An efficient three-stage approach for removing salt & pepper noise from digital images

In this paper, an efficient three-stage scheme for the removal of salt & pepper noise based on an efficient impulse detector, an adaptive mean-median filter and the total variation inpainting method was proposed. This approach removes salt & pepper noise by detecting, estimating and modifying noisy pixels in an image. If a pixel is classified as noise, its intensity is first estimated by a mean-median filter; and then an accurate estimation is obtained through the use of the total variation inpainting method. Conversely, the pixel value is kept unchanged when it is classified as noise-free, yielding the quality of the restored image being well maintained. Experimental results demonstrate that the proposed three-stage approach can not only remove salt & pepper impulse noise efficiently, but also preserve the detailed information of an image well.