Qualified Thresholds forWavelet Shrinkage
Fritz G. Boese · PAMM · 2005
Abstract One of many method for noise reduction in measured data is the wavelet‐based Wavelet Shrinkage propagated by D. L. Donoho, I. M. Johnstone et al. since about 1990. A crucial step within this approach is the setting of the treshold which decides whether a wavelet coefficient is considered as noise or as data. We propose an one‐paramerter family of thresholds. The parameter is the probability of making a false decision. (© 2005 WILEY‐VCH Verlag GmbH & Co. KGaA, Weinheim)