SAR Image Recognition Based on Parallel Vision

In order to solve the problems of insufficient SAR data and difficulty in labeling in SAR image recognition task, this paper proposes a SAR image recognition method based on parallel vision. We present an improved deep convolutional generative adversarial network model that is used to generate a large number of diverse virtual samples. By mixing real images and virtual images, we carry out computational experiments for SAR image recognition. A large number of experiments on the public dataset MSTAR verify the effectiveness of parallel vision applied to SAR image recognition. Combining parallel vision and deep learning can further promote the interpretation of SAR images.