A multiplicative gradient-based anisotropic diffusion approach for speckle noise removal

We propose a novel directional diffusion method for speckle noise removal that uses the multiplicative gradient as an edge detector and operates on a moving orthonormal basis issued by a structure tensor based-approach and stochastic modelling. The method has good speckle removal and edge preservation properties and it can be used for filtering ultrasound, optical coherence tomography medical images or other types of images degraded by speckle, such as those acquired in Synthetic Aperture Radar (SAR) imaging systems. The effectiveness of our approach in speckle removal applications is demonstrated experimentally on computer generated and on real ultrasound images through comparisons with state-of-the-art Partial Differential Equations (PDE) and non-PDE-based methods.