3D Signature for Efficient Authentication in Multimodal Biometric Security Systems

Unimodal biometric systems rely on a single source of biometric trait information for recognition of individuals. These systems are highly vulnerable to spoof attacks as imposters easily imitate the particular biometric trait of any genuine user. The impact of circumvention is reduced by combining the functions of different unimodal biometric systems to perform as a multi-biometric system. The multimodal biometric systems operate in two or more ways to authenticate individuals by their biometric traits. This paper proposes a multimodal biometric security model for efficient authentication. The model deals with multi-biometrics in first two phases for identification, verification followed by the decision making as third phase. The first phase employs physiological biometric traits for identification by exhibiting the liveliness of individual. The second phase uses 3D handwritten signature for verification of the claiming identity. The 3D handwritten signature records the pressure information on the special signature pad during the signing process. The pressure information recorded on different layers of the signature pad provides distinct information for verification of the individuals based on their signatures. This unique pressure information raises the level of difficulty in the forgery of signatures. The individual matching score is calculated in identification phase and verification phase. The fusion is performed on the obtained matching scores and compared with threshold value in the decision phase to provide efficient authentication of the individual. The threshold value in the decision phase is varied according to particular application for combating the problem of circumvention in biometric security systems. The preliminary results show the viability of using 3D handwritten signature in biometric security.