Theoretical analysis of Winsorizing smoothers and their applications to image processing

The Winsorizing smoother (W smoother), which is a center weighted median (CWM) filter giving more weight only to the central value of each window, is studied. This filter can preserve image details while suppressing additive white and/or impulsive-type noise. The statistical properties of the W smoother are analyzed. It is shown that the W smoother can outperform the median filter, while its implementation is almost as simple as median filtering. Some relationships between W smoothers and other median-type filters, such as the weighted median filter and the multi-stage median filter, are derived.<<ETX>>

[1]  Yrjö Neuvo,et al.  FIR-median hybrid filters , 1987, IEEE Trans. Acoust. Speech Signal Process..

[2]  Sung-Jea Ko,et al.  Detail Preserving Weighted Median Filters , 1988 .

[3]  C. L. Mallows,et al.  Some Theory of Nonlinear Smoothers , 1980 .

[4]  B I Justusson,et al.  Median Filtering: Statistical Properties , 1981 .

[5]  Gonzalo R. Arce,et al.  Detail-preserving ranked-order based filters for image processing , 1989, IEEE Trans. Acoust. Speech Signal Process..

[6]  D. R. K. Brownrigg,et al.  The weighted median filter , 1984, CACM.

[7]  Thomas S. Huang,et al.  A fast two-dimensional median filtering algorithm , 1979 .

[8]  Gonzalo R. Arce,et al.  Theoretical analysis of the max/Median filter , 1987, IEEE Trans. Acoust. Speech Signal Process..

[9]  Yrjö Neuvo,et al.  A New Class of Detail-Preserving Filters for Image Processing , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  M. Ahmad,et al.  A fast algorithm for two dimensional median filtering , 1987 .