Asaduzzaman Babu and Mahmoud R. El-Sakka, "SRAD with Weighted Diffusion Function", International Conference on Image Analysis and Recognition, ICIAR'2013, LNCS 7950, pp. 264-273, Springer-Verlag Berlin Heidelberg, June 2013, Povoa de Varzim, Portugal.

Abstract

Speckle Reducing Anisotropic Diffusion, SRAD, is a multiplicative noise reduction method. In highly speckled environment, SRAD occasionally produces over-smoothed, dislocated/broadened edge lines and inadequate de-noising on homogeneous image regions where the speckles are well developed. To overcome these weaknesses, we propose a modification to SRAD with a weighted diffusion function. The proposed diffusion function is a weighted sum of two components – (1) a global ratio-based edge detection inspired component and (2) the original diffusion function of SRAD. The proposed filter shows significant improvement in de-noising and edge preservation.