Title :
Image restoration using parametric adaptive fuzzy filter
Author :
Wang, Jung-Hua ; Da Lin, Lian
Author_Institution :
Dept. of Electr. Eng., Nat. Taiwan Ocean Univ., Keelung, Taiwan
Abstract :
The authors apply a parametric adaptive fuzzy filter (PAFF) to the restoration of noisy blurred images. Input histogram statistics are used to estimate parameters of the near-optimal fuzzy membership functions. PAFF is shown to be effective in removing highly impulsive noise while preserving edge sharpness. PAFF shows superior performance over conventional methods especially when the noise rate ⩾20%
Keywords :
adaptive signal processing; filtering theory; fuzzy set theory; image restoration; neural nets; noise; parameter estimation; statistical analysis; edge sharpness; highly impulsive noise removal; input histogram statistics; near-optimal fuzzy membership functions; noisy blurred image restoration; parameter estimation; parametric adaptive fuzzy filter; Adaptive filters; Adaptive systems; Filtering; Fuzzy sets; Histograms; Image restoration; Neural networks; Nonlinear filters; Oceans; Pixel;
Conference_Titel :
Fuzzy Information Processing Society - NAFIPS, 1998 Conference of the North American
Conference_Location :
Pensacola Beach, FL
Print_ISBN :
0-7803-4453-7
DOI :
10.1109/NAFIPS.1998.715564