Neural network verification of dynamic signatures using pressure sensitive pen

Tham Heng Keit; P. Raveendran; Fumiaki Takeda; Yoshikazu Yoshida

Neural network verification of dynamic signatures using pressure sensitive pen

Tham Heng Keit, P. Raveendran, Fumiaki Takeda, Yoshikazu Yoshida

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

Abstract

In this paper, we present a technique to classify signatures produced by the pressure exerted on the pen tip. Before the features are exerted, a low pass filter using Sum Filter is designed to remove frequencies greater that 50 Hz. A new segmentation technique is used to divide the time series data into segments. The autoregressive (AR) coefficients are derived from each segment. From the coefficients, the power spectral density (PSD) is determined for every segment. Values from the spectral are then fed into a Multilayer Perceptron (MLP) classifier with one hidden layer for verification. A database of 1000 signatures is used for training and testing. The system is tested for genuine as well as forged signatures. The result obtained showed 2.13% error in rejecting genuine signatures and 3.40% error in accepting forged signatures.

Original language	English
Title of host publication	Proceedings of the 6th Joint Conference on Information Sciences, JCIS 2002
Editors	J.H. Caulfield, S.H. Chen, H.D. Cheng, R. Duro, J.H. Caufield, S.H. Chen, H.D. Cheng, R. Duro, V. Honavar
Pages	840-843
Number of pages	4
Publication status	Published - 2002
Externally published	Yes
Event	Joint Conference on Information Sciences 2002 - Research Triange Park, United States of America Duration: 8 Mar 2002 → 13 Mar 2002 Conference number: 6th

Publication series

Name	Proceedings of the Joint Conference on Information Sciences
Volume	6

Conference

Conference	Joint Conference on Information Sciences 2002
Abbreviated title	JCIS 2002
Country/Territory	United States of America
City	Research Triange Park
Period	8/03/02 → 13/03/02

Keywords

Burg's Autoregressive Model
Neural Networks
Signature Verification and Spectral Analysis

Cite this

Keit, T. H., Raveendran, P., Takeda, F., & Yoshida, Y. (2002). Neural network verification of dynamic signatures using pressure sensitive pen. In J. H. Caulfield, S. H. Chen, H. D. Cheng, R. Duro, J. H. Caufield, S. H. Chen, H. D. Cheng, R. Duro, & V. Honavar (Eds.), Proceedings of the 6th Joint Conference on Information Sciences, JCIS 2002 (pp. 840-843). (Proceedings of the Joint Conference on Information Sciences; Vol. 6).

Keit, Tham Heng ; Raveendran, P. ; Takeda, Fumiaki et al. / Neural network verification of dynamic signatures using pressure sensitive pen. Proceedings of the 6th Joint Conference on Information Sciences, JCIS 2002. editor / J.H. Caulfield ; S.H. Chen ; H.D. Cheng ; R. Duro ; J.H. Caufield ; S.H. Chen ; H.D. Cheng ; R. Duro ; V. Honavar. 2002. pp. 840-843 (Proceedings of the Joint Conference on Information Sciences).

@inproceedings{15a83fdc7327414582de859e366a9662,

title = "Neural network verification of dynamic signatures using pressure sensitive pen",

abstract = "In this paper, we present a technique to classify signatures produced by the pressure exerted on the pen tip. Before the features are exerted, a low pass filter using Sum Filter is designed to remove frequencies greater that 50 Hz. A new segmentation technique is used to divide the time series data into segments. The autoregressive (AR) coefficients are derived from each segment. From the coefficients, the power spectral density (PSD) is determined for every segment. Values from the spectral are then fed into a Multilayer Perceptron (MLP) classifier with one hidden layer for verification. A database of 1000 signatures is used for training and testing. The system is tested for genuine as well as forged signatures. The result obtained showed 2.13% error in rejecting genuine signatures and 3.40% error in accepting forged signatures.",

keywords = "Burg's Autoregressive Model, Neural Networks, Signature Verification and Spectral Analysis",

author = "Keit, {Tham Heng} and P. Raveendran and Fumiaki Takeda and Yoshikazu Yoshida",

year = "2002",

language = "English",

isbn = "0970789017",

series = "Proceedings of the Joint Conference on Information Sciences",

pages = "840--843",

editor = "J.H. Caulfield and S.H. Chen and H.D. Cheng and R. Duro and J.H. Caufield and S.H. Chen and H.D. Cheng and R. Duro and V. Honavar",

booktitle = "Proceedings of the 6th Joint Conference on Information Sciences, JCIS 2002",

note = "Joint Conference on Information Sciences 2002, JCIS 2002 ; Conference date: 08-03-2002 Through 13-03-2002",

}

Keit, TH, Raveendran, P, Takeda, F & Yoshida, Y 2002, Neural network verification of dynamic signatures using pressure sensitive pen. in JH Caulfield, SH Chen, HD Cheng, R Duro, JH Caufield, SH Chen, HD Cheng, R Duro & V Honavar (eds), Proceedings of the 6th Joint Conference on Information Sciences, JCIS 2002. Proceedings of the Joint Conference on Information Sciences, vol. 6, pp. 840-843, Joint Conference on Information Sciences 2002, Research Triange Park, North Carolina, United States of America, 8/03/02.

Neural network verification of dynamic signatures using pressure sensitive pen. / Keit, Tham Heng; Raveendran, P.; Takeda, Fumiaki et al.
Proceedings of the 6th Joint Conference on Information Sciences, JCIS 2002. ed. / J.H. Caulfield; S.H. Chen; H.D. Cheng; R. Duro; J.H. Caufield; S.H. Chen; H.D. Cheng; R. Duro; V. Honavar. 2002. p. 840-843 (Proceedings of the Joint Conference on Information Sciences; Vol. 6).

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

TY - GEN

T1 - Neural network verification of dynamic signatures using pressure sensitive pen

AU - Keit, Tham Heng

AU - Raveendran, P.

AU - Takeda, Fumiaki

AU - Yoshida, Yoshikazu

N1 - Conference code: 6th

PY - 2002

Y1 - 2002

N2 - In this paper, we present a technique to classify signatures produced by the pressure exerted on the pen tip. Before the features are exerted, a low pass filter using Sum Filter is designed to remove frequencies greater that 50 Hz. A new segmentation technique is used to divide the time series data into segments. The autoregressive (AR) coefficients are derived from each segment. From the coefficients, the power spectral density (PSD) is determined for every segment. Values from the spectral are then fed into a Multilayer Perceptron (MLP) classifier with one hidden layer for verification. A database of 1000 signatures is used for training and testing. The system is tested for genuine as well as forged signatures. The result obtained showed 2.13% error in rejecting genuine signatures and 3.40% error in accepting forged signatures.

AB - In this paper, we present a technique to classify signatures produced by the pressure exerted on the pen tip. Before the features are exerted, a low pass filter using Sum Filter is designed to remove frequencies greater that 50 Hz. A new segmentation technique is used to divide the time series data into segments. The autoregressive (AR) coefficients are derived from each segment. From the coefficients, the power spectral density (PSD) is determined for every segment. Values from the spectral are then fed into a Multilayer Perceptron (MLP) classifier with one hidden layer for verification. A database of 1000 signatures is used for training and testing. The system is tested for genuine as well as forged signatures. The result obtained showed 2.13% error in rejecting genuine signatures and 3.40% error in accepting forged signatures.

KW - Burg's Autoregressive Model

KW - Neural Networks

KW - Signature Verification and Spectral Analysis

UR - http://www.scopus.com/inward/record.url?scp=1642390003&partnerID=8YFLogxK

M3 - Conference Paper

AN - SCOPUS:1642390003

SN - 0970789017

T3 - Proceedings of the Joint Conference on Information Sciences

SP - 840

EP - 843

BT - Proceedings of the 6th Joint Conference on Information Sciences, JCIS 2002

A2 - Caulfield, J.H.

A2 - Chen, S.H.

A2 - Cheng, H.D.

A2 - Duro, R.

A2 - Caufield, J.H.

A2 - Chen, S.H.

A2 - Cheng, H.D.

A2 - Duro, R.

A2 - Honavar, V.

T2 - Joint Conference on Information Sciences 2002

Y2 - 8 March 2002 through 13 March 2002

ER -

Keit TH, Raveendran P, Takeda F, Yoshida Y. Neural network verification of dynamic signatures using pressure sensitive pen. In Caulfield JH, Chen SH, Cheng HD, Duro R, Caufield JH, Chen SH, Cheng HD, Duro R, Honavar V, editors, Proceedings of the 6th Joint Conference on Information Sciences, JCIS 2002. 2002. p. 840-843. (Proceedings of the Joint Conference on Information Sciences).

Neural network verification of dynamic signatures using pressure sensitive pen

Abstract

Publication series

Conference

Keywords

Other files and links

Cite this