Cybernetics, Vol. 3, pp. 2270–2275 (1996).Google Scholar
  20. 20.
    He, Z. and Siyal, M.: Edge detection with BP neural networks, Proc. Int. Conf. Signal Processing, Vol. 2, London, UK, pp. 1382–1384 (1998).Google Scholar
  21. 21.
    Nagai, H., Miyanaga, Y. and Tochinai, K.: An edge detection by using self-organization, Proc. IEEE ICASSP, pp. 2749–2752 (1998).Google Scholar
  22. 22.
    Toivanen, P., Ansamaki, J., Leppajarvi, S. and Parkkinen, J.: Edge detection of multispectral images using the 1-D self organizing map, Proc. ICANN, Skovde Sweden, pp. 737–742 (1998).Google Scholar
  23. 23.
    Bhuiyan, M., Sato, M., Fujimoto, H. and Iwata, A.: Edge detection by neural network with line process, Proc. IJCNN, pp. 1223–1226 (1993).Google Scholar
  24. 24.
    Iwata, H., Agui, T. and Nagahashi, H.: Boundary detection of color images using neural networks, Proc. IEEE ICNN, pp. 1426–1429 (1995).Google Scholar
  25. 25.
    Aizenberg, I., Aizenberg, N. and Vandewalle, J.: Multi-Valued and Universal Binary Neurons-Theory, Learning and Applications-, Kluwer Academic Pub. (2000).Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • Kenji Suzuki
    • 1
  • Isao Horiba
    • 1
  • Noboru Sugie
    • 2
  1. 1.Faculty of Information Science and TechnologyAichi Prefectural UniversityNagakuteJapan
  2. 2.Faculty of Science and TechnologyMeijo UniversityNagoyaJapan

Personalised recommendations