Biometric identification through hand vein patterns

Vein Pattern is the vast network of blood vessels underneath a person´s skin. Anatomically, the shape of vascular patterns in the back of the hand is unique to the individual even for identical twins and it remains stable over a long period. The properties of uniqueness, stability and strong immunity to forgery of the vein pattern make it a potentially good biometric trait. In this study, we present a novel biometric technique based on the statistical processing of the hand vein patterns. To test the performance of the algorithm, we constructed a hand vein image database of 30 people, 20 men and 10 women, in the near infrared band. We have considered alternative features and classifiers as well as their fusion. We pursue methods to make the algorithm resistant to various physical conditions.