期刊名称：IOP Conference Series: Earth and Environmental Science
印刷版ISSN：1755-1307
电子版ISSN：1755-1315
出版年度：2019
卷号：252
期号：3
页码：1-10
DOI：10.1088/1755-1315/252/3/032210
出版社：IOP Publishing
摘要：Biometrics is a highly efficient method of personal identification in civil fields. In this paper, we present a new biometrics system based on inner-knuckle-print (IKP). A new IKP image acquisition device with a finger guide is built for restricting the finger posture in a friendly way. A modified maximum curvature point method is proposed for feature extraction; it can extract the central region of the IKP line pattern robustly against illumination variation. The experimental results show that the proposed method achieves the equal error rate of 0.36%, performing better other traditional methods. In addition, it works in real-time.
