An Adaptive Variational PDE Based Image Restoration Model Using Hopfield Neural Network

Abstract:

An adaptive variational partial differential equation (PDE) based aproach for restoration of gray level images degraded by a known shift-invariant blur function and additive noise is presented. The restoration problem of a degraded image is solved by minimizing this model, and this minimizing problem is realized by using Hopfield neural network. In the proposed image restoration model, an adaptive regularization parameter is developed instead of the constant regularization parameter used in previous PDE model. The value of the adaptive regularization parameter changes according to different regions of the image to remove noises and preserve edge better. Several computer simulation results show that the image restoration results of the proposed model both look better and have better SNR (Signal to Noise Ratio) than the previous variational PDE based model.

• Periodical: Applied Mechanics and Materials (Volumes 48-49)
• Pages: 174-178
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.48-49.174
• Online since: February 2011
• Authors: Wei Sun, Sheng Nan Liu
• Keywords: Hopfield Neural Network, Image Restoration, Partial Differential Equation (PDE), Regularization Parameter

References

[1] Wu Yadong; Zhang Hongying; , A Novel Image Restoration Algorithm Using Neural Network Based on Variational PDE Model, Communications, Circuits and Systems Proceedings, 2006 International Conference on , vol. 1, no., pp.433-436, 25-28(2006).

DOI: 10.1109/icccas.2006.284670

[2] Yonghong Jia, Digital Image Processing, pp., Wuhan college press, Wuhan (2003).

[3] L. Pieniazek and B. Wojtowicz, A discrete dynamical system as a model of a neural network with generalized Hebbian synapses, J. Math. Anal. Appl. 308 , no. 1, 79-91, (2005).

[4] Y. T. Zhou. R. Chellappa. and B. K. Jenkins, Image restoration using a neural network, IEEE Trans. Acoust., Speech. Signal Processing. Vol. ASSP-36, pp.1140-1151, (1988).

DOI: 10.1109/29.1641

[5] Paik, J.K.; Katsaggelos, A.K., in: Image restoration using a modified Hopfield network, Image Processing, IEEE Transactions on , vol. 1, no. 1, pp.49-63, (1992).

DOI: 10.1109/83.128030

[6] Ailing Wang, Mingsheng Ye, Qiuxiang Deng, Image Processing Technology and Applications, pp., Electronic Industry Press, Beijing (2008).

[7] Perry, S.W.; Guan, L.; , Weight assignment for adaptive image restoration by neural networks , Neural Networks, IEEE Transactions on , vol. 11, no. 1, pp.156-170, (2000).

DOI: 10.1109/72.822518

[8] Katsaggelos, A.K.; Biemond, J.; Schafer, R.W.; Mersereau, R.M.; , A regularized iterative image restoration algorithm, Signal Processing, IEEE Transactions on , vol. 39, no. 4, pp.914-929, (1991).

DOI: 10.1109/78.80914

[9] Bin. Wu, Yadong. Wu, Ying. Zhang, Partial differential equations based on variational image restoration technique, Beijing college press, Beijing(2008).

[10] Gutierrez. J., Guerrero, L.G., Spatially Adaptive Regularization Image Restoration Using a Modified Hopfield Network, Electronics, Robotics and Automotive Mechanics Conference, 2007. CERMA 2007 , vol., no., pp.229-234, 25-28(2007).

DOI: 10.1109/cerma.2007.4367691