作者: Zheng, Qian; Kumar, Ajay; Pan, Gang
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 卷: 38 期: 6 页: 1272-1279 出版年: JUN 2016
This paper proposes a new feature descriptor for the 2D palmprint matching. The descriptor is extracted for each point on the palmprint, based on the ordinal measure which partially describes the difference of the neighboring points’ normal vectors. We show that such 3D information can be extracted from a single 2D palmprint image. Four publicly available 2D palmprint databases are evaluated for both identification and verification.