Adaptive denoising based on lifting scheme
Yonghong Wu, Quan Pan, Hongcai Zhang, Shaowu Zhang · 2005
Observing that the Haar wavelet is sensitive to step edges, and the CDF(2.2) wavelet which is a subset of the Cohen-Daubechies-Feauveau family performs well for smooth signals, we present a new adaptive wavelet transform via the lifting scheme for noise reduction. Unlike many popular wavelet that adapt scale-by-scale, the proposed wavelet can adapt point-by-point. Experiment results show that the proposed method has advantages of both the Haar and CDF(2,2) wavelets and performs well for the smooth and edge-dominated regions. Moreover, the interval of the switch thresholding parameter of the proposed wavelet is given by experiments.