In our previous study, we proposed a hand-waving finger vein authentication system, in which finger region extraction
from captured images was effective to verify the finger vein patterns with high accuracy. However, it is not easy to
extract the correct finger region from grayscale images that are taken with a near infra-red LED, because the background
condition of the captured image changes complicatedly according to the location of the waving hand. In order to
overcome this limitation, we propose an alternative finger region extraction method that takes color images with an RGB
camera and a white light source and identifies the finger region based on the skin color information.
|