Advertisement

Adaptive adjustment of the CNN output function to obtain contrast enhancement

  • M. A. Jaramillo Morán
  • J. A. Fernández Muñoz
Images
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1607)

Abstract

In this paper we propose an adaptive modification of the output function of the CNN (Cellular Neural Network) model to perform contrast enhancement of an image. First, we define the output function to operate in the interval [0,1] with variable saturation limits in order to adapt the behaviour of the network to the grey levels in the neighbourhood of every cell. Then we propose a three-layers CNN where the mean value of the neighbourhood of a pixel is obtained by the first layer and the calculation of the mean deviation of the pixel values from the mean in the same neighbourhood is carried out by the second one. These parameters are control signals that define the saturation limits of the piecewise linear output function of each cell in the third layer, the output of the network, adapting it to the neighbourhood of each cell. Some examples are presented to demonstrate the capabilities of the model.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    L. O. Chua, L. Yang. “Cellular Neural Networks: Theory.” IEEE Trans. on Circuits and Systems. Vol. 35, No. 10. October 1988. pp. 1257–1272.MATHCrossRefMathSciNetGoogle Scholar
  2. [2]
    L. O. Chua, L. Yang. “Cellular Neural Networks: Applications.” IEEE Trans. on Circuits and Systems. Vol. 35, No. 10. October 1988. pp. 1273–1290.CrossRefMathSciNetGoogle Scholar
  3. [3]
    T. Matsumoto, L. O. Chua, R. Furukawa. “CNN Cloning Template: Hole-Filler”. IEEE Trans. on Circuits and Systems. Vol. 37, No. 5. May 1990 pp. 635–638.CrossRefGoogle Scholar
  4. [4]
    T. Matsumoto, L. O. Chua, T. Yokohama. “Image Thinning with a Cellular Neural Network.” IEEE Trans. on Circuits and Systems. Vol. 37, No. 5. May 1990. pp. 638–640.CrossRefGoogle Scholar
  5. [5]
    B. E. Shi, T. Roska, L. O. Chua. “Design of Linear Cellular Neural Network for Motion Sensitive Filtering.” IEEE Trans. on Circuits and Systems. II: Analog and Digital Signal Processing. Vol. 40, No. 5. May 1993. pp. 320–331.MATHCrossRefGoogle Scholar
  6. [6]
    L. O. Chua, T. Roska. “The CNN Paradigm.” IEEE Trans. on Circuits and Systems. I: Fundamental Theory and Applications. Vol. 40, No. 3. March 1993. pp. 147–156.MATHCrossRefMathSciNetGoogle Scholar
  7. [7]
    E. B. Kosmatopoulos, M. M. Polycarpou, M. A. Christodoulou, P. A. loannou. “High-Order Neural Network Structures for Identification of Dynamical Systems”. IEEE Transactions on Neural Networks, Vol. 6, No. 2, pp. 422–431.Google Scholar
  8. [8]
    F. J. López Aligué, M. I. Acevedo Sotoca, M. A. Jaramillo Morán. “A High Order Neural Model”. Lecture Notes in Computer Science, No. 686, “New Trends Neural Computation”. pp. 108–113, Springer-Verlag, Berlin. June 1993.Google Scholar
  9. [9]
    R. Dogaru, K. R. Crounse, L. O. Chua. “An Extended Class of Synaptic Operators with Applications for Efficient VLSI Implementation of Cellular Neural Networks”. IEEE Transactions on Circuits and Systems, Vol. 45, No. 7, July 1998, pp. 745–755.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1999

Authors and Affiliations

  • M. A. Jaramillo Morán
    • 1
  • J. A. Fernández Muñoz
    • 1
  1. 1.Dpto. Electrónica e Ingeniería Electromecánica. Escuela de Ingenierías IndustrialesUniversidad de ExtremaduraBadajozSpain

Personalised recommendations