Image denoising system for protecting image details

Abstract

The invention discloses an image denoising system for protecting image details, which belongs to the technical field of image processing, and comprises a first denoising module for removing impulse noise in an image by using a multi-neighborhood median filtering algorithm; and a second denoising module which is used for removing Gaussian noise in the image by utilizing an NL-Means algorithm basedon non-local image block averaging. Compared with a traditional filtering method, details of the image can be well protected while noise is filtered; and different processing is carried out for different noises, so that the pertinence is higher, and the filtering effect is better.

Description

technical field [0001] The invention belongs to the technical field of image processing, in particular to an image denoising system for protecting image details. Background technique [0002] In today's information society, images play an increasingly important role in information dissemination, and images will inevitably be disturbed by noise during the process of acquisition, processing and dissemination. There are many sources of noise in images, and these noises come from various aspects such as image acquisition, transmission, and compression. There are also different types of noise, such as impulse noise, Gaussian noise, etc. The interference of various noise sources in the process of image acquisition and transmission degrades the image quality, which weakens the ability of human eyes or machines to detect and recognize objects in the image, and detecting details such as the edge of the image is an important way for object detection and tracking. , so in digital ima...

AI Technical Summary

Problems solved by technology

[0003] Impulse noise is particularly prominent in the noise that may appear. In order to eliminate impulse noise, many methods have been proposed. Among them, the standard median filter has a good denoising effect on impulse noise, which arranges the gray values ​​of pixels in the window from small to large. Taking the median value as the gray value of the pixel in the center of the window has the advantages of simplicity and high efficiency, but it also loses part of the image detail information while suppressing noise. The traditional median filtering method needs to perform Therefore, it will inevitably destroy the pixels that are not polluted by noise, so that the quality of the filtered image will be degraded

Gaussian noise is also a noise with a high frequency in engineering. The commonly used method is image averaging. The result of averaging N identical images will reduce the variance of Gaussian noise to one-Nth of the original. Now the effect is better. Algorithms are designed based on this idea, but it can't protect image details well and can't remove noise points well

Images