A Multimodal Biometrics Secured ATM

Security is crucial in financial institutions to protect clients from financial losses which can occur due to identity theft and ineffective authorization measures. Biometrics techniques are commonly used in these security systems to prevent thieves from stealing people's identity and using it for financial gains. However, the risk of identity theft has increased over the years due to the development of technology, especially the Internet of Things (IoT) and social media. To secure financial access, various systems and methods have been developed, such as the radio frequency identification (RFID)-based and the biometrics-based automated teller machine (ATM). The RFID-based devices have a dependency on the RFID cards which can be stolen, lost, misplaced or hacked. Existing biometric-based devices also have some drawbacks, with reliability and accuracy as the most common ones. The purpose of this research is to prevent identity theft by using multimodal biometrics technology for financial authorization and authentication. The biometric features used in this paper are the fingerprint and face due to their high accuracy when combined. A more reliable access granting system is developed with the low possibility to be spoofed. The proposed method also avoids the need to carry an ATM card, therefore, reducing the cases of it being stolen or misplaced.