We have proposed a denoising method by combining shearlet transform method and weighted Yaroslavsky’s filter (YF) for a wide class of cartoon like images with various properties such as thin features and naturalistic. The weights of the Yaroslavsky’s filter are also achieved by pixel similarities in the restored image achieved from shearlet transform method. The theoretical results are confirmed via simulations for images corrupted by additive white Gaussian noise. Experimental results illustrate that proposed approach has good effect on suppressing the pseudo-Gibbs and shearlet-like artifacts and can obtain better performance in terms of mean square error (MSE), peak signal to noise ratio (PSNR) and structural similarity (SSIM) index rather than classical shearlet transform method.

This presentation is part of Contributed Presentation “CP6 - Contributed session 6”

Authors:

Reza Abazari (University of Tabriz)

Mehrdad Lakestani (University of Tabriz)

Keywords:

image denoising, image reconstruction, image representation, inverse problems, shearlet transform, yaroslavsky’s filter.