基于2DPCA-SCN正则化的SAR图像目标识别方法

合成孔径雷达（synthetic aperture radar，SAR）图像解译是一项重大的科学应用挑战，SAR图像目标识别已成为该领域的主要研究方向之一。针对SAR图像识别算法训练参数较多的问题，本文提出一种二维主成分分析（two-dimensional principal component analysis，2DPCA）与L2正则化约束的随机配置网络（stochastic configuration network，SCN）进行集成学习的SAR图像目标识别方法。2DPCA不仅能够有效地提取出目标的特征信息而且通过稀疏表征方式降低数据量，SCN正则化算法参数较少且可以有效避免网络过拟合问题，提高网络的识别率。我们将提出的方法在MSTAR (moving and stationary target acquisition and recognition)数据集上进行实验，结果表明该方法相对传统方法具有更高的识别率。 

Target Recognition Method Based on 2DPCA-SCN Regularization for SAR Images

Synthetic aperture radar (SAR) image interpretation is a major scientific application challenge. SAR image target recognition has become one of the main research directions in this field. In view of the fact that target recognition algorithms for SAR images needs many training parameters. This paper proposes a target recognition method based on the two-dimensional principal component analysis (2DPCA) and the L2 regularization constrained stochastic configuration network (SCN) for integrated learning. 2DPCA can not only effectively extract the feature information of the target but also reduce the amount of data through sparse representation. The Regularized SCN algorithm can effectively avoid the over-fitting problem and improve the recognition rate of the network. Based on the moving and stationary target acquisition and recognition (MSTAR) dataset, the experimental results show that the proposed method can achieve a higher recognition rate than the traditional method.