Cover
Vol. 10 No. 2 (2010)

Published: September 30, 2010

Pages: 76-89

Original Article

Impulsive Noise Removal based on Neural Network Schemes

Turki Y. Abdalla 1 Abdul-Kareem Younis 2 Sarah Behnam Aziz 1
1 Computer Engineering Department, Engineering College, Basrah University
2 Computer Science Department, Science College, University of Basrah
History
  • Received: June 30, 2010
  • Available Online: September 30, 2010
DOI

https://doi.org/10.33971/bjes.10.2.7

Abstract

Interest in neural networks as an alternative to the conventional algorithmic techniques has grown rapidly in recent years. Noise removal or noise suppression is an important task in image processing. In general, the results of the noise removal have a strong influence on the quality of the following image processing techniques. In this paper, two feed forward NN schemes have been presented for impulsive noise removal. The computation is reduced by using an artificial image in training. Results of NN schemes show high performance especially when the ratio of impulsive noise in testing are the same or greater than that of training image. The presented schemes are used for grayscale and also for truecolor.

References

  1. Mitra, K. Arakawa, "A new Efficient Approach for the Removal of Impulse Noise from Highly Corrupted Images", IEEE Trans. on Image Processing, Vol. 5, No. 6, 1996, pp. 1012-1025.
  2. R. Gonzalez and R. Woods, "Digital Image Processing", 1st Edition, Addison Wesley PCI, 1992.
  3. G. Baker, "Image Noise", [Online]. Available: www.cs.nu.oz.au/-gavinb/download.php?file=noise.pdf
  4. J. Tukey, "Nonlinear (nonsuperposable) methods for smoothing data", Cong. Rec. EASCOM, pp. 673, 1974.
  5. Anderson, J. A., "An introduction to neural networks", MIT Press, 1995.
  6. Hertz, J., A. Krogh and R. G. Palmer, "Introduction to the theory of neural computation", Addison-Wesley Publ. Co., 1991.
  7. K. Hornik, M. Stinchombe, and H. White, "Multilayer Feed Forward Networks are Universal Approximators", Neural Networks, vol. 2, pp. 359-366, 1989.
  8. E. Schlünzen, "Classificação de dados multiespectrais utilizando redes neurais: a influência da amostragem no processo de treinamento", Anais do Workshop sobre Visão Cibernética, São Carlos, Agosto 1994.
  9. J. Moreira and L. Costa, "Neural-based color image segmentation and classification using self-organizing maps", GAPIS Architecture and Image & Signal Processing Research Group, 1996.
  10. D. Ridder, R. Duin, L. Vliet, and P. Verbeek, "Nonlinear image processing using artificial neural networks", Pattern Recognition Group, Dept. of Applied Physics, Delft University of Technology, Netherlands, 2003.
  11. D. Ridder, R. Duin, P. Verbeek, and L. Viiet, "The Applicability of Neural Networks to Non-linear Image Processing", Pattern Recognition Group, Applied Physics Dept., Delft University of Technology, Delft, Netherlands, 1999.
  12. A. Kokaram, "Introduction to Electrical Engineering: Digital Image and Video Processing", Dept. of Electronic and Electrical Engineering, Trinity College, Dublin University, 2004.
  13. L. Fausett, "Fundamentals of Neural Networks", 1st Edition, Prentice Hall, New Jersey, 1994.
  14. J. Hertz, A. Krogh, and R. Palmer, "Introduction to the Theory of Neural Computation", Addison-Wesley, New York, 1991.
  15. A. Minns, "Artificial Neural Network as Sub Symbolic Process Descriptors", PhD thesis, Delft University of Technology, (Holland), Abbot M. B., 1998.
  16. H. Paramahamsan, "Fundamental Properties of Synthetic O-D Generation Formulations and Solutions", M. thesis, Virginia Polytechnic Institute and State University, Blacksburg, Virginia, 1999.
  17. T. Samad, "Back-propagation improvements based on heuristic arguments", Proceedings of International Joint Conference on Neural Networks, Washington, vol. 1, pp. 565-568, 1990.
  18. V. Ooten and B. Nienhuis, "Improving the convergence of the back-propagation algorithm", Neural Networks, vol. 5, pp. 465-471, 1992.
  19. A. Minai and R. Williams, "Acceleration of Back-Propagation Through Learning Rate and Momentum Adaptation", International Joint Conference on Neural Networks, IEEE, pp. 676-679, 1990.
  20. R. Jacobs, "Increased rates of convergence through learning rate adaptation", Neural Networks, vol. 1, pp. 295-308, 1988.
  21. D. Nguyen and B. Widrow, "Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights", Proceeding of the International Joint Conference on Neural Networks, vol. 3, pp. 21-26, 1990.