Radar Hrrp Target Recognition Using Multi-Kfd-Based Lda Algorithm

Linear double-layered feature extraction (DFE) technique has recently appeared in radar automatic target recognition (RATR). This paper develops this technique to a nonlinear field via parallelizing a series of kernel Fisher discriminant (KFD) units, and proposes a novel kernel-based DFE algorithm, namely, multi-KFD-based linear discriminant analysis (MKFD-LDA). In the proposed method, a multi-KFD (MKFD) parallel algorithm is constructed for feature extraction, and then the projection features on the MKFD subspace are further processed by LDA. Experimental results on radar HRRP databases indicate that, compared with some classical kernel-based methods, the proposed MKFD-LDA not only performs better and more harmonious recognition, but also keeps higher robustness to kernel parameters, lower training computational cost, and competitive noise immunity.