I am doing a project related to sar and optical image registration. I need to segment sar and optic image and register the obtained regions in two images.
SAR imaging has exactly the same mathematical modeling as ultrasound imaging. It can be modeled with a multiplicative model as the noise corupting the images is multiplicative. Thinking in this direction, the methods tah can be used to segment SAR images could be the same as used for ultrasound. There are a lot of methods proposed towards this direction. Maybe you can look at my publications:
C.P. Loizou, C.S. Pattichis, A. Nicolaides, M. Pantziaris, “Manual and automated media and intima thickness measurements of the common carotid artery,” IEEE Trans. Ultras. Ferroel. Freq. Contr., vol. 56, no. 5, pp. 983-994, 2009.
You may also have a look at our website: http://www.medinfo.cs.ucy.ac.cy/