Multibiometric systems based verification technique
Farhat Anwar, Md. Arafatur Rahman, Saiful Azad · Padua@thesis (Department of Information Engineering University of Padova) · 2009
Multibiometric systems represent the fusion of two or more unimodal biometric systems. Such systems are expected to be more reliable due to the presence of multiple independent pieces of evidence. Since security is one of the important concerns of twenty first century, multibiometric systems can play an important role in ensuring security. In this paper, a multibiometric system is proposed for human verification i.e. authenticating the identity of an individual. The geometrical dimensions of a human hand, such as hand geometry, finger stripe geometry or palm geometry, contain information that is capable of verifying an individual. Among them, hand geometry based verification is the oldest implemented biometric type (debuting in the market in the late 1980s) and finger stripe is the most recent biometric type proposed. The proposed multibiometric system uses both hand and finger stripe geometry for verification. Artificial Neural Network (ANN) is applied for feature learning and verification process. At the end of the paper, results based on 200 individuals and comparison between proposed method and published alternative methods are demonstrated. The experimental results exhibit that the proposed method outperforms the existing methods.