Bilateral regression filter method for grayscale and colored images

Abstract

The invention relates to a bilateral regression filter method for grayscale and colored images. As an effective information carrier, images can be used as an important manner for obtaining and exchanging effective information by users; but the images systematically import certain noises due to various interference factors in the forming, transmission and reception processes, some detail features are hidden in the noises, and great difficulties are brought to the image processing processes such as image observation as well as feature information extraction and analysis, so that adopting a proper method to remove pollution noises in the images is a very important pre-processing step. The bilateral regression filter method provided by the invention can be used for the filtering of grayscale and colored images.

Description

Technical field: [0001] The invention relates to a filtering method applicable to grayscale and color images, which is named bilateral regression filtering. Background technique: [0002] As an effective information carrier, images are an important way for people to obtain and communicate effective information. However, in the process of image formation, transmission, and reception, certain noises will be systematically introduced due to the existence of various interference factors, and some detailed features are often submerged in the noise. posed great difficulties. It is a very important preprocessing step to adopt an appropriate method to remove the pollution noise in the image. [0003] Common filtering methods will blur the edge of the image contour while removing noise, such as Butterworth filter and Gaussian filter. The edge of the image contour contains important information of the image, so an important issue in image filtering is to maintain the edge of the im...

AI Technical Summary

Problems solved by technology

When applied to an image containing salt and pepper noise, since the gray value of the noise point is significantly different from that of adjacent points, the local weighted average of the bilateral filter will fail, so the bilateral filter cannot remove the salt and pepper noise.

Durand and Dorsey proposed to combine bilateral filtering and median filtering to filter salt and pepper noise [5] , but the median filter will lose the details of the image

In addition, in order to achieve a good filtering effect, the bilateral filter should set the standard deviation of the range Gaussian kernel function according to the noise level of the image. When the image noise variance is large, increasing the standard deviation of the range Gaussian kernel function can enhance denoising effect, but this will lead to blurring of the edge of the image; if the standard deviation of the Gaussian kernel function is not increased, the edge of the image can be maintained, but the denoising effect will be reduced

Therefore, when the noise variance is large, the denoising effect of the bilateral filter needs to be strengthened.

Images