Robust Designs for Directed Edge Overstriking CNNs with Applications

  • Yongmei Su
  • Lequan Min
  • Xinjian Zhuo
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5264)

Abstract

A kind of templates of coupled Cellular Neural Network (CNN) are introduced, which are able to generate gray edges to a binary image and overstrike them “directionally”. The robustness analysis gives the template parameter inequalities which guarantee the corresponding CNNs to work well for performing prescribed tasks. As applications, the CNNs may be used to generate art letters.

Keywords

Cellular neural network Robust designs Gray-scale image Image processing 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Chua, L.O., Yang, L.: Cellular Neural Networks: Theory and Appilcations. IEEE Trans. Circuits Syst. 35, 1257–1290 (1988)MATHCrossRefMathSciNetGoogle Scholar
  2. 2.
    Chua, L.O.: CNN: A Vision of Complex. Int. J. Bifurcation and Chaos 7(10), 2219–2425 (1997)MATHCrossRefMathSciNetGoogle Scholar
  3. 3.
    Chua, L.O., Roska, T.: Cellular Neural Networks and Visual Computing. Cambridge University Press, Cambridge (2002)Google Scholar
  4. 4.
    kananen, A., Paasio, A., Laiho, M.: CNN Applications from the Hardware Point of View: Video Sequence Segmentation. Int. J. of Circuits Syst. I 30, 117–137 (2002)MATHGoogle Scholar
  5. 5.
    Grssi, G., Grieco, L.A.: Object-orriected Image Analysis Using the CNN Univeral Machine: New Analogic CNN Algorithms for Motion Compensation, Image Synthesis and Considtency Observation. IEEE Transactions on Circuits and Systems I 50(4), 488–499 (2003)CrossRefGoogle Scholar
  6. 6.
    Chang, C., Su, S.: Apply the Counter Propagation Neural Network to Digital Image Copyright Authentication. In: 9th IEEE Int. Workshop on Cellular Neural Networks and Their Applications, pp. 110–113 (2005)Google Scholar
  7. 7.
    Arena, P., Basile, A., Fortuna, L., et al.: CNN Wave Based Compution for Robot Navigation Planning. In: Proc. of the Int. Symposium on Circuit and Systems, vol. 5, pp. 500–503 (2004)Google Scholar
  8. 8.
    Werblin, F.S., Roska, T., Chua, L.O.: The Analogic Cellular Neural Network as a Bionic Eye. Int. J. of Circuit Theory and Applications 23, 541–569 (1995)CrossRefGoogle Scholar
  9. 9.
    Bálya, D., Roska, B., Roska, T., Werblin, F.S.: A CNN Framework for Modeling Parallel Processing in a Mammalian Retina. Int. J. on Circuit Theory and Applications 30, 363–393 (2002)MATHCrossRefGoogle Scholar
  10. 10.
    Dogaru, R., Chua, L.O.: Universal CNN cells. Int. J. Bifurcation and Chaos 9(9), 1–48 (1999)MATHGoogle Scholar
  11. 11.
    Min, L., Lei, M., Dong, X.: New Templates of CNN for Extracting Corners of Objects in Gray-scale Images. J. of Univ. of Sci. Technol. Beijing 10(3), 73–75 (2003)Google Scholar
  12. 12.
    Liu., J., Min, L.: Design for CNN Templates with Performance of Global Connectivity Detection. Commun Theor. Phys. 41(1), 151–156 (2004)Google Scholar
  13. 13.
    Liu, J., Min, L.: Robust Designs for Gray-scale Global Connectivity Detection CNN Template. INT. J. Bifurcationand Chaos 17(8), 2827–2838 (2007)MATHCrossRefMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Yongmei Su
    • 1
  • Lequan Min
    • 1
  • Xinjian Zhuo
    • 2
  1. 1.Applied Science SchoolUniversity of Science and Technology BeijingBeijingPR China
  2. 2.School of Information EngineeringUniversity of Post and TelecommunicationsBeijingPR China

Personalised recommendations