Radar HRRP Target Recognition Based on Optimal Transformation of Kernel Space and Cluster Centers

How to extract effective discriminant features of high-resolution range profile (HRRP) is one of the issues for radar automatic target recognition (RATR). In this paper, a novel method for extracting discriminant features is proposed by using kernel optimal transformation and cluster centers techniques (KOT-CC). In addition, to alleviate the effect of independent noises on the discrimination, we propose a general algorithm for dealing with the singular cases of total scatter matrix, which are often encountered in various kernel methods, such as kernel fisher discriminant analysis (KFDA). Finally, experiment results on the measured radar data are compared and analyzed, which verify that KOT-CC is a powerful technique for extracting nonlinear discriminant features and improving recognition rate.