Image denoising: a nonlinear robust statistical approach
A. Ben Hamza, Hamid Krim · IEEE Transactions on Signal Processing · 2001
Nonlinear filtering techniques based on the theory of robust estimation are introduced. Some deterministic and asymptotic properties are derived. The proposed denoising methods are optimal over the Huber /spl epsi/-contaminated normal neighborhood and are highly resistant to outliers. Experimental results showing a much improved performance of the proposed filters in the presence of Gaussian and heavy-tailed noise are analyzed and illustrated.