IDENTIFICATION TYPE OF NOISE IN GRAY SCALE IMAGES USING WAVELET-NETWORK (WN)

Main Article Content

W. A. Mahmoud
H. H. Khalil

Abstract

In this paper, Wavelet-Network (WN) model has been recently proposed and applied to image processing, e.g., identification type of noise in Gray-Scale Images (GSI). This paper develops a new technique, which employs a Discrete Wavelet Transform (DWT) and an Artificial Neural Network (ANN). This WN technique uses special mother wavelet y(xl,x2) of (DWT) as activation function for (ANN) instead of the traditional activation functions like (Log sigmoid, Tan sigmoid, etc). It is shown here that the benefit of WN circuits which uses WN is a good approximation tool for GSI images. These approximation patterns for images forced ANN to learn on these images which will be used in the test phase after that.

Article Details

How to Cite
“IDENTIFICATION TYPE OF NOISE IN GRAY SCALE IMAGES USING WAVELET-NETWORK (WN)” (2005) Journal of Engineering, 11(01), pp. 203–211. doi:10.31026/j.eng.2005.01.18.
Section
Articles

How to Cite

“IDENTIFICATION TYPE OF NOISE IN GRAY SCALE IMAGES USING WAVELET-NETWORK (WN)” (2005) Journal of Engineering, 11(01), pp. 203–211. doi:10.31026/j.eng.2005.01.18.

Publication Dates

References

T. Poggio and F. Oirosi, (1990), Networks for Approximationd and Learning, Proc. JEEE, vol. 78, no. Sept.

K. Homik, (1989), Multilayer feedforward networks are universal Approximatora, Neural Networks, vol, 2,

Scoit E. Umbaugh. (1998), Computer Vision and Image Processing, A Practicál Approach using UVIP Tools. Prentice Hall, Inc., Upper Saddle River, NJ 07458 (USA).

Nonlinear Noise Reduction, Course Project to Electrical Eag., University of Stanford, from Intemet thup:/www. stanford.edu), 2000. 206 Number Volume 11 March 2005 Journal of Englneering

C. Cyhenko. (1989). Approxination by Superposition's of a Sigmoidal Function, Mahematics of control. signals and systems, 2 303-314

K. Hamik. M. Stincheombe, H. White and P. Auer, (1994), Degree of Approximation Results for Feedforward Networks Approximating Unknown Mappings and Their Derivatives, Neural Computation. 6 (6) 1262-1275

M. I. Jordan, (1985), The Leaming of Representations for Soquemial Performance, Doctoral Disseration, University of Califomia, San Diego,.

Nerrand. P. Roussel Ragot, D. Urbani, L. Personnaz, G. Dreyfus, (1994), Training recurrent neural nelworks: why and how? An Ilustration in Process Modeling, IEEE Trans. an Neural

Netwurks 5 (2) 178-184 Y. C. Pali and P. S. Krishnaparasad, (1993), Analysis and Syothesis of Feedforward Neural Networks Using Discrete Affine Wavelet Trunsformations, lEEE Trans. on Neural Networks 4(1) 71-85

L Daubachies, (1991), The Wavelet Transform. Time-Frequency Localization and Signal Analysis IEFT Truns. Informat. Theory, vol. 36, Sept.

S. G. Mallat, (1989), A Theory for Multiresolution Signal Decomposition: The Wavelet Represenation, IEEE Trans. I AMI, vol. 11, no. 7, July.

S. G. Mallat. (1989). Multiresolution Approxination and Wavelets Orthonormal Basis of LR) Trans, Amer. Math Soc., 315, no. 1. 69-88

P. Byrascano and P. Lucci, (1990), A Learning Rule Eliminating Local Minima in Multilayer Perceptrons, Proc, ICASSP 90, Albuquerque, Apr. 3-6,

R. Hecht-Nielsen. (1989). Back Propagation Error Surfaces can have Local Minima, IEEE-INNS Int joint conterence on neural networks, Washington D.C., June

A Benveniste. M Metivier and P. Priouret, (1990), Adaptive Algorithms and Stochastic Approximations. Applications of Mathemalics, vol. 22, Springer Veriag