Tuning of level-set speed function for speckled image segmentation

The segmentation of speckled images, as the synthetic aperture radar (SAR) images, is usually recognized as a very complex problem, because of the speckle, multiplicative noise, which produces granular images. In segmentation problems, based on level set method, the evolution of the curve is determined by a speed function, which is fundamental to achieve a good segmentation. In this paper we propose a study of the new speed function obtained by the linear combination of image average intensity and image gradient speed functions. Thus the aim is tuning the combined speed in the segmentation process. We segmented synthetic images by tuning parameters of the new speed function and we evaluated the best computed results. Then we applied this experimental setup to real SAR images, which are PRecision Images, acquired during European Remote Sensing mission, and a Cosmo-SkyMed image. In particular, we are interested in monitoring complex areas with low light covered by clouds, as coastlines and polar regions may be. In Earth Observation, the acquisition of SAR data becomes fundamental, since the SAR sensor can work in the night/day and in all weather conditions.