A Fast SAR Target Recognition Approach Using PCA Features

The real-time ability and recognition rate are two primary goals for evaluating the performance of an SAR image target recognition system. This paper concentrates on the analysis of key factors which influence these two goals. According to the analysis, a fast SAR target recognition approach is proposed, which utilizes a self-organizing neural network trained with the Hebbian rule to extract the principal component features and a multi-layer neural perceptron network as the classifier. The experimental results show that it consumes little memory and runs very fast with a considerable recognition rate, thus can be used in a real-time application.