A novel statistical approach to remove salt-and-pepper noise

ABSTRACT

Recently, image simulation has widely attracted people’s attentions. In this paper, we propose a novel statistical approach to remove salt-and-pepper noise. A statistic model of the number of noise pixels is built and the noise ratio of the corrupted image is estimated. To remove the noise, two steps including pixels analysis and noise removal are studied. Firstly, a statistical approach is proposed to analyse pixels to identify whether they are noise or not. Secondly, we adopt two different mean filters to remove noise with respect to corrupted images whose noise ratios are no more than 30% and above 30%, respectively. For a noiseless pixel, we keep its value unchanged. For a noisy pixel, we replace it with the mean value according to its corresponding noise ratio. Simulation results show that compared with some state-of-the-art methods, our method can effectively eliminate noise, hold more details and acquire larger values with two image quality metrics: peak signal to noise ratio and structural similarity.

KEYWORDS:

• Image simulation
• statistical approach
• salt-and-pepper noise
• peak signal to noise ratio
• structural similarity

AMS SUBJECT CLASSIFICATION:

• 68Q32

Acknowledgements

The authors would like to thank the reviewers for their valuable comments.

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Funding

This work is supported by National Science Foundation of China [grant number 61473013] and the China Open Fund of State Key Laboratory of Intelligent Manufacturing System Technology.