Multipatch Unbiased Distance Non-Local Adaptive Means With Wavelet Shrinkage

Many existing non-local means (NLM) methods either use Euclidean distance to measure the similarity between patches, or compute weight ω_ij only once and keep it unchanged during the subsequent denoising iterations, or use only the structure information of the denoised image to update weight ω_ij . These may lead to the limited denoising performance. To address these issues, this paper proposes the non-local adaptive means (NLAM) for image denoising. NLAM treats weight ω_ij as an optimization variable and iteratively updates its value. We then introduce three unbiased distances, namely, pixel-pixel, patch-patch, and coupled unbiased distances. These unbiased distances are more robust to measure the image pixel/patch similarity than Euclidean distance. Using the coupled unbiased distance, we propose the unbiased distance non-local adaptive means (UD-NLAM). Because UD-NLAM uses only a single patch size to compute weight ω_ij , we introduce multipatch UD-NLAM (MUD-NLAM) to adapt different noise levels. To further improve denoising performance, we then propose a new denoising method called MUD-NLAM with wavelet shrinkage (MUD-NLAM-WS). Experimental results show that the proposed NLAM, UD-NLAM, and MUD-NLAM outperform existing NLM methods, and MUD-NLAM-WS achieves a better performance than the state-of-the-art denoising methods.