A Practical Approach To Image Reconstruction From Projections Using Neural Networks Structure

  • Robert Cierniak
Conference paper
Part of the Advances in Soft Computing book series (AINSC, volume 19)


This paper presents a practical approach to the key problem in the computer tomography: image reconstruction from projections, using neural network. The two layer structure of the neural network is used, realizing the maximization of the energy, defined as difference between signal energy and its entropy. Some interesting results of the performed simulations are shown.


Neural Network Image Reconstruction Soft Computing Signal Reconstruction Neural Network Structure 
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]
    Cormack A. M., Representation of a function by its line integrals with some radiological application, J. Appl. Phys., vol. 34, pp. 2722–2727, 1963.MATHCrossRefGoogle Scholar
  2. [2]
    Frieden B. R., Zoltani C. R., Maximum bounded entropy: application to tomographic reconstruction, Appl. Optics, vol. 24, pp. 201–207, 1985.Google Scholar
  3. [3]
    Ingman D., Merlis Y., Maximum entropy signal reconstruction with neural networks, IEEE Trans. on Neural Networks, vol. 3, pp. 195–201, 1992.CrossRefGoogle Scholar
  4. [4]
    Jain A. K., Fundamentals of Digital Image Processing, Prentice Hall, New Jersey, 1989.MATHGoogle Scholar
  5. [5]
    Kaczmarz S., Angeneaherte Aufloesung von Systemen Linearer Gleichungen, Bull. Acad. Polon. Sci. Lett. A., vol. 35, pp. 355–357, 1937.Google Scholar
  6. [6]
    Luo Fa-Long, Unbehauen R., Applied Neural Networks for Signal Processing, Cabridge University Press, 1998.Google Scholar
  7. [7]
    Radon J., Ueber die Bestimmung von Functionen durch ihre Integralwerte Tangs gewisser Mannigfaltigkeiten, Berichte Saechsiche Akad. Wissenschaften, Math. Phys. Klass, vol. 69, pp. 262–277, Leipzig, 1917.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Robert Cierniak
    • 1
  1. 1.Technical University of CzęstochowaCzęstochowaPoland

Personalised recommendations