Image denoising by arithmetic means based on similarity

In this paper, we propose a Non-Local Means algorithm-based denoising method. In conventional NLM, the weighting functions are acquired based on the similarity between target patch and its neighboring patches and then Gaussian-range kernel is calculated based on the similarity. Then, target patch is replaced by weighted means value of neighboring patches. In comparison, our method extracts similar patches by thresholding and only calculates simple arithmetic average. The method does not only outperform the conventional NLM but also implement with less computation. Finally, we compare the proposed and the conventional NLM, and validate the advantage.