Noise processing method and system based on image smoothing

Abstract

The invention relates to the technical field of image processing, in particular to a noise processing method and system based on image smoothing. The method comprises the following steps: acquiring a noise image, graying the noise image to obtain a grayscale image, and performing edge detection on the grayscale image to obtain a grayscale edge image; the grayscale image is segmented into a plurality of areas, the variance of pixel values in each area is obtained, the area with the variance larger than or equal to the preset area variance is filtered to obtain a filtered image, and the value range of the preset area variance is determined by the overall variance of a grayscale filtered image obtained after the grayscale image is filtered; and continuously adjusting the variance of the preset region to obtain a plurality of filtered images, and screening out an adaptive filtered image from the plurality of filtered images. The purposes of performing partition filtering on the grayscale image, selecting the proper preset region variance to eliminate the noise points in the region and reserving the normal points in the normal region are achieved.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a noise processing method and system based on image smoothing. Background technique [0002] Today's society is an era of informationization. The form of information is no longer pure voice, but has developed into multimedia forms including data, text, images and videos. Image processing technology plays an increasingly important role in all aspects of human production and life. For example, people download or browse multimedia information such as images and videos on the Internet. However, digital images are often affected by imaging equipment and external environmental noise in the process of digitization and transmission. Effects such as interference are called noisy images or noisy images. [0003] At present, the commonly used method to deal with image noise is to perform adaptive filtering on images. However, when adaptive filtering is currently performed ...

AI Technical Summary

Problems solved by technology

[0003] At present, the commonly used method to deal with image noise is to perform adaptive filtering on the image, but it is difficult to accurately judge the value of the adaptive threshold when performing adaptive filtering on the image, and the selection of the adaptive threshold is cumbersome. When the value of the adaptive threshold is inaccurate, normal points will be removed as noise points or a large number of noise points will not be removed, making it difficult to retain a complete normal image

Images