Improvement of on-line signature verification based on gradient features

Yumiko Kawazoe, Wataru Oyama, Tetsushi Wakabayashi, Fumitaka Kimura

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

This paper proposes a new on-line signature verification technique which employs gradient features and a pooled within-covariance matrix of training samples not only of the user but also of the others. Gradient features are extracted from a signature image reflecting the velocity of pen movement as the grayscale so that both on-line and off-line features are exploited. All training samples of different signatures collected in design stage are pooled together with the user's samples and used for learning within-individual variation matrix to reduce required sample size of the user to minimum number. The result of evaluation test shows that the proposed technique improves the verification accuracy by 4.9% when user's sample of size three is pooled with samples with others. This result shows that the samples of different signatures are useful for training within-individual variation of a specific user.

Original languageEnglish
JournalIEEJ Transactions on Electronics, Information and Systems
Volume130
Issue number12
DOIs
Publication statusPublished - Jan 1 2010

Fingerprint

Covariance matrix

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Cite this

Improvement of on-line signature verification based on gradient features. / Kawazoe, Yumiko; Oyama, Wataru; Wakabayashi, Tetsushi; Kimura, Fumitaka.

In: IEEJ Transactions on Electronics, Information and Systems, Vol. 130, No. 12, 01.01.2010.

Research output: Contribution to journalArticle

Kawazoe, Yumiko ; Oyama, Wataru ; Wakabayashi, Tetsushi ; Kimura, Fumitaka. / Improvement of on-line signature verification based on gradient features. In: IEEJ Transactions on Electronics, Information and Systems. 2010 ; Vol. 130, No. 12.
@article{04c5ccf855fb41de9110ae60b50a13cc,
title = "Improvement of on-line signature verification based on gradient features",
abstract = "This paper proposes a new on-line signature verification technique which employs gradient features and a pooled within-covariance matrix of training samples not only of the user but also of the others. Gradient features are extracted from a signature image reflecting the velocity of pen movement as the grayscale so that both on-line and off-line features are exploited. All training samples of different signatures collected in design stage are pooled together with the user's samples and used for learning within-individual variation matrix to reduce required sample size of the user to minimum number. The result of evaluation test shows that the proposed technique improves the verification accuracy by 4.9{\%} when user's sample of size three is pooled with samples with others. This result shows that the samples of different signatures are useful for training within-individual variation of a specific user.",
author = "Yumiko Kawazoe and Wataru Oyama and Tetsushi Wakabayashi and Fumitaka Kimura",
year = "2010",
month = "1",
day = "1",
doi = "10.1541/ieejeiss.130.2142",
language = "English",
volume = "130",
journal = "IEEJ Transactions on Electronics, Information and Systems",
issn = "0385-4221",
publisher = "The Institute of Electrical Engineers of Japan",
number = "12",

}

TY - JOUR

T1 - Improvement of on-line signature verification based on gradient features

AU - Kawazoe, Yumiko

AU - Oyama, Wataru

AU - Wakabayashi, Tetsushi

AU - Kimura, Fumitaka

PY - 2010/1/1

Y1 - 2010/1/1

N2 - This paper proposes a new on-line signature verification technique which employs gradient features and a pooled within-covariance matrix of training samples not only of the user but also of the others. Gradient features are extracted from a signature image reflecting the velocity of pen movement as the grayscale so that both on-line and off-line features are exploited. All training samples of different signatures collected in design stage are pooled together with the user's samples and used for learning within-individual variation matrix to reduce required sample size of the user to minimum number. The result of evaluation test shows that the proposed technique improves the verification accuracy by 4.9% when user's sample of size three is pooled with samples with others. This result shows that the samples of different signatures are useful for training within-individual variation of a specific user.

AB - This paper proposes a new on-line signature verification technique which employs gradient features and a pooled within-covariance matrix of training samples not only of the user but also of the others. Gradient features are extracted from a signature image reflecting the velocity of pen movement as the grayscale so that both on-line and off-line features are exploited. All training samples of different signatures collected in design stage are pooled together with the user's samples and used for learning within-individual variation matrix to reduce required sample size of the user to minimum number. The result of evaluation test shows that the proposed technique improves the verification accuracy by 4.9% when user's sample of size three is pooled with samples with others. This result shows that the samples of different signatures are useful for training within-individual variation of a specific user.

UR - http://www.scopus.com/inward/record.url?scp=78951491481&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78951491481&partnerID=8YFLogxK

U2 - 10.1541/ieejeiss.130.2142

DO - 10.1541/ieejeiss.130.2142

M3 - Article

VL - 130

JO - IEEJ Transactions on Electronics, Information and Systems

JF - IEEJ Transactions on Electronics, Information and Systems

SN - 0385-4221

IS - 12

ER -