Adaptive image denoising method based on non-local means filtering

This paper proposes an adaptive image denosing method. Conventional non-local means(NLM) method is not able to adaptively choose filter parameter. According to the characteristic value of different image patch, we build a prediction function, which is used to choose a suitable NLM parameter for the image, thus realize the adaptive non-local means filtering. Experimental results illustrate that the proposed method is superior to the traditional non-local means in both peak signal-to-noise ratio and subjective denoising quality for images.