An Approach for High Resolution Radar Target Recognition Based on BP Neural Network

The paper introduces an approach for high resolution radar target recognition by BP neural network. To solve the problem of sensitivity characteristics of HRRP, some preprocessing measures are taken, which enhances the signal-to-noise ratio,effectively. Some features such as general central moments and distribution entropy of HRRP are extracted to form a new feature vector. A back-propagation (BP) neural network classifier is designed and trained to discriminate three kinds of target from each other, having as input the extracted features vector. Experiment results demonstrate that the method can improve the target classification performance efficiently and effectively.