合成孔径雷达自动目标识别是目前国内外模式识别领域的重点研究课题之一。本文给出了一种内存需求小,低计算复杂度且具有较好识别性能的SAR图像目标识别方法,先通过自适应阈值分割来获得目标图像,然后提取其中心矩特征,采用SVM来进行识别。基于美国M STAR实测数据的识别试验验证了该方法的有效性。 Synthetic aperture radar automatic target recognition is one of the key research topics in the field of pattern recognition at home and abroad. This paper presents a SAR image target recognition method with small memory requirement, low computational complexity and good recognition performance. Firstly, the target image is obtained by adaptive threshold segmentation, then the centroid features are extracted and SVM is used to identify . The identification test based on the measured data of M STAR in USA verifies the validity of this method.