Comparing infrared and visible illumination for contactless hand based biometric scheme

Abstract

This paper presents two contact-free biometric identification system based on geometrical features of the human hand. The right hand images are acquired by a commercial modified webcam with a 320x240 pixels resolution. The main difference between both systems is the illumination. A 60 W visible range bulb was the first choice. An infra-red light was used in the second approach to solve segmentation problems in real environments. The geometrical features are obtained from the binarized images and consist in normalized measures of the index, middle and ring finger for the infra-red system and projective invariants features for the visible light system. A Support Vector Machines is used as verifier.