Fuzzy filter based on neural network and its application to image restoration

Author

Shutao, Li ; Yaonan, Wang ; Changfan, Zhang ; Jianxu, Mao

Author_Institution

Inst. of Electr. & Inf. Eng., Hunan Univ., Changsha, China

Volume

2

fYear

2000

fDate

2000

Firstpage

1133

Abstract

A novel fuzzy filter based on a neural network is proposed in order to remove salt and pepper noise on images. The filter proposed here is obtained as the sum of the input signal and non-linear transform on the output of fuzzy reasoning filter, and the non-linear transform is obtained by a trained neural network. Examples of processing actual images with salt and pepper noise are shown to verify the high performance of this filter. Moreover, the influence of the training signal on the filter performance is shown to be helpful for selecting the training signal

Keywords

digital filters; fuzzy systems; image restoration; learning (artificial intelligence); neural nets; noise; transforms; filter performance; fuzzy filter; fuzzy reasoning filter; image processing; image restoration; input signal; neural network; nonlinear transform; salt and pepper noise removal; trained neural network; training signal; Cameras; Digital images; Fuzzy neural networks; Fuzzy reasoning; Gaussian noise; Image restoration; Neural networks; Noise cancellation; Nonlinear filters; Pixel;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing Proceedings, 2000. WCCC-ICSP 2000. 5th International Conference on

Conference_Location

Beijing

Print_ISBN

0-7803-5747-7

Type

conf

DOI

10.1109/ICOSP.2000.891739

Filename

891739