Paolo Abeni

NIS03-4: Implementing Biometrics-Based Authentication for Mobile Devices

This paper presents a face recognition system for mobile devices running the Symbian operating system. The recognition algorithm is based on a one-class classification approach implemented by means of support vector machines. It discusses important aspects related to the practical implementation of the algorithm on Symbian 60 Series mobile phones, and gives some preliminary results outlining the performances achieved by the recognition system with several different configurations.

User Authentication based on Face Recognition with Support Vector Machines

The present paper proposes an authentication scheme which relies on face biometrics and one-class Support Vector Machines. The proposed recognition procedures are based on both a global approach and on a combination of a global and a component-based approaches. Two different features extraction methods and three light compensation algorithms are tested. The combined system outperforms the global system and yields a significant performance enhancement with respect to the prior results obtained with the one-class Support Vector Machines approach for face recognition.

A Face Recognition System for Mobile Phones

The present paper proposes a biometrics-based authentication system for mobile devices running the Symbian Operating System. Mobile devices are becoming more and more similar to personal computers, hence they are also becoming repositories for sensitive information. In this context a more powerful authentication mechanism than simple passwords becomes essential. The paper describes a face recognition approach for mobile devices, discusses some important issues related to the practical implementation of the authentication scheme, and gives some preliminary results outlining the performances and the limits of proposed recognition system.