SAR target recognition method of MSTAR data set based on multi-feature fusion

To solve the problem of low recognition rate of synthetic aperture radar (SAR) target based on feature recognition, a target recognition method of SAR image based on multi-feature fusion is proposed, which combines Hu moment, Harris corner point and Gabor feature. The three kinds of features describe the target's geometric shape feature, corner feature and image texture feature respectively, which can improve the accuracy of SAR target recognition from the aspect of feature extraction. Based on the MSTAR data set, the experiment is carried out under standard and extended operating conditions. The results show that the proposed method can effectively overcome the deficiency of insufficient single feature description information and improve the SAR target recognition rate to a certain extent.