Multimodal biometric authentication framework

Abstract

Biometric authentication is getting more and more popular in recent years with the usage on smartphones, offices, airports and others. However, due to problems like noisy data and spoofing attacks, the accuracy and security of the authentication method greater decrease. Research shows that multimodal biometric is a solution that helps improve the reliability and accuracy of biometric systems. Multimodal biometrics system helps to target issues found in unimodal biometric systems. With multimodal biometrics system, attackers instead have to spoof multiple independent human traits which is more of a challenge compared to targeting unimodal biometric systems. The purpose of this project is to develop a mobile application which provides multimodal biometric authentication to users. This project targets to improve on existing biometric authentication system and provide a good user experience for the users. This application is created on Android Studio and uses Iritech Iris Scanner together with a facial recognition library using OpenCV. It combines both biometrics and perform score level fusion to help arrive at the final decision. Aside from the two biometrics, password login will also be added as an alternative allowing multiple login combination for the user to select from. In conclusion, the application is mostly completed but still require further improvement like UI design and additional settings.