Wavelet-Based Denoising With Nearly Arbitrarily Shaped Windows

The estimation of the signal variance in a noisy environment is a critical issue in denoising. The signal variance is simply but effectively obtained by the locally adaptive window-based maximum likelihood or the maximum a posteriori estimate. The size of the locally adaptive window is also an important factor in estimating the signal variance. In this letter, we propose a novel algorithm for determining the variable size of the locally adaptive window using a region-based approach. A region including a denoising point is partitioned into disjoint subregions. The locally adaptive window for denoising is obtained by selecting the proper subregions. In our method, a nearly arbitrarily shaped window is achieved for image denoising. The experimental results show that our method outperforms other critically sampled wavelet denoising schemes.