Removal of Multiplicative Noise and Segmentation based Efficient Symlet Thresholding in Ultrasound Kidney Images

Abstract

Nowadays the ultrasound medical images are used everywhere for diagnosing various diseases. We are using ultrasound kidney images for this project, in this first the noise was identified and then the image was treated with discrete wavelet transform(DWT).In this the pixels are converted into wavelets and then filtering are done with the help of median filter and wiener filter.In this filter the noise was removed and then the edges were preserved. The wavelet transform is done with the help of haar and symlet wavelet. And then the images are segmented to identify the presence of kidney stones.Then the final output was obtained with the help of Peak Signal to Noise Ratio(PSNR) and Mean Square Error(MSE).