Call for Paper - January 2023 Edition
IJCA solicits original research papers for the January 2023 Edition. Last date of manuscript submission is December 20, 2022. Read More

Image Restoration using a Network of Reduced and Regularized Neural Networks

Print
PDF
International Journal of Computer Applications
© 2012 by IJCA Journal
Volume 54 - Number 8
Year of Publication: 2012
Authors:
Fillali Ferhat
Maza Sofiane
Graini Abid
10.5120/8583-2331

Fillali Ferhat, Maza Sofiane and Graini Abid. Article: Image Restoration using a Network of Reduced and Regularized Neural Networks. International Journal of Computer Applications 54(8):1-6, September 2012. Full text available. BibTeX

@article{key:article,
	author = {Fillali Ferhat and Maza Sofiane and Graini Abid},
	title = {Article: Image Restoration using a Network of Reduced and Regularized Neural Networks},
	journal = {International Journal of Computer Applications},
	year = {2012},
	volume = {54},
	number = {8},
	pages = {1-6},
	month = {September},
	note = {Full text available}
}

Abstract

The aim of this paper is to implement an optimal neural network model to resolve the problem of colour image restoration which consists of retrieving original image degraded by invariant blur and corrupted by random white additive noise. We propose in this paper an algorithm which implements a general network of reduced neural networks model and adaptive regularization. The developed model is based on the original model of zhou and the modified model of Paik and katsaggelos. The adaptive regularization parameter is used in our case when degradation model contains an additive component (additive noise) in order to obtain a compromise between image sharpness and noise elimination. It is chosen using an iterative algorithm which calculates the best value that maximizes the PSNR of the restored image. Our model presents some improvements in terms of complexity and quality of restored images. It is shown by experiments that restored images obtained by the proposed model are better in terms of both numerical measurement and visual quality.

References

  • S. Uma, Dr. S. Annadurai, 2005. "Colour Image Restoration Using Morphological Neural Network", ICGST International Journal on Graphics, Vision and Image Processing, Volume 8 53-30.
  • Ferhat Fillali, Khier Benmahammed and Graini Abid, 2010. "Image restoration using SVD and adaptive regularization" J. Automation & Systems Engineering 4-3 173-181.
  • Stuart William Perry, 1997. "Adaptive Image Restoration: Perception Based Neural Network Models and Algorithms", Ph. D. thesis in Electrical and Information Engineering, School of Electrical and Information Engineering, University of Sydney, NSW 2006.
  • Jaroslaw Szost akowski, Andrzej Stajniak, 1996. "Neural Least - Squares Image Filter with Positive Constraints". Proceding of the International Workshop on Neural Networks for Identification, Control, Robotics, and Signal / Image Processing (NICROSP'96), Venice (Italy) 222-227.
  • Zhou Y. T. , Vaid A. , Jenkins B. K. , 1988. "Image restoration using a neural network", IEEE Trans. Acoust. Speech, Signal Processing, vol. 36, 1141-1151.
  • J. K. Paik and A. K. Katsaggelos, 1992. "Image Restoration Using a Modified Hopfield Network", IEEE Trans. Image Processing, vol. 1, no. 1, 49-63.
  • Yi Sun, 2000. "Hopfield Neural Network Based Algorithms for Image Restoration and Reconstruction—Part I: Algorithms and Simulations", IEEE Transactions on Signal Processing, Vol. 48, NO. 7, 2105-2118. 1
  • R. Youmaran and A. Adler, 2004. "Combining Regularization Frameworks for Image Deblurring: Optimization of Combined Hyper-parameters". In Proceeding of Canadian Conf. Electrical and Computer Engineering, Niagara Falls, Canada, 723-726.
  • Ling Guan, "Model-based neural evaluation and iterative gradient optimization in image restoration and statistical filtering", Journal of Electronic Imaging 4(4), (1995) 407-412.
  • Ling Zhang, Yun Zhang, Yi Min Yang, 2003. "Colour image restoration with multilayer Morphological Neural network", Proceedings of the second international conference on Machine learning and Cybernetics, Xian, 2831-2834.
  • T. A. Cheema, I. M. Qureshi and A. Hussain, 2005. "Blind Image Deconvolution using a Space-variant Neural Network Approach", IEE Electronics Letters, Vol. 41, No. 6, 308-309.