ICDAR 2013 competitions on signature verification and writer identification for on- and offline skilled forgeries (SigWiComp 2013)

Muhammad Imran Malik, Marcus Liwicki, Linda Alewijnse, Wataru Ohyama, Michael Blumenstein, Bryan Found

研究成果: ジャーナルへの寄稿Conference article

56 引用 (Scopus)

抄録

This paper presents the results of the ICDAR2013 competitions on signature verification and writer identification for on- and offline skilled forgeries jointly organized by PR researchers and Forensic Handwriting Examiners (FHEs). The aim is to bridge the gap between recent technological developments and forensic casework. Two modalities (signatures, and handwritten text) are considered where training and evaluation data (in Dutch and Japanese) were collected and provided by FHEs and PR-researchers. Four tasks were defined where the systems had to perform Dutch offline signature verification, Japanese offline signature verification, Japanese online signature verification, and Dutch writer identification. The participants of the signatures modality were motivated to report their results in Likelihood Ratios (LR). This has made the systems even more interesting for application in forensic casework. For evaluation of signatures modality, we used both the traditional Equal Error Rate (EER) and forensically substantial Cost of Log Likelihood Ratios (Cllr). The system having the smallest value of the Minimum Cost of Log Likelihood Ratio (Cllrmin) is declared winner. For evaluation of the handwritten text modality, we used the precision and accuracy measures and winners are announced on the basis of best F-measure value.

元の言語英語
記事番号6628858
ページ(範囲)1477-1483
ページ数7
ジャーナルProceedings of the International Conference on Document Analysis and Recognition, ICDAR
DOI
出版物ステータス出版済み - 12 11 2013
イベント12th International Conference on Document Analysis and Recognition, ICDAR 2013 - Washington, DC, 米国
継続期間: 8 25 20138 28 2013

Fingerprint

Costs

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

これを引用

ICDAR 2013 competitions on signature verification and writer identification for on- and offline skilled forgeries (SigWiComp 2013). / Malik, Muhammad Imran; Liwicki, Marcus; Alewijnse, Linda; Ohyama, Wataru; Blumenstein, Michael; Found, Bryan.

:: Proceedings of the International Conference on Document Analysis and Recognition, ICDAR, 11.12.2013, p. 1477-1483.

研究成果: ジャーナルへの寄稿Conference article

Malik, Muhammad Imran ; Liwicki, Marcus ; Alewijnse, Linda ; Ohyama, Wataru ; Blumenstein, Michael ; Found, Bryan. / ICDAR 2013 competitions on signature verification and writer identification for on- and offline skilled forgeries (SigWiComp 2013). :: Proceedings of the International Conference on Document Analysis and Recognition, ICDAR. 2013 ; pp. 1477-1483.
@article{4314b278ff9a409d86ab4e8b7dcb6ef1,
title = "ICDAR 2013 competitions on signature verification and writer identification for on- and offline skilled forgeries (SigWiComp 2013)",
abstract = "This paper presents the results of the ICDAR2013 competitions on signature verification and writer identification for on- and offline skilled forgeries jointly organized by PR researchers and Forensic Handwriting Examiners (FHEs). The aim is to bridge the gap between recent technological developments and forensic casework. Two modalities (signatures, and handwritten text) are considered where training and evaluation data (in Dutch and Japanese) were collected and provided by FHEs and PR-researchers. Four tasks were defined where the systems had to perform Dutch offline signature verification, Japanese offline signature verification, Japanese online signature verification, and Dutch writer identification. The participants of the signatures modality were motivated to report their results in Likelihood Ratios (LR). This has made the systems even more interesting for application in forensic casework. For evaluation of signatures modality, we used both the traditional Equal Error Rate (EER) and forensically substantial Cost of Log Likelihood Ratios (Cllr). The system having the smallest value of the Minimum Cost of Log Likelihood Ratio (Cllrmin) is declared winner. For evaluation of the handwritten text modality, we used the precision and accuracy measures and winners are announced on the basis of best F-measure value.",
author = "Malik, {Muhammad Imran} and Marcus Liwicki and Linda Alewijnse and Wataru Ohyama and Michael Blumenstein and Bryan Found",
year = "2013",
month = "12",
day = "11",
doi = "10.1109/ICDAR.2013.220",
language = "English",
pages = "1477--1483",
journal = "Proceedings of the International Conference on Document Analysis and Recognition, ICDAR",
issn = "1520-5363",

}

TY - JOUR

T1 - ICDAR 2013 competitions on signature verification and writer identification for on- and offline skilled forgeries (SigWiComp 2013)

AU - Malik, Muhammad Imran

AU - Liwicki, Marcus

AU - Alewijnse, Linda

AU - Ohyama, Wataru

AU - Blumenstein, Michael

AU - Found, Bryan

PY - 2013/12/11

Y1 - 2013/12/11

N2 - This paper presents the results of the ICDAR2013 competitions on signature verification and writer identification for on- and offline skilled forgeries jointly organized by PR researchers and Forensic Handwriting Examiners (FHEs). The aim is to bridge the gap between recent technological developments and forensic casework. Two modalities (signatures, and handwritten text) are considered where training and evaluation data (in Dutch and Japanese) were collected and provided by FHEs and PR-researchers. Four tasks were defined where the systems had to perform Dutch offline signature verification, Japanese offline signature verification, Japanese online signature verification, and Dutch writer identification. The participants of the signatures modality were motivated to report their results in Likelihood Ratios (LR). This has made the systems even more interesting for application in forensic casework. For evaluation of signatures modality, we used both the traditional Equal Error Rate (EER) and forensically substantial Cost of Log Likelihood Ratios (Cllr). The system having the smallest value of the Minimum Cost of Log Likelihood Ratio (Cllrmin) is declared winner. For evaluation of the handwritten text modality, we used the precision and accuracy measures and winners are announced on the basis of best F-measure value.

AB - This paper presents the results of the ICDAR2013 competitions on signature verification and writer identification for on- and offline skilled forgeries jointly organized by PR researchers and Forensic Handwriting Examiners (FHEs). The aim is to bridge the gap between recent technological developments and forensic casework. Two modalities (signatures, and handwritten text) are considered where training and evaluation data (in Dutch and Japanese) were collected and provided by FHEs and PR-researchers. Four tasks were defined where the systems had to perform Dutch offline signature verification, Japanese offline signature verification, Japanese online signature verification, and Dutch writer identification. The participants of the signatures modality were motivated to report their results in Likelihood Ratios (LR). This has made the systems even more interesting for application in forensic casework. For evaluation of signatures modality, we used both the traditional Equal Error Rate (EER) and forensically substantial Cost of Log Likelihood Ratios (Cllr). The system having the smallest value of the Minimum Cost of Log Likelihood Ratio (Cllrmin) is declared winner. For evaluation of the handwritten text modality, we used the precision and accuracy measures and winners are announced on the basis of best F-measure value.

UR - http://www.scopus.com/inward/record.url?scp=84889607928&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84889607928&partnerID=8YFLogxK

U2 - 10.1109/ICDAR.2013.220

DO - 10.1109/ICDAR.2013.220

M3 - Conference article

AN - SCOPUS:84889607928

SP - 1477

EP - 1483

JO - Proceedings of the International Conference on Document Analysis and Recognition, ICDAR

JF - Proceedings of the International Conference on Document Analysis and Recognition, ICDAR

SN - 1520-5363

M1 - 6628858

ER -