Noise Suppression using Weighted Median Filter for Improved Edge Analysis in Ultrasound Kidney Images?

Due to the characteristic speckle noise of ultrasound(US) kidney images, a noise reducing filter must be first applied before image processing stages like segmentation, registration etc. In addition the speckle noise suppression methods are highly required to improve the quality of the ultrasound image in retaining the edge features of the kidney images. The effect of this stage increases the dynamic range of gray levels which in turn increase the image contrast. The proposed system develops Weighted Median filter speckle noise suppression method for ultrasound kidney images. This paper designs intensity invariant local image phase features, obtained using improved Circular Gabor filter banks, for extracting edge texture features that occur at core and intermediate layer interfaces. The proposed model does the extension of phase symmetry features to modified circular Gabor mode for use in automatic extraction of kidney edge texture features from US normal and diseased patient images. The system functionality is proved qualitatively and quantitatively through experimentation for synthetic and real data sets. The speckle noise error ratio with respect to the standard US images are compared and experimented.