Image filtering based on piecewise linear models

Piecewise linear (PWL) models are very attractive for image processing due to their simplicity and effectiveness. A new filtering architecture adopting parameterized PWL functions is presented. The proposed approach takes into different account the correlation between the central pixel of a moving window and its neighbors in two subwindows. As a result, the filtering errors can be reduced and a very accurate restoration of the image data can be achieved. The sensitivity to a change of the parameter settings is also investigated

[1]  Fabrizio Russo.  A method for estimation and filtering of Gaussian noise in images , 2003, IEEE Trans. Instrum. Meas..

[2]  G. Ramponi.  Image processing with rational operators: noise smoothing and anisotropic diffusion , 2001, ISPA 2001. Proceedings of the 2nd International Symposium on Image and Signal Processing and Analysis. In conjunction with 23rd International Conference on Information Technology Interfaces (IEEE Cat..

[3]  Sanjit K. Mitra,et al.  Nonlinear image processing , 2000 .

[4]  Guillermo Sapiro,et al.  Robust anisotropic diffusion , 1998, IEEE Trans. Image Process..

[5]  Jesse S. Jin,et al.  An adaptive nonlinear diffusion algorithm for filtering medical images , 2000, IEEE Transactions on Information Technology in Biomedicine.