Ensemble Learning and Optimizing KNN Method for SAR Target Recognition
As we know, the target classification of synthetic aperture radar (SAR) image is often affected by its azimuths.So we want to find a new method to solve the problem.Ensemble with K Nearest Neighbor (KNN) learner is a novel approach which has many advantages over other conversational methods such as simplicity and good generalization ability.In this paper, we intend to improve the performance of the SAR image target recognition system by introducing a novel method combining optimizing annular region-weighted distance KNN with BagWithProb ensemble learning schemes.And feature vectors of target images are extracted with principal component analysis in wavelet domain.Experiments studied in this paper indicate that the proposed method can effectively improve the accuracy of the new system.
ensemble learning SAR image Automatic Target recognition
Bo Qian Shengli Wang Weimin Wang Li Yu
Nanjing Research Institute of Electronic Technology,Nanjing,Jiangsu,210039,China
国内会议
大连
英文
448-455
2010-08-20（万方平台首次上网日期，不代表论文的发表时间）