A New Non-local Mean Method for the Image Denoising of Coal Dust

Abstract

In the process of coal dust image collecting and transmitting, it is inevitable that it will be interfered by noise. The denoising effect of image is crucial for the segmentation and recognition of image behind. The denoising effect of image is better based on the non-local mean denoising algorithm. However, the exponential weighted kernel function is used in the traditional non-local mean filtering algorithm, which tends to cause the image details to be blurred due to excessive smoothing. Therefore, according to the exponential weighted kernel function, a new non-local mean image denoising algorithm is designed by using the Gaussian kernel function of weighted of cosine coefficient, and applied to the weighting coefficient calculation. The experimental results show that the denoising performance of the algorithm is better than the traditional algorithm and can better preserve the details of coal dust image.