Comparative study of Various Denoising Filters for MR Images

Magnitude Resonance imaging (MRI) is a priceless indicative apparatus and a basic noninvasive imaging methodology that gives an incomprehensible measure of anatomical and useful data valuable for diagnosis and patient treatment. The MRI images captured are usually corrupted from Gaussian noise, salt and pepper noise, speckle noise etc., Therefore obtaining of brain image with accuracy is very difficult. The presence of noise results in the reduction of quality in the magnetic resonance (MR) images and hence limits the visual review and impact the quantitative estimations from the information. So there is requirement for image preprocessing of the obtained image to remove unwanted noise. In this paper, various filtering algorithms in the spatial domain are discussed and their performance in removing noise is examined. The performance of these techniques was accessed with respect to two quantitative measures, Peak Signal-to-Noise Ratio (PSNR), and Mean Square Error (MSE).