Passive millimeter-wave metal target recognition based on manifold learning

The existence and characteristics of low dimensional embedded manifold of the short-time Fourier spectrum of metal target echo signal are explored using manifold learning algorithm, Laplacian eigenmaps, aiming at the disadvantages of feature extraction and selection of the traditional methods in passive millimeter-wave (MMW) metal target recognizing process. Target classification is performed through comparing the similarity of the test samples and the positive class in terms of the embedded manifold. The experiments show that the method gets higher recognition rate than other linear and kernel-based nonlinear dimensionality reduction algorithm, and is robust to data aliasing.