Ship Classification Based on Density Features in SAR Images

Abstract Ship classification in SAR images has attracted much attention by researchers. In this paper, a target method for three commercial ships (container ships, bulk carriers and oil tanker) is proposed analyzing their scattering features. Firstly, the ship slice preprocessed to obtain binary image, from which density features can be extracted, describing point distribution. Finally, support vector machine (SVM) classifier applied classify these types of ships. The experimental results show that accuracy structure feature strength low, while reach 80% combination with improve accuracy. Combining best performance.