Images de-noising with Mapshrink estimate and dual-threshold in Curvelet Domain

Mapshrink algorithm is widely used in the image processing of wavelet Domain, and Curvelet transform is a new multi-scale transform theory with multi-direction. By applying Mapshrink to Curvelet Domain and analyzing single threshold de-noising method existing problem, this paper proposes a de-noising method with dual threshold, combining global threshold and local threshold, which not only retains the quality of global threshold in keeping the general gray scale of an image but also preserves the advantage in edge detail maintenance of local self-adaptive method. Based on the experimental results, this method is much more effective than de-noising method of global threshold or self-adaptive threshold in Curvelet Domain.