Optimal edge detection under difficult imaging conditions

  • Md. Shoaib Bhuiyan
  • Yuji Iwahori
  • Akira Iwata
Poster Session II
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1352)


This paper incrementally extends the energy minimization techniques for image analysis developed by [Koch et al. 1986]. Our application is edge extraction and we use the dual intensity and line processes introduced by [Geman and Geman, 1984]. The approach seeks to minimize a global energy functional that explicitly incorporates image properties to be minimized into weighted terms of the energy functional. Our specific contribution is modifying the weighting of terms in the energy functional that were previously independent of spatial gray level change to explicitly include spatial change in the weighting. We argue that the weighting used in previous implementations resulted in a reduced contribution from the edge components due to a dominance of the spatial intensity difference term as that spatial difference increases in size. Our specific modification compensates for this effect by scaling the edge process weighting factors by the spatial difference value (to the second order), thus, maintaining the same relative effect as the spatial difference increases. We found that the proposed algorithm works significantly better as compared to Koch et al. because of this modification.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [Geman and Geman, 1984]
    S. Geman and D. Geman, “Stochastic Relaxation, Gibb's Distributions and the Bayesian Restoration of Images,” IEEE Trans., Pattern Anal. Machine Intell., Vol. PAMI-6, pp.721–741, 1984.Google Scholar
  2. [Bhuivan, 1996]
    Md. Shoaib Bhuiyan, “Contrast based Edge Detection using Artificial Neural Network,” DEng Dissertation, Nagoya Institute of Technology, Nagoya, Japan, pp. 19–21, Jan 1996.Google Scholar
  3. [Hopfield and Tank, 1985]
    J. J. Hopfield, and D. W. Tank, J. J. Hopfield, and D. W. Tank, “Neural” computation of decisions in optimization problems, Biological Cybernetics, vol. 52, pp. 141–152, 1985.Google Scholar
  4. [Koch et al., 1986]
    C. Koch, J. Marroquin, and A. Yuille: Analog “neuronal” networks in early vision; in Proc. Natl. Acad. Sci., USA, vol. 83. pp. 4263–4267, June 1986.Google Scholar
  5. [Bhuiyan et al., 1993]
    M. S. Bhuiyan, M. Sato, H. Fujimoto, and A. Iwata “Edge detection by neural network with line process.” in Proc. Int'l. Joint Conf. on Neural Networks, Nagoya, Japan, vol. 2, pp. 1223–1226. Oct. 25–29, 1993.Google Scholar
  6. [Bhuiyan et al., 1996]
    M. S. Bhuiyan, H. Matsuo, A. Iwata, H. Fujimoto, and M. Sato. “Edge Detection using Neural Network for Non-uniformly illuminated Images,” IEICE Transactions on Information and Systems, vol. E79D, no. 2, pp. 150–160; Feb 1996.Google Scholar
  7. [Bhuiyan and Iwata, 1995]
    M. S. Bhuivan and A. Iwata, “Performance Evaluation of a Neural Network based Edge Detector for high contrast images,” in World Congress on Neural Networks, Washington, D.C., USA, Vol. 2, pp. 550–554, July 17–21, 1995.Google Scholar
  8. [Marr and Hildreth, 1980]
    D. C. Marr and E. Hildreth,“Theory of Edge Detection,” in Proc. Roy. Soc. London, vol. B207, pp. 187–217, 1980.Google Scholar
  9. [Canny, 1986]
    J. Canny, “A Computational Approach to Edge Detection,” IEEE Trans., Pattern Anal. Machine Intell., vol. PAMI-8, no. 6. pp. 679–698, Nov. 1986.Google Scholar
  10. [Johnson, 1990]
    1 R. P. Johnson,” Contrast based Edge detection”, Pattern Recognition, pp. 311–318, 1990.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Md. Shoaib Bhuiyan
    • 1
  • Yuji Iwahori
    • 1
  • Akira Iwata
    • 2
  1. 1.Educational Center for Information ProcessingJapan
  2. 2.Dept. Electrical & Computer EngineeringNagoya Institute of TechnologyShowa, NagoyaJapan

Personalised recommendations