Neural Network-based Hwritten Signature Verification

Handwritten signatures are considered as the most natural method of authenticating a person’s identity (compared to other biometric and cryptographic forms of authentication). The learning process inherent in Neural Networks (NN) can be applied to the process of verifying handwritten signatures that are electronically captured via a stylus. This paper presents a method for verifying handwritten signatures by using a NN architecture. Various static (e.g., height, slant, etc.) and dynamic (e.g., velocity, pen tip pressure, etc.) signature features are extracted and used to train the NN. Several Network topologies are tested and their accuracy is compared. The resulting system performs reasonably well with an overall error rate of 3:3% being reported for the best case.

[1]  Louis Vuurpijl,et al.  Coarse writing-style clustering based on simple stroke-related features. , 1996 .

[2]  Dexin Zhang,et al.  Personal Identification Based on Iris Texture Analysis , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  K. P. Zimmermann,et al.  Handwriter identification from one-bit quantized pressure patterns , 1985, Pattern Recognit..

[4]  W. L. Woo,et al.  Blind Source Separation of Postnonlinear Convolutive Mixture , 2007, IEEE Transactions on Audio, Speech, and Language Processing.

[5]  S.J. Elliott,et al.  Keystroke Dynamics Verification Using a Spontaneously Generated Password , 2006, Proceedings 40th Annual 2006 International Carnahan Conference on Security Technology.

[6]  Graham Leedham,et al.  Signature Verification by Neural Networks with Selective Attention , 2004, Applied Intelligence.

[7]  Emile H. L. Aarts,et al.  On-line signature verification with hidden Markov models , 1998, Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170).

[8]  D. Z. Lejtman,et al.  On-line handwritten signature verification using wavelets and back-propagation neural networks , 2001, Proceedings of Sixth International Conference on Document Analysis and Recognition.

[9]  Yoshua Bengio,et al.  LeRec: A NN/HMM Hybrid for On-Line Handwriting Recognition , 1995, Neural Computation.

[10]  Wai Lok Woo,et al.  Blind Source Separation of Postnonlinear Convolutive Mixture , 2007, IEEE Transactions on Audio, Speech, and Language Processing.

[11]  Tran Huy Dat,et al.  Heart sound as a biometric , 2008, Pattern Recognit..

[12]  Réjean Plamondon,et al.  The Design of An On-Line Signature Verification System: From Theory to Practice , 1994, Int. J. Pattern Recognit. Artif. Intell..

[13]  Ali Zilouchian,et al.  FUNDAMENTALS OF NEURAL NETWORKS , 2001 .

[14]  Hewitt D. Crane,et al.  Automatic signature verification using a three-axis force-sensitive pen , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[15]  P. GALLINARI,et al.  On the relations between discriminant analysis and multilayer perceptrons , 1991, Neural Networks.

[16]  Vassilis Anastassopoulos,et al.  Methods for writer identification , 1996, Proceedings of Third International Conference on Electronics, Circuits, and Systems.

[17]  Jarrod Trevathan,et al.  Implementation and Analysis of a Handwritten Signature Verification Technique , 2007, SECRYPT.

[18]  Jinhai Cai,et al.  Integration of structural and statistical information for unconstrained handwritten numeral recognition , 1998, Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170).

[19]  Wai Lok Woo,et al.  Regularised nonlinear blind signal separation using sparsely connected network , 2005 .