Adaptive Parameters Determination Method of Pulse Coupled Neural Network Based on Water Valley Area

  • Min Li
  • Wei Cai
  • Zheng Tan
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4233)


Pulse coupled neural network (PCNN) is different from traditional artificial neural networks, models of which have biological background and are based on the experimental observations of synchronous pulse bursts in the cat visual cortex. However, it is very difficult to determine the exact relationship between the parameters of PCNN model. Focusing on the famous difficult problem of PCNN, how to determine the optimum parameters automatically, this paper proposes the definition of water valley area, establishes a modified PCNN, and puts forward an adaptive PCNN parameters determination algorithm based on water valley area. Extensive experimental results on image processing demonstrate its validity and robustness.


Image Segmentation Synthetic Aperture Radar Iteration Time Pulse Couple Neural Network Segmented Result 
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.
    Eckhorn, R., ReitBoeck, H.J., et al.: Feature linking via synchronization among distributed assemblies: simulation of results form cat visual cortex. Neural Computation 2, 293–307 (1990)CrossRefGoogle Scholar
  2. 2.
    Kuntimad, G., Ranganath, H.S.: Perfect image segmentation using pulse coupled neural networks. IEEE Trans. Neural Networks 10, 591–598 (1999)CrossRefGoogle Scholar
  3. 3.
    Ma, Y.D., Dai, R.L., Li, L.: Automated image segmentation using pulse coupled neural networks and image’s entropy. Journal of China Institute of Communications 23, 46–51 (2002)Google Scholar
  4. 4.
    Liu, Q., Ma, Y.D., Qian, Z.B.: Automated image segmentation using improved PCNN model based on cross-entropy. Journal of Image and Graphics 10, 579–584 (2005)Google Scholar
  5. 5.
    Gu, X.D., Guo, S. D., Yu, D.H.: A new approach for automated image segmentation based on unit-linking PCNN. In: Proceedings of the first International Conference on Machine learning and Cybernetics, Beijing, China, pp. 175–178 (2002)Google Scholar
  6. 6.
    Karvonen, J.A.: Baltic sea ice SAR segmentation and classification using modified pulse-coupled neural networks. IEEE Trans. Geoscience and Remote Sensing 42, 1566–1574 (2004)CrossRefGoogle Scholar
  7. 7.
    Bi, Y.W., Qiu, T.S.: An adaptive image segmentation method based on a simplified PCNN. Acta Electronica Sinica 33, 647–650 (2005)Google Scholar
  8. 8.
    Aboul, E.H., Jafar, M.A.: Digital Mammogram Segmentation Algorithm Using Pulse Coupled Neural Networks. In: Proceedings of the 3th International Conference on Image and Graphics, Hong Kong, China, pp. 92–95 (2004)Google Scholar
  9. 9.
    Gu, X.D., Yu, D.H.: Image shadow removal using pulse coupled neural network. IEEE Trans. Neural Networks 16, 692–695 (2005)CrossRefGoogle Scholar
  10. 10.
    Ma, Y.D., Shi, F., Li, L.: Gaussian noise filter based on PCNN. In: IEEE Int. Conf. Neural Networks & Signal Processing, Nanjing, China, pp. 149–151 (2003)Google Scholar
  11. 11.
    Johnson, J.L., Taylor, J.R., Anderson, M.: Pulse coupled neural network shadow compensation. In: SPIE Conference on Applications and Science of Computational Intelligence, Orlando, Florida, pp. 452–456 (1999)Google Scholar
  12. 12.
    Ekblad, U., Kinser, J.M., Atmer, J., Zetterlund, N.: The intersecting cortical model in image processing. Nuclear Instruments and Methods in Physics Research A 525, 392–396 (2004)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Min Li
    • 1
    • 2
  • Wei Cai
    • 2
  • Zheng Tan
    • 1
  1. 1.School of Electronics and Information EngineeringXi’an Jiaotong UniversityXi’anP.R. China
  2. 2.Xi’an Research Inst. of Hi-TechP.R.C.

Personalised recommendations