Preliminary work on rotation-invariant algorithms for contactless palm vein biometrics

摘要: Contactless palm vein biometrics is an emerging technology that identifies a person based on his/her palm's vascular pattern without needing the to have contact with recording device. The underlying beneath human palm, so information maintains secrecy. Most of existing contactless systems are unable locate region interest (ROI) when rotation user's hand large and rotated certain angles. Large in position will adversely affect performance system. In this paper, we propose novel rotation-invariant algorithm called Zig-Zag valley detection (Z2VDA) solve problem. proposed Z2VDA uses circular intersection technique points root fingers which serve as landmark correct hand. An empirical study shows works well able detect effectively eight different