On-line signature verification based on FIR system characterizing motion pressure

Abstract

We propose an on-line signature verification method based on finite impulse response(FIR) system characterizing motion pressure of pen-point trajectory in signing process. The discrete cosine transforms(DCTs) of the handwriting feature is used to reduce the fluctuation and extract the feature of handwriting. The signature verification system is realized by four FIR subsystems. Then motion pressure can be characterized by using the FIR subsystem having the DCTs of the area pressure and motion pressure as the input and the output of the FIR system, respectively. The obtained impulse responses of the four FIR subsystems are used as the individual feature for signature verification. Finally, the signature can be verified by evaluating the difference between the impulse responses of the FIR subsystems for a reference signature and the signature to be verified. The signature verification experiments were performed on the SUBCORPUS-100 MCYT [J.Ortega-Garcia et al.2003] signature database consisting of 5,000 signatures from 100 signers. The propose method yielded equal error rate(EER) 4.38 % on skilled forgeries.