Denoising medical image using Efficient Fussion filter

Abstract

Digital images play vital role in medical image processing. The quality of the images affected by different noises such as distortion and blurring. There are all affect the accuracy of the prediction. So it can be denoised by various filtering algorithms. These algorithms help to improve the quality of the digital image and increase the SNR (Signal-to-Noise Ratio) value. In this paper, a statistical filter has been proposed named as Fusion filters, a modified version of Median filter and kalman filter by sorting the luma component values, then median value has been assigned to the processing pixel value in a sliding window (4×4). Also, Median filter, Mean filter, Kalman filter and proposed had taken for the comparative study. PSNR and MSE metrics are compared to examine the performance and the quality of the image. The result shows that the proposed filter increases the PSNR (Peak Signal to Noise ratio) and reduces MSE (Mean Square Error) metric values and produces good results.