Image filtering method and device

Abstract

The invention discloses an image filtering method and device, which relates to the field of computers and can solve the problem that the bilateral filtering method in the prior art cannot achieve the expected filtering effect. The method includes: dividing the target image into at least two image areas; calculating the spatial distance coefficient and pixel difference coefficient of each image area in the at least two image areas; and for any pixel in the target image, according to the location of the pixel The spatial distance coefficient and pixel difference coefficient of the image area perform bilateral filtering on the pixels. The present invention is suitable for scenes where images are filtered.

Description

technical field [0001] The invention relates to the field of computers, in particular to an image filtering method and device. Background technique [0002] When the user takes a photo, often due to reasons such as the shooting environment and the pollution of the camera lens, the photo taken contains noise. Therefore, users often need to use image processing technology to correct the photographs taken. In image processing technology, bilateral filtering is widely used because of its edge preservation effect. The edge feature of the bilaterally filtered image is obvious, and the image quality is high. [0003] However, bilateral filtering is essentially a filtering process of weighted average of neighborhood pixel values, which will inevitably blur image features. For example, although low-scale bilateral filtering can properly preserve the edge features of the image, its denoising effect is poor; although high-scale bilateral filtering has a good denoising effect, it wil...

AI Technical Summary

Problems solved by technology

[0005] However, the first type of bilateral filtering has the following defects: due to the different edge features and noise conditions in different regions of the image to be processed, using fixed filter coefficients in different regions of the image to be processed often makes the filtering effect less than expected ; The second bilateral filtering process has the following defects: the filter coefficient for each pixel in the image to be processed is easily affected by the noise of the image to be processed, so the edge features of the image to be processed are excessively blurred, or the image to be processed The noise of the image is not filtered cleanly, resulting in the filtering effect not reaching the expected effect

Images