The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Dans cet article, nous proposons une nouvelle stratégie à modèle unique basée sur un ensemble de modèles moyens et une déformation temporelle dynamique pondérée localement/globalement (LG-DTW) pour améliorer les performances de la vérification de signature en ligne. Plus précisément, lors de la phase d'inscription, nous mettons en œuvre une méthode de moyenne de séries chronologiques, la moyenne du barycentre DTW basée sur le barycentre euclidien, pour obtenir un ensemble de modèles moyens tenant compte de la variabilité intra-utilisateur parmi les échantillons de référence. Ensuite, nous acquérons une estimation de pondération locale en considérant une séquence de stabilité locale obtenue en analysant plusieurs points de correspondance d'une correspondance optimale entre le modèle moyen et les ensembles de référence. Par la suite, nous obtenons une estimation de pondération globale basée sur l'importance variable estimée par gradient boosting. Enfin, dans la phase de vérification, nous appliquons des méthodes de pondération locale et globale pour acquérir une distance LG-DTW discriminante entre l'ensemble de modèles moyens et un échantillon de requête. Les résultats expérimentaux obtenus sur les ensembles de données de signature publics SVC2004 Task2 et MCYT-100 confirment l'efficacité de la méthode proposée pour la vérification des signatures en ligne.
Manabu OKAWA
Metropolitan Police Department
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Manabu OKAWA, "Online Signature Verification Using Single-Template Matching Through Locally and Globally Weighted Dynamic Time Warping" in IEICE TRANSACTIONS on Information,
vol. E103-D, no. 12, pp. 2701-2708, December 2020, doi: 10.1587/transinf.2020EDP7099.
Abstract: In this paper, we propose a novel single-template strategy based on a mean template set and locally/globally weighted dynamic time warping (LG-DTW) to improve the performance of online signature verification. Specifically, in the enrollment phase, we implement a time series averaging method, Euclidean barycenter-based DTW barycenter averaging, to obtain a mean template set considering intra-user variability among reference samples. Then, we acquire a local weighting estimate considering a local stability sequence that is obtained analyzing multiple matching points of an optimal match between the mean template and reference sets. Thereafter, we derive a global weighting estimate based on the variable importance estimated by gradient boosting. Finally, in the verification phase, we apply both local and global weighting methods to acquire a discriminative LG-DTW distance between the mean template set and a query sample. Experimental results obtained on the public SVC2004 Task2 and MCYT-100 signature datasets confirm the effectiveness of the proposed method for online signature verification.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2020EDP7099/_p
Copier
@ARTICLE{e103-d_12_2701,
author={Manabu OKAWA, },
journal={IEICE TRANSACTIONS on Information},
title={Online Signature Verification Using Single-Template Matching Through Locally and Globally Weighted Dynamic Time Warping},
year={2020},
volume={E103-D},
number={12},
pages={2701-2708},
abstract={In this paper, we propose a novel single-template strategy based on a mean template set and locally/globally weighted dynamic time warping (LG-DTW) to improve the performance of online signature verification. Specifically, in the enrollment phase, we implement a time series averaging method, Euclidean barycenter-based DTW barycenter averaging, to obtain a mean template set considering intra-user variability among reference samples. Then, we acquire a local weighting estimate considering a local stability sequence that is obtained analyzing multiple matching points of an optimal match between the mean template and reference sets. Thereafter, we derive a global weighting estimate based on the variable importance estimated by gradient boosting. Finally, in the verification phase, we apply both local and global weighting methods to acquire a discriminative LG-DTW distance between the mean template set and a query sample. Experimental results obtained on the public SVC2004 Task2 and MCYT-100 signature datasets confirm the effectiveness of the proposed method for online signature verification.},
keywords={},
doi={10.1587/transinf.2020EDP7099},
ISSN={1745-1361},
month={December},}
Copier
TY - JOUR
TI - Online Signature Verification Using Single-Template Matching Through Locally and Globally Weighted Dynamic Time Warping
T2 - IEICE TRANSACTIONS on Information
SP - 2701
EP - 2708
AU - Manabu OKAWA
PY - 2020
DO - 10.1587/transinf.2020EDP7099
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E103-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2020
AB - In this paper, we propose a novel single-template strategy based on a mean template set and locally/globally weighted dynamic time warping (LG-DTW) to improve the performance of online signature verification. Specifically, in the enrollment phase, we implement a time series averaging method, Euclidean barycenter-based DTW barycenter averaging, to obtain a mean template set considering intra-user variability among reference samples. Then, we acquire a local weighting estimate considering a local stability sequence that is obtained analyzing multiple matching points of an optimal match between the mean template and reference sets. Thereafter, we derive a global weighting estimate based on the variable importance estimated by gradient boosting. Finally, in the verification phase, we apply both local and global weighting methods to acquire a discriminative LG-DTW distance between the mean template set and a query sample. Experimental results obtained on the public SVC2004 Task2 and MCYT-100 signature datasets confirm the effectiveness of the proposed method for online signature verification.
ER -