Structure Feature Extraction for Finger-Vein Recognition

Abstract

A new finger-vein image matching method based on structure feature is proposed in this paper. To describe the finger-vein structures conveniently, the vein skeletons are firstly extracted and used as the primitive information. Based on the skeletons, a curve tracing scheme depended on junction points is proposed for curve segment extraction. Next, the curve segments are encoded piecewise using a modified included angle chain, and the structure feature code of a vein network are generated sequentially. Finally, a dynamic scheme is adopted for structure feature matching. Experimental results show that the proposed method perform well in improving finger-vein matching accuracy.