A novel image denoising algorithm for suppressing mixture of speckle and impulse noise in spatial domain

Abstract

This paper proposes a novel image denoising algorithm in spatial domain for filtering mixture of speckle and impulse noise using combination of local statistics and non-linear Robust Estimator. Proper choice of despeckling filter is an important requirement for contrast enhancement. On the other hand suppression of impulse noise aids the enhancement and preservation of edges. The proposed algorithm improves the local statistics approach for despeckling followed by application of Robust Estimator for efficient filtering of high density impulse noise. Peak Signal to Noise Ratio (PSNR) and Coefficient of Correlation (COC) are used as quality metrics for evaluating the performance of the proposed algorithm. Simulation results portray significant improvement in the restored image obtained after suppression of the noise mixture (speckle + impulse) along with preservation of local features in comparison to other algorithms.