Adaptive image noise level estimation with Chi-square distribution on the flat patches selected by improved PCANet and ResNet101

Additive Gaussian white noise present in images adversely affects their quality, impeding effective human visualization. Current denoising approaches commonly rely on manual setting of the noise level, leading to insufficient noise removal or excessive smoothing. Traditional noise level estimation methods are not adaptive and their generalization ability is limited. To address this issue, this paper developed an adaptive image noise level estimation with Chi-square distribution on the flat patches selected by improved PCANet and ResNet101, including two key procedures: flat image patches selection and noise level estimation. The former was achieved using the improved PCANet and ResNet101 methods while the latter was completed by applying Chi-square distribution to the selected flat patches. Experimental results demonstrated that the reported method achieved high accuracy and powerful generalization ability, making it more suitable for extensive applications compared to existing methods.