Kriging Interpolation Filter to Reduce High Density Salt and Pepper Noise

Abstract: Image denoising is a critical issue in the field of digital image processing. This paper proposes a novel Salt & Pepper noise suppression by developing a Kriging Interpolation Filter (KIF) for image denoising. Gray-level images degraded with Salt & Pepper noise have been considered. A sequential search for noise detection was made using kXk window size to determine non-noisy pixels only. The non-noisy pixels are passed into Kriging interpolation method to predict their absent neighbor pixels that were noisy pixels at the first phase. The utilization of Kriging interpolation filter proves that it is very impressive to suppress high noise density. It has been found that Kriging Interpolation filter achieves noise reduction without loss of edges and detailed information. Comparisons with existing algorithms are done using quality metrics like PSNR and MSE to assess the proposed filter.