A comparative study of thresholding techniques for image denoising

This paper is a comparative study of four different thresholding techniques for image denoising in wavelet domain. The methods compared are Visual Shrink, Normal or Bayesian Shrink, Neighbor Shrink and Modified Neighbor Shrink. Visual and Normal Shrink are independent of window size whereas other two shrinks are dependent on window size. To benchmark against the best possible denoising technique four techniques have been compared. In this paper we have presented a more practical, implementation oriented work for the extensive theoretical and algorithmic work presented in the literature.