Spectrum Analysis Based onWindows with Variable Widths for Online Signature Verification

In this paper, an online signature verification scheme based on spectrum analysis and Mahalanobis decision is proposed. We firstly divided signatures to a number of frames with variable widths according to the characteristics of the time sequences, and then employed the fast Fourier transformation (FFT) to extract the spectrum of signatures. The distance between the Fourier coefficient within the corresponding frames is computed, and the Mahalanobis decision making is employed. Experimentation demonstrates that spectrum analysis based on windows with variable widths is effective for online signature signals

[1]  Juan J. Igarza,et al.  MCYT baseline corpus: a bimodal biometric database , 2003 .

[2]  Anil K. Jain,et al.  On-line signature verification, , 2002, Pattern Recognit..

[3]  Réjean Plamondon,et al.  Automatic signature verification and writer identification - the state of the art , 1989, Pattern Recognit..

[4]  Wu Zhong.  International Trends of Pattern Recognition Research A Brief Introduction to the 18th International Conference on Pattern Recognition , 2006 .

[5]  Suh-Yin Lee,et al.  On-line signature verification using LPC cepstrum and neural networks , 1997, IEEE Trans. Syst. Man Cybern. Part B.

[6]  Suh-Yin Lee,et al.  On-line signature verification based on logarithmic spectrum , 1998, Pattern Recognit..

[7]  K. Zimmermann,et al.  Signature recognition through spectral analysis , 1987, ICASSP '87. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[8]  Ronny Martens,et al.  On-line signature verification by dynamic time-warping , 1996, Proceedings of 13th International Conference on Pattern Recognition.