Despeckling trilateral filter

Abstract

The bilateral filter smoothes noisy signals while preserving the semantic signal features. Its main advantage is being non-iterative. It is effective for a variety of applications in computer vision and computer graphics. However, little is known about the usefulness of bilateral filtering for speckle images. We propose a non-iterative, despeckling trilateral filter (DSTF) for smoothing ultrasound or synthetic aperture radar imagery. This filter combines the spatial closeness, intensity similarity and the coefficient of variation component. It generates outputs with speckle regions smoothed and structural features well preserved. The performance of the method is illustrated using synthetic, ultrasound and radar images. We show that the DSTF improves the bilateral filter with better speckle suppression, and is more computational efficient than the heavily iterative speckle reducing anisotropic diffusion.