Image denoising method based on improved bilateral filtering

Abstract

The invention relates to an image denoising method based on improved bilateral filtering. The method comprises the steps of estimating a gray value of a neighborhood center pixel by performing a norbert wiener function on an input noise image, then calculating a brightness similarity weight value through a GM function, calculating a space proximity weight value through a Gaussian weight value, and multiplying the two obtained weight values to perform denoising. Compared with the prior art, the image denoising method disclosed by the invention has the advantages that the quality of a denoised image can be improved, edge texture information is protected, target and background information are accurately expressed, and an ideal denoising effect is achieved.

Description

technical field

[0001] The invention relates to an image denoising method, in particular to an image denoising method based on improved bilateral filtering. Background technique

[0002] In the process of acquisition, transmission and processing, the quality of images is usually reduced due to noise interference, which seriously affects the performance of subsequent image processing such as image feature extraction, image recognition and image retrieval. Therefore, image denoising, as a basic technique of image processing, has always been the focus of people's attention. Classic image denoising algorithms include: Gaussian filter, median filter, wavelet transform, Wiener filter and so on. Among them, the Gaussian filter does not distinguish between edges and details due to its isotropy, so this method is easy to cause image edges and details to be blurred; although median filtering can effectively maintain the edge information of the image, it does not affect the details an...

Images