A synthetic aperture radar (SAR) target recognition method is proposed via linear representation over the global and local dictionaries. The collaborative representation is performed on the local dictionary, which comprises of training samples from a single class. Then, the reconstruction errors as for representing the test sample reflect the absolute representation capabilities of different training classes. Accordingly, the target label can be directly decided when one class achieves a notably lower reconstruction error than the others. Otherwise, several candidate classes with relatively low reconstruction errors are selected as the candidate classes to form the global dictionary, based on which the sparse representation-based classification (SRC) is performed. SRC also produces the reconstruction errors of the candidate classes, which reflect their relative representation capabilities for the test sample. As a comprehensive consideration, the reconstruction errors from the collaborative representation and SRC are fused for decision-making. Therefore, the proposed method could inherit the high efficiency of the collaborative representation. In addition, the selection of the candidate training classes also relieves the computational burden during SRC. By combining the absolute and relative representation capabilities, the final classification accuracy can also be improved. During the experimental evaluation, the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset is employed to test the proposed method under several different operating conditions. The proposed method is compared with some other SAR target recognition methods simultaneously. The results show the superior performance of the proposed method.

中文翻译：

---

基于两阶段稀疏表示的合成孔径雷达图像目标识别

通过在全局和局部字典上的线性表示，提出了一种合成孔径雷达（SAR）目标识别方法。协作表示是在本地字典上执行的，该字典包含来自单个班级的训练样本。然后，用于表示测试样本的重构误差反映了不同训练课程的绝对表示能力。因此，当一个类别的重建误差明显低于其他类别时，可以直接确定目标标签。否则，选择具有相对较低的重构误差的几个候选类作为候选类以形成全局字典，基于该字典执行基于稀疏表示的分类（SRC）。SRC还会产生候选类别的重构错误，反映了它们对测试样本的相对表示能力。作为综合考虑，将来自协作表示和SRC的重构错误融合在一起以进行决策。因此，该方法可以继承协同表示的高效性。此外，候选训练课程的选择还减轻了SRC期间的计算负担。通过组合绝对表示能力和相对表示能力，还可以提高最终分类的准确性。在实验评估过程中，动静目标获取和识别（MSTAR）数据集用于在几种不同的操作条件下测试该方法。同时将该方法与其他SAR目标识别方法进行了比较。