Abstract
In this paper, the problem of color image restoration using a neural network learning approach is addressed. Instead of explicitly specifying the local regularization parameter values, we modify the neural network weights, which are considered as the regularization parameters. These are modified through the supply of appropriate training examples. The desired response of the network is in the form of estimated value for the current pixel. This estimate is used to modify the network weights such that the restored value produced by the network for a pixel is closer to this desired response. In this way, once the neural network is trained, images can be restored without having prior information about the model of noise/blurring with which the image is corrupted.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Banham, M.R., Katsaggelos, A.K.: Digital Image Restoration. IEEE Sig. Proc. Mag. 1053(5888), 24–41 (1997)
Andrews, H.C.M., Hunt, B.R.: Digital Image Restoration. Prentice Hall, NJ (1977)
Jain, A.K.: Fundamentals of digital Image Processing, PHI, New Delhi (2001)
Kang, M.G., Katsaggelos, A.K.: Simultaneous Iterative Image Restoration and Evaluation of the Regularization Parameter. IEEE Trans. Sig. Proc. 40, 2329–2334 (1992)
Miller, K.: Least Squares Methods for Ill-Posed Problems with a Prescribed Bound. J. Math. Anal. 1, 52–74 (1970)
Wong, H.S., Chan, L.: A neural learning approach for adaptive image restoration using a fuzzy model based network architecture. IEEE Trans. Neu. Net. 12(3), 516–531 (2001)
Zhou, Y.T., Chellappa, R., Vaid, A., Jenkins, B.K.: Image restoration using a neural network. IEEE Trans. Acoust. Sp. Sig. Proc. 36(7), 1141–1151 (1988)
Perry, S., Guan, L.: Weight assignment for adaptive image restoration by neural networks. IEEE Trans. Neu. Net. 11, 156–170 (2000)
Anand, R., Mehrotra, K., Mohan, C.K., Ranka, S.: Efficient classification for multiclass problems using modular neural networks. IEEE Trans. Neu. Net. 6, 117–124 (1995)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Chickerur, S., Aswatha Kumar, M. (2010). A Neural Network Based Solution to Color Image Restoration Problem. In: Das, V.V., Vijaykumar, R. (eds) Information and Communication Technologies. ICT 2010. Communications in Computer and Information Science, vol 101. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-15766-0_117
Download citation
DOI: https://doi.org/10.1007/978-3-642-15766-0_117
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-15765-3
Online ISBN: 978-3-642-15766-0
eBook Packages: Computer ScienceComputer Science (R0)