SAR image segmentation based on the advanced level set

Image segmentation takes an important role in SAR image processing. In this paper, a SAR image segmentation method based on level set evolution combining edge feature and statistic information is proposed. In order to enhance the impact of edge on image segmentation, all edge values are homogenized according to the calculated ROA operator. Different from traditional method where the SAR distribution is often specified based on human experiences, the Edgeworth algorithm, an approximation method for statistical distribution model, gives any SAR image distribution a statistical expression. Considering the practicability of ROA operator and the adaptivity of Edgeworth series expansion at fitting statistical distribution, an energy function based on edge and region properties is defined. To implement image division, partial differential equation (PDE) of curve evolution is obtained by minimizing the function. The proposed approach uses more information from SAR images and is appropriate for any SAR images without the need for human-specified distribution pattern. Finally, the experimental results which are obtained from the SAR images of some typical regions such as rivers and buildings show the applicability of the proposed method.