Biometric Authentication via Finger Photoplethysmogram
Xiao Zhang, Zheng Qin, Yongqiang Lyu · Proceedings of the 2018 2nd International Conference on Computer Science and Artificial Intelligence · 2018
With the advent of information society, identity recognition technology has become more and more important. Traditional biometric-based identity authentication technologies such as fingerprint, iris, and face have been widely used in various fields of society. However, such methods have more or less problems. This paper proposes a biometric identification technology based on photoplethysmogram (PPG) signal, which can achieve recognition accuracy about 90% via Support Vector Machine (SVM). Two kinds of identity authentication algorithms and optimization of one with Kernel Principal Component Analysis(KPCA) are introduced. Meanwhile, the False Reject (FR) and False Accept (FA) are low, which represents a good performance. Experimental results and simulation analysis show that the PPG-based technology is a reliable biometric technology with high security, and broad application prospects.