Biometrics for Mobile Devices: A Comparison of Performance and Pattern Classification Approaches

Mobile devices have become indispensable tools nowadays. With growing technologies, applications and services are being added to the mobile devices all the time. Its usage in business and enterprises need it to be secure from unauthorised access. The extent of protection currently available is not adequate for the services that are employed in mobile devices. Biometrics have the privilege of providing secure authentication through utilising the unique characters of a person. Reports on the theft and loss of information and the wide acceptance on biometric authentication paved the way in its research on mobile devices. Several performance issues are to be considered when implementing biometrics in mobile devices This paper focuses on the comparison of different pattern classification approaches employed in Face, Fingerprint, Keystroke and Signature biometric techniques and their effect on the performance on these devices. A detailed study on different algorithms employed in each technique has been performed. Most of the algorithms that are used for authentication follows similar approach regardless of the techniques and are broadly categorised between statistical and neural network approaches. Processing time in each approach is spent for feature extraction and classification and the storage for holding these features. Neural network techniques performs authentication with higher accuracy but require huge memory capacity and longer training time which makes it infeasible to be employed in mobile devices. Statistical approaches although consumes less processing time than neural networks, still requires considerable processing time to perform authentication in real time. Biometrics is a future technology which can provide secure authentication. Biometrics in mobile devices will become practical if the developments in technology in mobile architectures and software are implemented fully on these devices