In this work, an integrated contactless multiple hand feature acquisition system is designed. The system can capture
palmprint, palm vein, and palm dorsal vein images simultaneously. Moreover, the images are captured in a contactless
manner, that is, users need not to touch any part of the device when capturing. Palmprint is imaged under visible
illumination while palm vein and palm dorsal vein are imaged under near infrared (NIR) illumination. The capturing is
controlled by computer and the whole process is less than 1 second, which is sufficient for online biometric systems.
Based on this device, this paper also implements a contactless hand-based multimodal biometric system. Palmprint, palm
vein, palm dorsal vein, finger vein, and hand geometry features are extracted from the captured images. After similarity
measure, the matching scores are fused using weighted sum fusion rule. Experimental results show that although the
verification accuracy of each uni-modality is not as high as that of state-of-the-art, the fusion result is superior to most of
the existing hand-based biometric systems. This result indicates that the proposed device is competent in the application
of contactless multimodal hand-based biometrics.