An Open-Set Recognition Approach for SAR Targets Using Only Classification Scores

Focusing on the open set recognition problem of Synthetic aperture radar (SAR) targets, a simple and robust openset recognition approach using only a simple convolutional neural classification network is proposed in this paper. The proposed approach constructs the D-SCORE feature and uses the statistical method to model the D-SCORE obtained in the training phase, so as to obtain the threshold for identifying the known and unknown classes, and ultimately realizes the open-set recognition of SAR targets. Experiments on the moving and stationary target acquisition and recognition (MSTAR) dataset show that the proposed approach achieves better open-set recognition performance.