Online Multi-Parameter 3D Signature Verification through Curve Fitting

Summary Biometric based personal identification is a reliable and widely accepted method for authentication. Human 3D signature is distinct from other biometric authentication methods due to the presence of third dimensional hidden information. In this paper, a new model for on-line 3D signature verification using multiple parameters is proposed. The parameters considered from human signature namely, velocity, acceleration, pressure, direction, pen ups/downs, total time taken, length and depth of the signature are unique for each person. The proposed model highlights the third dimensional distinctive parameter, depth of the signature for its hidden information. Curve fitting is performed on the points obtained from different non-linearly spaced layers of the signature pad. The best fitted curves from all the layers and other signature parameters are used in the process of verification of 3D signature. The digital multi-parameters of the 3D signature are further encrypted with cryptographic algorithms to protect from cryptanalysis. The attempts for 3D signature expert forgery by satisfying both the global and local parameters of the signature are difficult. The application of the 3D signature verification broadly ranges from authentication of financial transactions to authorization of administrative documents.