A Two Phase Ultrasound Image De-speckling Framework by Nonlocal Means on Anisotropic Diffused Image Data

Image de-speckling is one of the most challenging issues in multimedia imaging systems. All available speckle noise reduction filters are almost capable but failed to restore subtle features such as low gray level edges and fine details under poor contrast background. This paper presents a two phase ultrasound image framework by utilizing capability non-local mean filtering method for edge preservation on anisotropic diffused images. The prior smoothing along with enhancement diffusion carried out first which then followed means sharpening next phase. degree attenuation evaluated standard images results compared state-of-the-art advanced techniques methods. experimental analysis demonstrates proposed reducing preserving better than filters.