A new image denoising method based on the dependency wavelet coefficients
Erhu Zhang, Shuying Huang · 2005
The denoising of a natural image corrupted by noise is a classical problem in signal processing. A new method for image denoising is discussed. The bivariate shrinkage function based on the dependency between wavelet coefficients is derived from Bayesian maximum a posterior (MAP) estimation theory and applied to image denoising. The performance of the method is compared with that of the conventional soft thresholding technique. Experimental results show the method is satisfying in noise suppression, preserving edges and details.