Secure multi-spectral hand recognition system

This paper proposes a secure multimodal biometric recognition system with a multi-level fusion architecture. A multi-spectral camera is used to capture hand images in the visible and in the near-infrared (NIR) bands of the spectrum. The system uses four biometric traits from the user´s hands: palmprint (PP), finger surface (FS), hand geometry (HG) and palm veins (PV), being the latter captured in the near-infrared band. In the feature extraction stage, three different techniques (i.e., Orthogonal Line Ordinal Features, Competitive Code and PalmCode) are implemented to extract features from the palmprint, finger surface and palm veins. The resulting features are then converted to binary in order to apply a secure template storage scheme, consisting of a cryptographic hash function combined with an error-correcting code. In the proposed system architecture, the hand geometry is used as a database indexing trait to reduce the search time needed for identification. Recognition results, obtained using a proprietary database that was built for that purpose, are presented for different combinations of the feature extraction techniques on the various biometric traits, as well as for different fusion methods.