Recognition of Radar Target Based on Optimal Factor Analysis Subspace Using Rangeprofile
雷达目标一维距离像识别中的最优因式分析子空间法

A novel approach of radar target recognition is proposed in this paper.For each target class, according to maximum likelihood rule and minimum classification error rate rule,an optimal factor analysis subspace is constructed by factor analysis on the training sample sets of target rangeprofiles.The optimal factor analysis subspace can produce an enhancement of correlation existing in the features of same target class.Such an enhancement provides higher clustering degree of the same class features.Thus,the factor analysis subspace is used to extract the feature of target for improving the accuracy of classification.The experimental results of three kinds of airplane targets demonstrate the efficiency of the approach proposed in this paper.