Neural implementation of ARMA type filters for image restoration

Author

Stajniak, Andrzej ; Szostakowski, Jarostaw

Author_Institution

Inst. of Control & Ind. Electron., Warsaw Univ. of Technol., Poland

Volume

2

fYear

1995

fDate

23-26 Oct 1995

Firstpage

520

Abstract

We present a novel neural implementation of the autoregressive moving average (ARMA) type filters for image deblurring. Our filter is designed on the basis of a known blur system. As the neural net, we used a multilayer perceptron. Due to connection of the parallel processing and nonlinear characteristics in the neural networks, we hoped to reduced the influence of noise and roundoff errors. We present the construction of different learning patterns for this net. Some practical examples are shown

Keywords

IIR filters; autoregressive moving average processes; backpropagation; filtering theory; image restoration; multilayer perceptrons; noise; parallel processing; roundoff errors; ARMA type filters; IIR filter; autoregressive moving average; backpropagation; blur system; image deblurring; image restoration; learning patterns; multilayer perceptron; neural implementation; neural net; neural networks; noise; nonlinear characteristics; parallel processing; roundoff errors; Degradation; Filtering; IIR filters; Image restoration; Industrial electronics; Multi-layer neural network; Multilayer perceptrons; Neural networks; Parallel processing; Pixel;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing, 1995. Proceedings., International Conference on

Conference_Location

Washington, DC

Print_ISBN

0-8186-7310-9

Type

conf

DOI

10.1109/ICIP.1995.537530

Filename

537530