ABSTRACT

As biometrics gains popularity, there is an increasing concern about privacy and

misuse of biometric data held in central repositories. Furthermore, biometric
verification systems face challenges arising from noise and intra-class variations.
To tackle both problems, a multimodal biometric verification system combining
fingerprint and voice modalities is proposed. The system combines the two
modalities at the template level, using multibiometric templates. The fusion of
fingerprint and voice data successfully diminishes privacy concerns by hiding the
minutiae points from the fingerprint, among the artificial points generated by the
features obtained from the spoken utterance of the speaker. Accuracy is increased
compared to the previous results for voice verification over the same speaker
database. In the long run, biometric identification promises to provide the global
citizen with a sound identity management system, which could develop quite
independently of nation states. Of course one could argue that this would be a
tragedy, and that an ID management solution controlled and operated by
governments is absolutely essential in order for government agencies to provide
the services citizens expect to receive and to guarantee the survival of the same
notion of state. Many private employers also require biometric identification
systems to control access to workplaces or as cheat-proof time clocks. The
proposed automated attendance system based on fingerprint recognition was tested
on a class of student fingerprint databases and achieved significant results for
taking an attendance of the students. The proposed system has been implemented
using matlab and arduino programming paradigm platform