Global Features for the Off-Line Signature Verification Problem

Vu Nguyen; Michael Blumenstein; Graham Leedham

doi:10.1109/ICDAR.2009.123

Global Features for the Off-Line Signature Verification Problem

Vu Nguyen, Michael Blumenstein, Graham Leedham

Computer Science

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

73 Citations (Scopus)

Abstract

Global features based on the boundary of a signature and its projections are described for enhancing the process of automated signature verification. The first global feature is derived from the total 'energy' a writer uses to create their signature. The second feature employs information from the vertical and horizontal projections of a signature, focusing on the proportion of the distance between key strokes in the image, and the height/width of the signature. The combination of these features with the Modified Direction Feature (MDF) and the ratio feature showed promising results for the off-line signature verification problem. When being trained using 12 genuine specimens and 400 random forgeries taken from a publicly available database, the Support Vector Machine (SVM) classifier obtained an average error rate (AER) of 17.25%. The false acceptance rate (FAR) for random forgeries was also kept as low as 0.08%.

Original language	English
Title of host publication	Proceedings of the 10th International Conference on Document Analysis and Recognition
Editors	Bob Werner
Place of Publication	Los Alamitos, United States of America
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	1300-1304
ISBN (Print)	9781424445004, 9780769537252
DOIs	https://doi.org/10.1109/ICDAR.2009.123
Publication status	Published - 2009
Event	ICDAR 2009: 10th International Conference on Document Analysis and Recognition - Barcelona, Spain Duration: 26 Jul 2009 → 29 Jul 2009

Conference

Conference	ICDAR 2009: 10th International Conference on Document Analysis and Recognition
City	Barcelona, Spain
Period	26/07/09 → 29/07/09

Keywords

Pattern Recognition and Data Mining
Computer Vision

Access to Document

10.1109/ICDAR.2009.123

https://hdl.handle.net/1959.11/9753

Handle.net

Persistent link

Cite this

@inproceedings{e295ef8f15ae44cdbd978d4006fc625e,

title = "Global Features for the Off-Line Signature Verification Problem",

abstract = "Global features based on the boundary of a signature and its projections are described for enhancing the process of automated signature verification. The first global feature is derived from the total 'energy' a writer uses to create their signature. The second feature employs information from the vertical and horizontal projections of a signature, focusing on the proportion of the distance between key strokes in the image, and the height/width of the signature. The combination of these features with the Modified Direction Feature (MDF) and the ratio feature showed promising results for the off-line signature verification problem. When being trained using 12 genuine specimens and 400 random forgeries taken from a publicly available database, the Support Vector Machine (SVM) classifier obtained an average error rate (AER) of 17.25\%. The false acceptance rate (FAR) for random forgeries was also kept as low as 0.08\%.",

keywords = "Pattern Recognition and Data Mining, Computer Vision",

author = "Vu Nguyen and Michael Blumenstein and Graham Leedham",

year = "2009",

doi = "10.1109/ICDAR.2009.123",

language = "English",

isbn = "9781424445004",

pages = "1300--1304",

editor = "Bob Werner",

booktitle = "Proceedings of the 10th International Conference on Document Analysis and Recognition",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

note = "ICDAR 2009: 10th International Conference on Document Analysis and Recognition ; Conference date: 26-07-2009 Through 29-07-2009",

}

Nguyen, V, Blumenstein, M & Leedham, G 2009, Global Features for the Off-Line Signature Verification Problem. in B Werner (ed.), Proceedings of the 10th International Conference on Document Analysis and Recognition. Institute of Electrical and Electronics Engineers (IEEE), Los Alamitos, United States of America, pp. 1300-1304, ICDAR 2009: 10th International Conference on Document Analysis and Recognition, Barcelona, Spain, 26/07/09. https://doi.org/10.1109/ICDAR.2009.123

Global Features for the Off-Line Signature Verification Problem. / Nguyen, Vu; Blumenstein, Michael; Leedham, Graham.
Proceedings of the 10th International Conference on Document Analysis and Recognition. ed. / Bob Werner. Los Alamitos, United States of America: Institute of Electrical and Electronics Engineers (IEEE), 2009. p. 1300-1304.

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

TY - GEN

T1 - Global Features for the Off-Line Signature Verification Problem

AU - Nguyen, Vu

AU - Blumenstein, Michael

AU - Leedham, Graham

PY - 2009

Y1 - 2009

N2 - Global features based on the boundary of a signature and its projections are described for enhancing the process of automated signature verification. The first global feature is derived from the total 'energy' a writer uses to create their signature. The second feature employs information from the vertical and horizontal projections of a signature, focusing on the proportion of the distance between key strokes in the image, and the height/width of the signature. The combination of these features with the Modified Direction Feature (MDF) and the ratio feature showed promising results for the off-line signature verification problem. When being trained using 12 genuine specimens and 400 random forgeries taken from a publicly available database, the Support Vector Machine (SVM) classifier obtained an average error rate (AER) of 17.25%. The false acceptance rate (FAR) for random forgeries was also kept as low as 0.08%.

AB - Global features based on the boundary of a signature and its projections are described for enhancing the process of automated signature verification. The first global feature is derived from the total 'energy' a writer uses to create their signature. The second feature employs information from the vertical and horizontal projections of a signature, focusing on the proportion of the distance between key strokes in the image, and the height/width of the signature. The combination of these features with the Modified Direction Feature (MDF) and the ratio feature showed promising results for the off-line signature verification problem. When being trained using 12 genuine specimens and 400 random forgeries taken from a publicly available database, the Support Vector Machine (SVM) classifier obtained an average error rate (AER) of 17.25%. The false acceptance rate (FAR) for random forgeries was also kept as low as 0.08%.

KW - Pattern Recognition and Data Mining

KW - Computer Vision

UR - http://www.cvc.uab.es/icdar2009/papers/3725b300.pdf

UR - https://www.scopus.com/pages/publications/71249104257

U2 - 10.1109/ICDAR.2009.123

DO - 10.1109/ICDAR.2009.123

M3 - Conference contribution

SN - 9781424445004

SN - 9780769537252

SP - 1300

EP - 1304

BT - Proceedings of the 10th International Conference on Document Analysis and Recognition

A2 - Werner, Bob

PB - Institute of Electrical and Electronics Engineers (IEEE)

CY - Los Alamitos, United States of America

T2 - ICDAR 2009: 10th International Conference on Document Analysis and Recognition

Y2 - 26 July 2009 through 29 July 2009

ER -

Global Features for the Off-Line Signature Verification Problem

Abstract

Conference

Keywords

Access to Document

Handle.net

Fingerprint

Cite this