关键词: Shearlet变换, 去噪, 峰值信噪比, 图像处理, 多尺度几何分析

Abstract: According to the deficiency of de-noising algorithm based on the traditional transform domain, this paper proposed an image de-noising algorithm based on Shearlet transform. Firstly, a Shearlet decomposition and reconstruction implementation method was proposed in this paper. And then, the Monte-Carlo method was used to do estimation of the high-frequency coefficients. Finally the shrinkage de-noising would be done according to the threshold function. The experimental results demonstrate that the method can remove noise and remain edges, and obtain better visual effect and higher PSNR.

Key words: shearlet transform, de-noising, psnr, image processing, multi-scale geometric analysis