NOISE-REDUCTION USING AN UNDECIMATED DISCRETE WAVELET TRANSFORM

A new nonlinear noise reduction method is presented that uses the disc rete wavelet transform, Similar to Donoho and Johnstone, we employ thr esholding in the wavelet transform domain but, following a suggestion by Coifman, we use an undecimated, shift-invariant, nonorthogonal wave let transform instead of the usual orthogonal one, This new approach c an be interpreted as a repeated application of the original Donoho and Johnstone method for different shifts, The main feature of the new al gorithm is a significantly improved noise reduction compared to the or iginal wavelet based approach, This holds for a large class of signals , both visually and in the l(2) sense, and is shown theoretically as w ell as by experimental results.