Removal of Salt-and-Pepper Noise from Bimodal Images Using a Non-Symmetry and Anti-Packing Model

The visual perception of a digital image is often impaired by salt-and-pepper noise introduced during the recording, restoration, and/or transmission processes. Efficient and effective removal or reduction of salt-and-pepper noise is a challenging task. In the present paper, we propose a novel de-noising method for the reduction of salt-and-pepper noise in bimodal images. Firstly, the corrupted image was divided into several square blocks using the non-symmetry and anti-packing model. Subsequently, the suspicious noise regions were extracted by analyzing the distribution of the noise with low probability. Finally, since noise-free blocks were left unchanged, a block-based median filter was introduced to estimate the corrupted block value. Experimental results show that our method is better at retaining edge details, removing salt-and-pepper noise, and depressing artifacts as compared with some state-of-the-art algorithms.