A Biometric Identification Using the Motion of Fingers

Abstract

We propose a new method of biometric identification using the bending motion of fingers that is one of the highest repeated motions of the body. Forefingers consist of hinge joints that enable them to move in one direction only. They also have a tendon that helps the first joint of the finger move in tandem with the second joint. It causes high repeatability. In the algorithm, curvature, one of the behavioral profiles, is calculated from the edge pixels of binary image of the forefinger. Joint angle of the forefinger is measured, and the behavioral profiles are compared only when the joint angle of compared data is consistent with registered data. Proposed behavioral biometrics is able to define the comparison based on temporal continuity and static profiles providing high accuracy. From the experimental results, it is learned that this much data is sufficiently accurate for the identification.