Based on Rapid Fingerprint Identification Application in Railway Station Research

Yi-jun WANG, Hai-xin LIN, Li-mei GUO

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.

Keywords


Two-dimensional nuclear principal component analysis, Non-linear fingerprint template recognition, Dimension compressing, Fast recognition


DOI
10.12783/dtcse/aiie2017/18191

Full Text:

PDF

Refbacks

  • There are currently no refbacks.