Multibiometría de huella palmar y geomtería de mano para un sistema sin contacto orientado a dispositivos móviles.

A multimodal biometric system based on two handrelated traits included in a single image, hand geometry and palmprint, is proposed. The system has been designed to be used by applications in mobile devices, so contactless images were captured with minimum restrictions in an indoor environment to test its performance. This way, the images present certain interuser variability concerning to lighting, background or distance of the hand to the camera, together with high intra-user variability such as hand posing, orientation or openess degree, which directly influences the hand geometry and palmprint features.
To overcome the influence of this variability, a protocol to select those enrollment samples which best describe the user has been outlined. Results reinforce multimodal biometrics as a feasible solution to improve monomodal biometrics performance.