期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2018
卷号：96
期号：9
出版社：Journal of Theoretical and Applied
摘要：Finger vein is a physiological biometric technology used in the identification systems for personal authentication based on the physical features of the vein patterns in the finger. In this paper, computer vision algorithms (FAST and Harris) were used to extract features (corner points) from the finger vein image, while the matching of patterns was based on the differences between corners represented in the form of points using the Manhattan distance. The False Matching Rate (FMR) and False Non-Matching Rate (FNMR) were minimized to obtain the optimum threshold value. This threshold were used to make the final decision. The proposed system proved that use of two algorithms together reduces the error rate and aids to produce a reliable system of finger vein identification.
