Enhancing Security of Automated Teller Machines Using Biometric Authentication: A Case of a Sub-Saharan University

Abstract

A wide variety of systems need reliable personal recognition systems to either authorize or determine the identity of an individual demanding their services. The goal of such systems is to warrant that the rendered services are accessed only by a genuine user and no one else.In the absence of robust personal recognition schemes, these systems are vulnerable to the deceits of an impostor. The ATM has suffered a lot over the years against PIN theft and other associated ATM frauds. In this research is proposed a fingerprint and PIN based authentication arrangement to enhance the security and safety of the ATM and its users. The proposed system demonstrates a three-tier design structure. The first tier is the verification module, which concentrates on the enrollment phase, enhancement phase, feature extraction and matching of the fingerprints. The second tier is the database end which acts as a storehouse for storing the fingerprints of all ATM users preregistered as templates. The last tier presents a system platform to relate banking transactions such as balance enquiries, mini statement and withdrawal. The system is developed to run on Microsoft windows Xp or higher and all systems with .NET framework employing C# programming language, Microsoft Visio studio 2010 and SQL server 2008. The simulated results showed 96% accuracy, the simulation overlooked the absence of a cash tray. The findings of this research will be meaningful to Banks and other financial institutions.