A novel palm vein recognition approach based on Enhanced Local Gabor Binary Patterns Histogram Sequence
Matthias Fischer, Marlies Rybnicek, Simon Tjoa · International Conference on Systems, Signals and Image Processing · 2012
An emerging technology that increasingly gains importance on the biometric market during the last years is vein recognition. Therefore, in this paper a novel palm vein recognition system is presented which is based on the Enhanced Local Gabor Binary Patterns Histogram Sequence (ELGBPHS) algorithm. The ELGBPHS is a well-established face recognition algorithm combining 2D-Gabor Filters, Local Binary Pattern and Histogram Intersection for recognition. In course of this paper relevant pre-processing steps as localization and segmentation of the Region of Interest (ROI) are presented. Thereafter, we discuss the feasibility of the ELGBPHS algorithm for palm vein recognition. Within this evaluation the approach achieved a False Rejection Rate (FRR) of 1.7% and a False Acceptance Rate (FAR) of 0%.