Automatic Edge Detection by Combining Kohonen SOM and the Canny Operator

  • P. Sampaziotis
  • N. Papamarkos
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3773)

Abstract

In this paper a new method for edge detection in grayscale images is presented. It is based on the use of the Kohonen self-organizing map (SOM) neural network combined with the methodology of Canny edge detector. Gradient information obtained from different masks and at different smoothing scales is classified in three classes (Edge, Non Edge and Fuzzy Edge) using an hierarchical Kohonen network. Using the three classes obtained, the final stage of hysterisis thresholding is performed in a fully automatic way. The proposed technique is extensively tested with success.

Keywords

Receiver Operating Characteristic Gradient Magnitude Edge Pixel Ground Truth Image Sobel Operator 
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.

References

  1. 1.
    Canny, J.: A computational approach to edge detection. IEEE Transactions on pattern analysis and machine intelligence 8(6), 679–698 (1986)CrossRefGoogle Scholar
  2. 2.
    Liang, L.R., Looney, C.G.: Competitive fuzzy edge detection. Applied Soft Computing 3, 123–137 (2003)CrossRefGoogle Scholar
  3. 3.
    Marr, D., Hildreth, E.: Theory of edge detection. In: Proc. Roy. Soc. London B-207, pp. 187–217 (1980)Google Scholar
  4. 4.
    Kohonen, T.: Self-Organizing Maps, 2nd edn. Springer, Berlin (1997)MATHGoogle Scholar
  5. 5.
    Toivanen, P.J., Ansamaki, J., Parkkinen, J.P.S., Mielikainen, J.: Edge detection in multispectral images using the self-organizing map. Pattern Recognition Letters 24, 2987–2994 (2003)CrossRefGoogle Scholar
  6. 6.
    Yitzhaky, Y., Peli, E.: A Method for Objective Edge Detection Evaluation and Detector Parameter Selection. IEEE Transactions on pattern analysis and machine intelligence 25(8), 1027–1033 (2003)CrossRefGoogle Scholar
  7. 7.
    Bowyerm, K., Kranenburg, C.: Edge Detector Evaluation Using Empirical ROC Curves. Computer Vision and Image Understanding 84, 77–103 (2001)CrossRefGoogle Scholar
  8. 8.
    Law, T., Itoh, H., Seki, H.: Image Filtering, Edge Detection and Edge Tracing Using Fuzzy Reasoning. IEEE Transactions on pattern analysis and machine intelligence 18(5), 481–491 (1996)CrossRefGoogle Scholar
  9. 9.
    Pratt, W.K.: Digital Image Processing, 3rd edn. John Wiley & Sons, Inc., Chichester (2001)CrossRefGoogle Scholar
  10. 10.
    Pinho, A.J.: Modeling Non-Linear Edge Detectors Using Artificial Neural Networks. In: Proc. of the 15th Annual Int. Conf. of the IEEE Eng. in Medicine and Biology Soc., San Diego, CA, U.S.A, pp. 306–307 (October 1993)Google Scholar
  11. 11.
    Weller, S.: Artificial Neural Net Learns the Sobel Operators (and More), Applications of Artificial Neural Networks II. In: SPIE Proceedings Vol SPIE-1469, pp. 69–76 (August 1991)Google Scholar
  12. 12.
    Bezdek, J.C., Kerr, D.: Training Edge Detecting Neural networks with Model-Based Examples. In: Proc 3rd International Confererence on Fuzzy Systems, FUZZ-IEEE 1994, Orlando, Florida, USA, June 26 - 29, pp. 894–901 (1994)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • P. Sampaziotis
    • 1
  • N. Papamarkos
    • 1
  1. 1.Image Processing and Multimedia Laboratory, Department of Electrical & Computer EngineeringDemocritus University of ThraceXanthiGreece

Personalised recommendations