A novel automated hand-based personal identification

Abstract

A reliable and robust verification approach using hand-print features is presented in this paper. The characteristics of the proposed approach are that two hand-base features are employed, the palm-print and finger-print features. The system consists of two parts: a convenient device for hand-print image acquisition and an efficient algorithm for fast hand-print recognition. A robust and adaptive image coordinate system is defined to facilitate feature extraction. Discrete wavelet zero-crossing encoding scheme and 2-D Gabor filter is applied to hand-print feature extraction and representation. The experimental results demonstrate the effectiveness of the proposed system. © Springer-Verlag Berlin Heidelberg 2006.