Binary image restoration using neural network models

We apply the mean field theory (MFT) neural network approach to the problem of binary image restoration. The MFT works extremely fast by using a deterministic equation in place of the stochastic relaxation characterized by the simulated annealing strategy. Some experimental results are recorded.<<ETX>>

[1]  Richard P. Lippmann,et al.  An introduction to computing with neural nets , 1987 .

[2]  Xinhua Zhuang,et al.  Robust segmentation of noisy images using a neural network model , 1992, Image Vis. Comput..

[3]  Jun Zhang.  The mean field theory in EM procedures for Markov random fields , 1992, IEEE Trans. Signal Process..

[4]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  B. K. Jenkins,et al.  Image restoration using a neural network , 1988, IEEE Trans. Acoust. Speech Signal Process..

[6]  Behrooz Kamgar-Parsi,et al.  Simultaneous fitting of several planes to point sets using neural networks , 1990, Comput. Vis. Graph. Image Process..

[7]  Paolo Carnevali,et al.  Image Processing by Simulated Annealing , 1985, IBM J. Res. Dev..

[8]  Anna Tonazzini,et al.  Neural network use in maximum entropy image restoration , 1990, Image Vis. Comput..

[9]  Xinhua Zhuang,et al.  Robust and Adaptive Segmentation of Noisy Images Using Gibbs Random Field Models , 1992, Int. J. Pattern Recognit. Artif. Intell..

[10]  Federico Girosi,et al.  Parallel and Deterministic Algorithms from MRFs: Surface Reconstruction , 1991, IEEE Trans. Pattern Anal. Mach. Intell..