Optimal threshold selection for online verification of signature

A. Alizadeh, T. Alizadeh, Z. Daei

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

In this paper an innovative method for 1verification of signature using parametric features based on optimal threshold selection is proposed. For each signature, 62 parametric feature are derived from horizontal place, x(t), vertical place, y(t) and pen down and up signals which are obtained from a digitizer plane. The weighted distance between each feature of a signatories and the related reference features is compared to a suitable threshold value and then the feature is accepted or not. The number of the accepted features for a person is then compared to another threshold, which has a suitable value for each signature, and then the signature will be verified or rejected. In this research, 1500 original signatures from 30 person and 600 forgery signatures are used. For each person, 30 genuine and 10 forgery signatures are considered for training of the algorithm and the rest are used in testing and validation. It is shown in the results that there is 0.67% false rejection ratio and 0.67% false acceptation ratio for the training set and a 2.68% and 1.99% for the testing set, respectively.

Original languageEnglish
Title of host publicationProceedings of the International MultiConference of Engineers and Computer Scientists 2010, IMECS 2010
Pages98-102
Number of pages5
Publication statusPublished - 2010
Externally publishedYes
EventInternational MultiConference of Engineers and Computer Scientists 2010, IMECS 2010 - Kowloon, Hong Kong
Duration: Mar 17 2010Mar 19 2010

Other

OtherInternational MultiConference of Engineers and Computer Scientists 2010, IMECS 2010
CountryHong Kong
CityKowloon
Period3/17/103/19/10

Fingerprint

Testing

Keywords

  • Feature extraction
  • Online signature verification
  • Parametric features
  • Weighted Euclidean distance

ASJC Scopus subject areas

  • Computer Science (miscellaneous)

Cite this

Alizadeh, A., Alizadeh, T., & Daei, Z. (2010). Optimal threshold selection for online verification of signature. In Proceedings of the International MultiConference of Engineers and Computer Scientists 2010, IMECS 2010 (pp. 98-102)

Optimal threshold selection for online verification of signature. / Alizadeh, A.; Alizadeh, T.; Daei, Z.

Proceedings of the International MultiConference of Engineers and Computer Scientists 2010, IMECS 2010. 2010. p. 98-102.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Alizadeh, A, Alizadeh, T & Daei, Z 2010, Optimal threshold selection for online verification of signature. in Proceedings of the International MultiConference of Engineers and Computer Scientists 2010, IMECS 2010. pp. 98-102, International MultiConference of Engineers and Computer Scientists 2010, IMECS 2010, Kowloon, Hong Kong, 3/17/10.
Alizadeh A, Alizadeh T, Daei Z. Optimal threshold selection for online verification of signature. In Proceedings of the International MultiConference of Engineers and Computer Scientists 2010, IMECS 2010. 2010. p. 98-102
Alizadeh, A. ; Alizadeh, T. ; Daei, Z. / Optimal threshold selection for online verification of signature. Proceedings of the International MultiConference of Engineers and Computer Scientists 2010, IMECS 2010. 2010. pp. 98-102
@inproceedings{3af1997324c84663ac9fd3843a59f204,
title = "Optimal threshold selection for online verification of signature",
abstract = "In this paper an innovative method for 1verification of signature using parametric features based on optimal threshold selection is proposed. For each signature, 62 parametric feature are derived from horizontal place, x(t), vertical place, y(t) and pen down and up signals which are obtained from a digitizer plane. The weighted distance between each feature of a signatories and the related reference features is compared to a suitable threshold value and then the feature is accepted or not. The number of the accepted features for a person is then compared to another threshold, which has a suitable value for each signature, and then the signature will be verified or rejected. In this research, 1500 original signatures from 30 person and 600 forgery signatures are used. For each person, 30 genuine and 10 forgery signatures are considered for training of the algorithm and the rest are used in testing and validation. It is shown in the results that there is 0.67{\%} false rejection ratio and 0.67{\%} false acceptation ratio for the training set and a 2.68{\%} and 1.99{\%} for the testing set, respectively.",
keywords = "Feature extraction, Online signature verification, Parametric features, Weighted Euclidean distance",
author = "A. Alizadeh and T. Alizadeh and Z. Daei",
year = "2010",
language = "English",
isbn = "9789881701282",
pages = "98--102",
booktitle = "Proceedings of the International MultiConference of Engineers and Computer Scientists 2010, IMECS 2010",

}

TY - GEN

T1 - Optimal threshold selection for online verification of signature

AU - Alizadeh, A.

AU - Alizadeh, T.

AU - Daei, Z.

PY - 2010

Y1 - 2010

N2 - In this paper an innovative method for 1verification of signature using parametric features based on optimal threshold selection is proposed. For each signature, 62 parametric feature are derived from horizontal place, x(t), vertical place, y(t) and pen down and up signals which are obtained from a digitizer plane. The weighted distance between each feature of a signatories and the related reference features is compared to a suitable threshold value and then the feature is accepted or not. The number of the accepted features for a person is then compared to another threshold, which has a suitable value for each signature, and then the signature will be verified or rejected. In this research, 1500 original signatures from 30 person and 600 forgery signatures are used. For each person, 30 genuine and 10 forgery signatures are considered for training of the algorithm and the rest are used in testing and validation. It is shown in the results that there is 0.67% false rejection ratio and 0.67% false acceptation ratio for the training set and a 2.68% and 1.99% for the testing set, respectively.

AB - In this paper an innovative method for 1verification of signature using parametric features based on optimal threshold selection is proposed. For each signature, 62 parametric feature are derived from horizontal place, x(t), vertical place, y(t) and pen down and up signals which are obtained from a digitizer plane. The weighted distance between each feature of a signatories and the related reference features is compared to a suitable threshold value and then the feature is accepted or not. The number of the accepted features for a person is then compared to another threshold, which has a suitable value for each signature, and then the signature will be verified or rejected. In this research, 1500 original signatures from 30 person and 600 forgery signatures are used. For each person, 30 genuine and 10 forgery signatures are considered for training of the algorithm and the rest are used in testing and validation. It is shown in the results that there is 0.67% false rejection ratio and 0.67% false acceptation ratio for the training set and a 2.68% and 1.99% for the testing set, respectively.

KW - Feature extraction

KW - Online signature verification

KW - Parametric features

KW - Weighted Euclidean distance

UR - http://www.scopus.com/inward/record.url?scp=79952404986&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79952404986&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:79952404986

SN - 9789881701282

SP - 98

EP - 102

BT - Proceedings of the International MultiConference of Engineers and Computer Scientists 2010, IMECS 2010

ER -