Transform domain denoising using nonlinear filtering and cellular neural networks

Author

Oktem, R. ; Egiazarian, K. ; Aizenberg, Igor ; Aizenberg, N.

Author_Institution

Signal Process. Lab., Tampere Univ. of Technol., Finland

Volume

2

fYear

1998

fDate

4-7 Oct 1998

Firstpage

862

Abstract

Local transform domain nonlinear image filtering is studied in this work. Nonlinear filtering works in a moving window and several filtered outputs are obtained for each pixel from different windows. A second stage filtering is applied to those filtered outputs by cellular neural network with multivalued neurons. The simulation results are presented for additive Gaussian, Laplacian, and exponentially distributed noise corrupted images

Keywords

Gaussian noise; cellular neural nets; exponential distribution; filtering theory; image processing; nonlinear filters; transforms; Laplacian noise; additive Gaussian noise; cellular neural networks; exponentially distributed noise; filtered outputs; image processing; local transform domain; moving window; multivalued neurons; noise corrupted images; nonlinear image filtering; pixel; simulation results; transform domain denoising; Adaptive filters; Additive noise; Cellular neural networks; Filtering; Image processing; Neural networks; Noise reduction; Wavelet domain; Wavelet transforms; Wiener filter;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing, 1998. ICIP 98. Proceedings. 1998 International Conference on

Conference_Location

Chicago, IL

Print_ISBN

0-8186-8821-1

Type

conf

DOI

10.1109/ICIP.1998.723693

Filename

723693