Yamanappa, W.Sudeep, P.V.Sabu, M.K.Rajan, J.2026-02-052018IEEE Access, 2018, 6, , pp. 66914-66922https://doi.org/10.1109/ACCESS.2018.2869461https://idr.nitk.ac.in/handle/123456789/25326Most of the real-time image acquisitions produce noisy measurements of the unknown true images. Image denoising is the post-acquisition technique to improve the signal-to-noise ratio of the acquired images. Denoising is an essential pre-processing step for different image processing applications such as image segmentation, feature extraction, registration, and other quantitative measurements. Among different denoising methods proposed in the literature, the non-local means method is a preferred choice for images corrupted with an additive Gaussian noise. A conventional non-local means filter (CNLM) suppresses noise in a given image with minimum loss of structural information. In this paper, we propose modifications to the CNLM algorithm where the samples are selected statistically using Shapiro-Wilk test. The experiments on standard test images demonstrate the effectiveness of the proposed method. © 2013 IEEE.Electronic mailGaussian noise (electronic)Image acquisitionImage enhancementImage registrationImage segmentationMathematical transformationsNoise abatementSignal to noise ratioStandardsDe-noisingGaussiansNoiseNoise measurementsNon local meansShapiro-Wilk testsSize measurementsImage denoising