Fuzzy Based Fast Non Local Mean Filter to Denoise Rician Noise

Abstract

Abstract MRI images suffer from a type of multiplicative noise called Rician noise. The traditional smoothing filters are not effective to reduce this type of noise. Non local Means (NLM) filters with bias correction is a promising technique for such type of signal dependent noise. The NLM denoising is based on self-similarity and is computationally very expensive. Many researchers are working to improve its time complexity. In most cases there is a tradeoff between speed and quality of denoised image. This paper proposes a speed enhanced NLM method that use integral image and fuzzy Jacord similarity measure to find the self-similarity of sub windows. This helps to find the weights of similar pixel at a faster rate than the traditional NLM algorithm and more accurately than the existing fast NLM method. Consequently, these similar pixels are used to generate the noise free pixels. At the end the conventional bias subtraction method is used as post processing step. The proposed scheme is tested with the standard brain web data set with different noise levels and compared with existing Fast NLM techniques and basic NLM using Root mean square error (RMSE), peak signal noise ratio (PSNR), Structure similar index (SSIM), quality index and computational time parameters methods. The proposed method gives better result than existing Fast NLM technique with high density Rician noise in the image and is 20 times faster than traditional NLM.