Adaptive WFM filter with noise detection capability

Author

Lee, Chang-Shing ; Kuo, Yau-Hwang

Author_Institution

Inst. of Inf. Eng., Nat. Cheng Kung Univ., Tainan, Taiwan

Volume

1

fYear

1996

fDate

14-18 Oct 1996

Firstpage

602

Abstract

A new fuzzy filter for the removal of additive impulse noise, called adaptive weighted fuzzy mean (AWFM) filter, is proposed and analyzed. The AWFM is an extensive version of weighted fuzzy mean (WFM) filter and its filtered output signal is either the output of the WFM or the processed signal decided by the detection algorithm. This filter gives a better performance compared with conventional filters when evaluated by the mean absolute error (MAE), mean square error (MSE) and subjective evaluation criteria. For dedicated hardware implementation, the AWFM is also much simpler than the conventional median filter

Keywords

adaptive filters; adaptive signal detection; adaptive signal processing; filtering theory; fuzzy set theory; image processing; median filters; noise; MSE; adaptive WFM filter; adaptive weighted fuzzy mean filter; additive impulse noise removal; dedicated hardware implementation; detection algorithm; experimental results; filter performance; filtered output signal; fuzzy set theory; image processing; image transmission; mean absolute error; mean square error; median filter; noise detection; subjective evaluation; weighted fuzzy mean filter; Adaptive filters; Additive noise; Fuzzy sets; Hardware; Histograms; Information filtering; Information filters; Noise level; Pixel; Signal processing;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing, 1996., 3rd International Conference on

Conference_Location

Beijing

Print_ISBN

0-7803-2912-0

Type

conf

DOI

10.1109/ICSIGP.1996.567336

Filename

567336