Personal Authentication Using Finger Knuckle Surface

This paper investigates a new approach for personal authentication using fingerback surface imaging. The texture pattern produced by the finger knuckle bending is highly unique and makes the surface a distinctive biometric identifier. The finger geometry features can be simultaneously acquired from the same image at the same time and integrated to further improve the user-identification accuracy of such a system. The fingerback surface images from each user are normalized to minimize the scale, translation, and rotational variations in the knuckle images. This paper details the development of such an approach using peg-free imaging. The experimental results from the proposed approach are promising and confirm the usefulness of such an approach for personal authentication.

I. Introduction

The rapid growth in the use of e-commerce applications and penetration of information technology into daily life requires reliable user identification for effective and secured access control. Hand-based biometrics has received considerable attention over recent years which exploits several internal and external features that are quite distinct in an individual. The user acceptance for the hand-based biometrics system is very high. These systems are becoming more convenient and user friendly with the introduction of peg-free and touchless imaging. The use of these hand-based systems for large-scale personal authentication requires further efforts to explore additional features that can be simultaneously extracted from the hand images. in this paper, our efforts are focused on developing an automated method to extract knuckle texture and geometrical features from the fingerback surface and investigate its performance for a potential biometric system.