Recognition of SAR Image Based on SVM and New Invariant Moment Feature Extraction

Support vector machine (SVM) is regarded as a good alternative of the traditional learning classification. Because of its excellent learning performance, it has become a research hot spot in the field of machine learning. This paper describes the new invariant moment feature extraction of SAR objectives based on shape feature, then classify and train the eigenvectors by using SVM. The excellent recognition rates achieved in experiments indicate that SVM is well suited for SAR image target recognition.