ASSIGNING AUTOMATIC REGULARIZATION PARAMETERS IN IMAGE RESTORATION

Ignazio Gallo, Elisabetta Binaghi

2009

Abstract

This work aims to define and experimentally evaluate an adaptive strategy based on neural learning to select an appropriate regularization parameter within a regularized restoration process. The appropriate setting of the regularization parameter within the restoration process is a difficult task attempting to achieve an optimal balance between removing edge ringing effects and suppressing additive noise. In this context,in an attempt to overcome the limitations of trial and error and curve fitting procedures we propose the construction of the regularization parameter function through a training concept using a Multilayer Perceptron neural network. The proposed solution is conceived independent from a specific restoration algorithm and can be included within a general local restoration procedure. The proposed algorithm was experimentally evaluated and compared using test images with different levels of degradation. Results obtained proven the generalization capability of the method that can be applied successfully on heterogeneous images never seen during training.

References

  1. Andrews, H. C. and Hunt, B. R. (1977). Restoration. Prentice-Hall, New Jersey.
  2. Banhom, M. R. and k. Katsaggelos, A. (1997). Digital image restoration. IEEE Signal Processing Mag.
  3. Gallo, I., Binaghi, E., and Macchi, A. (2007). Adaptive image restoration using a local neural approach. In 2nd International Conference on Computer Vision Theory and Applications.
  4. Gallo, I., Binaghi, E., and Raspanti, M. (2008). Semi-blind image restoration using a local neural approach. In Signal Processing, Pattern Recognition, and Applications, pages 227-231.
  5. Inoue, K., Iiguni, Y., and Maeda, H. (2003). Image restoration using the rbf network with variable regularization parameters. Neurocomputing, 50:177-191.
  6. Katsaggelos, A. K. and Kang, M. G. (1995). Spatially adaptive iterative algorithm for the restoration of astronomical images. Int. J. Imaging Syst. Technol., 6:305-313.
  7. Lagendijk, R. L. and Biemond, J. (2001). Iterative Identification and Restoration of Images. Springer-Verlag New York, Inc., Secaucus, NJ, USA.
  8. Lagendijk, R. L., Biemond, J., and Boekee, D. E. (1988). Regularized iterative image restoration with ringing reduction. Acoustics, Speech, and Signal Processing, 36(12):1874-1888.
  9. Perry, S. W. and Guan, L. (2000). Weight assignment for adaptive image restoration by neural networks. IEEE Trans. on Neural Networks, 11:156-170.
  10. Qian, W. and Clarke, L. P. (1996). Wavelet-based neural network with fuzzy-logic adaptivity for nuclear image restoration. In Proceedings of the IEEE, volume 84, pages 1458-1473.
  11. Rumelhart, H., Hinton, G. E., and Williams, R. J. (1986). Learning internal representation by error propagation. Parallel Distributed Processing, pages 318-362.
Download


Paper Citation


in Harvard Style

Gallo I. and Binaghi E. (2009). ASSIGNING AUTOMATIC REGULARIZATION PARAMETERS IN IMAGE RESTORATION . In Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2009) ISBN 978-989-8111-69-2, pages 74-77. DOI: 10.5220/0001785500740077


in Bibtex Style

@conference{visapp09,
author={Ignazio Gallo and Elisabetta Binaghi},
title={ASSIGNING AUTOMATIC REGULARIZATION PARAMETERS IN IMAGE RESTORATION},
booktitle={Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2009)},
year={2009},
pages={74-77},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001785500740077},
isbn={978-989-8111-69-2},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2009)
TI - ASSIGNING AUTOMATIC REGULARIZATION PARAMETERS IN IMAGE RESTORATION
SN - 978-989-8111-69-2
AU - Gallo I.
AU - Binaghi E.
PY - 2009
SP - 74
EP - 77
DO - 10.5220/0001785500740077