Advertisement

Motion Blur Identification in Noisy Images Using Feed-Forward Back Propagation Neural Network

  • Mohsen Ebrahimi Moghaddam
  • Mansour Jamzad
  • Hamid Reza Mahini
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4153)

Abstract

Blur identification is one important part of image restoration process. Linear motion blur is one of the most common degradation functions that corrupts images. Since 1976, many researchers tried to estimate motion blur parameters and this problem is solved in noise free images but in noisy images improvement can be done when image SNR is low. In this paper we have proposed a method to estimate motion blur parameters such as direction and length using Radon transform and Feed-Forward back propagation neural network for noisy images. To design the desired neural network, we used Weierstrass approximation theorem and Steifel reference Sets. The experimental results showed algorithm precision when SNR is low and they were very satisfactory.

Keywords

Linear Motion blur Restoration Neural network noisy images 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Moghaddam, M.E., Jamzad, M.: Blur identification in noisy images using radon transform and power spectrum modeling. In: IEEE 12th International workshop on systems,signal and image processing(IWSSIP), Greece, Chalkida (2005)Google Scholar
  2. 2.
    Li, Q., Yoshida, Y.: Parameter Estimation and Restoration for motion blurred Images. IEICE Trans. Fundamentals E80-A(8) (August 1997)Google Scholar
  3. 3.
    Chang, M.M., Tekalp, A.M., Erdem, A.T.: Blur identification using the bispectrum. IEEE Trans. Acoust., Speech, Signal Processing 39 (October 1991)Google Scholar
  4. 4.
    Cannon, M.: Blind deconvolution of spatially invariant image blurs with phase. IEEE Trans. Acoust., Speech, Signal Processing 24, 58–63 (1976)CrossRefGoogle Scholar
  5. 5.
    Rekleities, I.M.: Optical Flow recognition from the power spectrum of a single blurred image. In: ICIP (1996)Google Scholar
  6. 6.
    Mayntz, C., Aach, T., Kunz, D.: Blur Identification using a spectral Inertial Tensor and Spectral zeros. In: ICIP (1999)Google Scholar
  7. 7.
    He, W.-G., Shao-Fali, Hu, F.-W.: Blur identification using adaptive adaline network. In: IEEE international conference on machine learning and cybernetics, Guangzhou, August 18-21 (2005)Google Scholar
  8. 8.
    Cho, C.-M., Don, H.-S.: Blur identification and image restoration using a multilayer neural network. In: IEEE international joint conference on Neural Networks (1991)Google Scholar
  9. 9.
    Yap, K.-H., Guan, L.: A recursive approach to joint image restoration and compensated blur identification. In: IEEE international society workshop on neural netwoks for signal processing, pp. 11–13 (December 2000)Google Scholar
  10. 10.
    Todd, J.: Introduction to the constructive theory of functions. California Institute of Technology (1961)Google Scholar
  11. 11.
    Powell, M.J.D.: Approximation Theory and Methods. Cambridge University Press, Cambridge (1981)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Mohsen Ebrahimi Moghaddam
    • 1
  • Mansour Jamzad
    • 1
  • Hamid Reza Mahini
    • 2
  1. 1.Department of Computer Engineering Sharif University of TechnologyTehranIran
  2. 2.IUST Behshahr BranchBehshahrIran

Personalised recommendations