Threshold Equalization for On-Line Signature Verification

In on-line signature verification, complexity of signature shape can influence the value of the optimal threshold for individual signatures. Writer-dependent threshold selection has been proposed but it requires forgery data. It is not easy to collect such forgery data in practical applications. Therefore, some threshold equalization method using only genuine data is needed. In this letter, we propose three different threshold equalization methods based on the complexity of signature. Their effectiveness is confirmed in experiments using a multi-matcher DWT on-line signature verification system.

[1]  Yutaka Fukui,et al.  DWT Domain On-Line Signature Verification Using the Pen-Movement Vector , 2006, IEICE Trans. Fundam. Electron. Commun. Comput. Sci..

[2]  Sargur N. Srihari,et al.  On-Line and Off-Line Handwriting Recognition: A Comprehensive Survey , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  I. Nakanishi,et al.  Parameter Fusion in DWT Domain On-Line Signature Verification , 2006, 2006 International Symposium on Intelligent Signal Processing and Communications.

[4]  Arun Ross,et al.  Handbook of Multibiometrics , 2006, The Kluwer international series on biometrics.

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

[6]  Julian Fiérrez,et al.  Target dependent score normalization techniques and their application to signature verification , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[7]  Yutaka Fukui,et al.  Multi-matcher on-line signature verification system in DWT domain , 2005, ICASSP.

[8]  Sebastiano Impedovo,et al.  Recent advancements in automatic signature verification , 2004, Ninth International Workshop on Frontiers in Handwriting Recognition.

[9]  Julian Fiérrez,et al.  Target dependent score normalization techniques and their application to signature verification , 2005, IEEE Trans. Syst. Man Cybern. Part C.