Targets Recognition Based on Deep Learning

A deep learning based recognition algorithm to identify various targets was proposed in this paper. Compared with traditional machine learning, deep learning can extract the features of recognized targets better and obtain higher accuracy. We first simulate electromagnetic scattering of targets and acquired the scattering electric field of targets at different frequencies and scattering angles. Then we use the scattering electric field to get the ISAR image. Then we input ISAR images to the deep convolutional neural networks for training, and extract the deeper features of the targets. In order to improve the accuracy of recognition, we combine different polarization ISAR images as one sample. Numerical results show that the average recognition accuracy of our proposed method is 99.72%, which verifies the effectiveness of the method.