Based on Rapid Fingerprint Identification Application in Railway Station Research

Abstract

Principal component analysis (PCA) is a common feature selection algorithm, the classical PCA method is to calculate the correlation between the various features, but the correlation cannot evaluate the nonlinear relationship between variables, then present 2DPCA and Kernel 2DPCA. The method proposed in this paper is aimed at the situation where the passenger traffic is large and the passenger fingerprint information gathering is affected by the external factors. Two dimensions of two - dimensional nuclear principal component analysis (K2DPCA+2DPCA) can effectively solve non-linear separable fingerprint identification problems. At the same time, it can reduce the computational complexity of the template and reduce the storage space.