Estimation and Removal of Gaussian Noise in Digital Images
Saraswatula Venkata Suryanarayana, B. L. Deekshatulu, K. Lal Kishore, Rakesh Kumar Y · Zenodo (CERN European Organization for Nuclear Research) · 2023
In this paper a novel algorithm for Gaussian noise estimation and removal is proposed by using 3x3 sub windows in which the test pixel appears. The standard deviation(STD) for all sub-windows are used to define reference STD(σref )and minimum(σmin) and maximum (σmax ) standard deviations. The average STD (σavg ) is then calculated as the average of those STDs of all sub-windows whose STD falls with in the range of [σmin, σmax]. This σavg is used for detecting and removing additive Gaussian noise. The performance is compared with that of the standard mean filter. The proposed scheme is outperforming than the standard mean filter.