Blind Additive Gaussian White Noise Level Estimation using Chi-square Distribution

Abstract

It is important for image denoising methods with accurate noise level on real-world noisy images. Traditional noise level estimation methods either overestimate or underestimate the noise level. The former will make denoising methods smooth rich structures while the latter will make them reduce noise incompletely. To accurately estimate AGWN level, this paper proposes a novel blind additive Gaussian white noise level estimation method using Chi-square distribution, including the following key points: First, we select an initial flat patch set from the base image, which is decomposed from the noisy image by the relative total variation. And the initial noise level is estimated by mapping the patch set to the original noisy image. Then, we get the detail images by the usage of the directional gradient operations on the noisy image. Next, the initial flat patches are refined by a patch selection method with initial noise level and Chi-square distribution on the detail images. Finally, an iterative criterion is reemployed to generate a stable noise level. Experimental results validate that the proposed noise level estimation method is effective and is even superior to the state-of-the-arts.