Contextual edge detection using a recurrent neural network

  • Armando J. Pinho
  • Luís B. Almeida
Poster Session C: Compression, Hardware & Software, Image Databases, Neural Network, Object Recognition & Reconstruction
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1311)


If we consider edge detection as a classification problem, then it seems reasonable that context should play an important role in its study. In fact, it is frequent that neighboring pixels exhibit a strong inter-dependence. In this paper we propose a recurrent neural network for edge detection, which uses a special architecture intended to incorporate contextual information during operation. Some experimental results are presented, showing its effectiveness.


Neural Network Feature Vector Contextual Information Edge Detection Recurrent Neural Network 
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.


  1. 1.
    M. Bertero, T. A. Poggio, and V. Torre. Ill-posed problems in early vision. Proceedings of the IEEE, 1988, 76, pp. 869–889.CrossRefGoogle Scholar
  2. 2.
    A. J. Pinho and L. B. Almeida. Some results on edge enhancement with neural networks. In Proc. of the 1st IEEE Int. Conf. on Image Processing, ICIP'94, Austin, TX, 1994, pp. 893–897 (vol. III).Google Scholar
  3. 3.
    A. J. Pinho and L. B. Almeida. Edge detection filters based on artificial neural networks. In Proc. of the 8th Int. Conf. on Image Analysis and Processing, ICIAP'95, Sanremo, Italy, 1995, pp. 159–164.Google Scholar
  4. 4.
    R. O. Duda and P. E. Hart. Pattern classification and scene analysis. Wiley-Interscience, 1973.Google Scholar
  5. 5.
    E. A. Wan. Neural network classification: a Bayesian interpretation. IEEE Trans. on Neural Networks, 1990, 1, pp. 303–305.CrossRefGoogle Scholar
  6. 6.
    D. W. Ruck, S. K. Rogers, M. Kabrisky, M. E. Oxley, and B. W. Suter. The multilayer perceptron as an approximation to a Bayes optimal discriminant function. IEEE Trans. on Neural Networks, 1990, 1, pp. 296–298.CrossRefGoogle Scholar
  7. 7.
    P. A. Shoemaker. A note on least-squares learning procedures and classification by neural network models. IEEE Trans. on Neural Networks, 1991, 2, pp. 158–160.CrossRefGoogle Scholar
  8. 8.
    F. Kanaya and S. Miyake. Bayes statistical behavior and valid generalization of pattern classifying neural networks. IEEE Trans. on Neural Networks, 1991, 2, pp. 471–475.CrossRefGoogle Scholar
  9. 9.
    M. D. Richard and R. P. Lippmann. Neural network classifiers estimate Bayesian a posteriori probabilities. Neural Computation, 1991, 3, pp. 461–483.Google Scholar
  10. 10.
    A. J. Pinho and L. B. Almeida. Neural network classifiers for edge detection. In A. Sanfeliu, J. J. Villanueva, and J. Vitrià, eds., Pattern Recognition and Image Analysis, Proc. of NSPRIA'97, Barcelona, Spain, 1997, pp. 371–376.Google Scholar
  11. 11.
    D. E. Rumelhart and J. L. McClelland, eds. Parallel distributed processing — explorations in the microstructure of cognition: foundations. Volume 1, MIT Press, Cambridge, MA, 1986.Google Scholar
  12. 12.
    P. J. Werbos. Backpropagation through time: what it does and how to do it. Proceedings of the IEEE, 1990, 78, pp. 1550–1560.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Armando J. Pinho
    • 1
  • Luís B. Almeida
    • 2
  1. 1.Dep. Electrónica e Telecomunicações / INESCUniversidade de AveiroAveiroPortugal
  2. 2.INESC / Inst. Superior TécnicoLisboaPortugal

Personalised recommendations