Verification of Static Signatures using Dynamic Time Warping on Features from High Pressure Points

Ruben Acosta-Velasquez; Leonardo Espinosa-Leal; Alexander Garcia-Perez; Kaj-Mikael Björk

doi:10.1007/978-3-031-21678-7_10

Verification of Static Signatures using Dynamic Time Warping on Features from High Pressure Points

Ruben Acosta-Velasquez, Leonardo Espinosa-Leal^*, Alexander Garcia-Perez, Kaj-Mikael Björk

^*Corresponding author for this work

Not published at VTT

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

Abstract

In this paper, we present a novel methodology for the classification of static handwritten signatures. We extract features from each user’s high-pressure points by filtering the skeletonized-binarized digital signatures at seven different thresholds. We compare the sequences obtained using the Dynamic Time Warping (DTW) algorithm with five metrics for the x and y axes. The resulting distances are used as features in a binary dataset of genuine-genuine and genuine-forgery signatures with fourteen features. We train and compare three classifiers: Random Forest (RF), extreme gradient boosting (XGBoost), and Extreme Learning Machines (ELM) on the processed data from the MCYT-75 dataset. Our results show that all models perform with similar accuracy, where the Euclidean and Manhattan metrics perform the best.

Original language	English
Title of host publication	Proceedings of ELM 2021
Subtitle of host publication	Theory, Algorithms and Applications
Editors	Kaj-Mikael Björk
Place of Publication	Cham
Publisher	Springer
Pages	104-113
ISBN (Electronic)	978-3-031-21678-7
ISBN (Print)	978-3-031-21677-0, 978-3-031-21680-0
DOIs	https://doi.org/10.1007/978-3-031-21678-7_10
Publication status	Published - 2023
MoE publication type	A4 Article in a conference publication
Event	11th International Conference on Extreme Learning Machines (ELM2021) - On-line, Helsinki, Finland Duration: 15 Dec 2021 → 16 Dec 2021 Conference number: 11 https://risklab.fi/events/

Publication series

Series	Proceedings in Adaptation, Learning and Optimization
Volume	16
ISSN	2363-6084

Conference

Conference	11th International Conference on Extreme Learning Machines (ELM2021)
Abbreviated title	ELM2021
Country/Territory	Finland
City	Helsinki
Period	15/12/21 → 16/12/21
Internet address	https://risklab.fi/events/

Access to Document

10.1007/978-3-031-21678-7_10

Cite this

Acosta-Velasquez, Ruben ; Espinosa-Leal, Leonardo ; Garcia-Perez, Alexander et al. / Verification of Static Signatures using Dynamic Time Warping on Features from High Pressure Points. Proceedings of ELM 2021: Theory, Algorithms and Applications. editor / Kaj-Mikael Björk. Cham : Springer, 2023. pp. 104-113 (Proceedings in Adaptation, Learning and Optimization, Vol. 16).

@inproceedings{3edebbedd27d48608971143f4f1b8e31,

title = "Verification of Static Signatures using Dynamic Time Warping on Features from High Pressure Points",

abstract = "In this paper, we present a novel methodology for the classification of static handwritten signatures. We extract features from each user{\textquoteright}s high-pressure points by filtering the skeletonized-binarized digital signatures at seven different thresholds. We compare the sequences obtained using the Dynamic Time Warping (DTW) algorithm with five metrics for the x and y axes. The resulting distances are used as features in a binary dataset of genuine-genuine and genuine-forgery signatures with fourteen features. We train and compare three classifiers: Random Forest (RF), extreme gradient boosting (XGBoost), and Extreme Learning Machines (ELM) on the processed data from the MCYT-75 dataset. Our results show that all models perform with similar accuracy, where the Euclidean and Manhattan metrics perform the best.",

author = "Ruben Acosta-Velasquez and Leonardo Espinosa-Leal and Alexander Garcia-Perez and Kaj-Mikael Bj{\"o}rk",

year = "2023",

doi = "10.1007/978-3-031-21678-7\_10",

language = "English",

isbn = "978-3-031-21677-0",

series = "Proceedings in Adaptation, Learning and Optimization",

publisher = "Springer",

pages = "104--113",

editor = "Kaj-Mikael Bj{\"o}rk",

booktitle = "Proceedings of ELM 2021",

address = "Germany",

note = "11th International Conference on Extreme Learning Machines (ELM2021), ELM2021 ; Conference date: 15-12-2021 Through 16-12-2021",

url = "https://risklab.fi/events/",

}

Acosta-Velasquez, R, Espinosa-Leal, L, Garcia-Perez, A & Björk, K-M 2023, Verification of Static Signatures using Dynamic Time Warping on Features from High Pressure Points. in K-M Björk (ed.), Proceedings of ELM 2021: Theory, Algorithms and Applications. Springer, Cham, Proceedings in Adaptation, Learning and Optimization, vol. 16, pp. 104-113, 11th International Conference on Extreme Learning Machines (ELM2021), Helsinki, Finland, 15/12/21. https://doi.org/10.1007/978-3-031-21678-7_10

Verification of Static Signatures using Dynamic Time Warping on Features from High Pressure Points. / Acosta-Velasquez, Ruben; Espinosa-Leal, Leonardo; Garcia-Perez, Alexander et al.
Proceedings of ELM 2021: Theory, Algorithms and Applications. ed. / Kaj-Mikael Björk. Cham: Springer, 2023. p. 104-113 (Proceedings in Adaptation, Learning and Optimization, Vol. 16).

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - Verification of Static Signatures using Dynamic Time Warping on Features from High Pressure Points

AU - Acosta-Velasquez, Ruben

AU - Espinosa-Leal, Leonardo

AU - Garcia-Perez, Alexander

AU - Björk, Kaj-Mikael

N1 - Conference code: 11

PY - 2023

Y1 - 2023

N2 - In this paper, we present a novel methodology for the classification of static handwritten signatures. We extract features from each user’s high-pressure points by filtering the skeletonized-binarized digital signatures at seven different thresholds. We compare the sequences obtained using the Dynamic Time Warping (DTW) algorithm with five metrics for the x and y axes. The resulting distances are used as features in a binary dataset of genuine-genuine and genuine-forgery signatures with fourteen features. We train and compare three classifiers: Random Forest (RF), extreme gradient boosting (XGBoost), and Extreme Learning Machines (ELM) on the processed data from the MCYT-75 dataset. Our results show that all models perform with similar accuracy, where the Euclidean and Manhattan metrics perform the best.

AB - In this paper, we present a novel methodology for the classification of static handwritten signatures. We extract features from each user’s high-pressure points by filtering the skeletonized-binarized digital signatures at seven different thresholds. We compare the sequences obtained using the Dynamic Time Warping (DTW) algorithm with five metrics for the x and y axes. The resulting distances are used as features in a binary dataset of genuine-genuine and genuine-forgery signatures with fourteen features. We train and compare three classifiers: Random Forest (RF), extreme gradient boosting (XGBoost), and Extreme Learning Machines (ELM) on the processed data from the MCYT-75 dataset. Our results show that all models perform with similar accuracy, where the Euclidean and Manhattan metrics perform the best.

U2 - 10.1007/978-3-031-21678-7_10

DO - 10.1007/978-3-031-21678-7_10

M3 - Conference article in proceedings

SN - 978-3-031-21677-0

SN - 978-3-031-21680-0

T3 - Proceedings in Adaptation, Learning and Optimization

SP - 104

EP - 113

BT - Proceedings of ELM 2021

A2 - Björk, Kaj-Mikael

PB - Springer

CY - Cham

T2 - 11th International Conference on Extreme Learning Machines (ELM2021)

Y2 - 15 December 2021 through 16 December 2021

ER -

Acosta-Velasquez R, Espinosa-Leal L, Garcia-Perez A, Björk KM. Verification of Static Signatures using Dynamic Time Warping on Features from High Pressure Points. In Björk KM, editor, Proceedings of ELM 2021: Theory, Algorithms and Applications. Cham: Springer. 2023. p. 104-113. (Proceedings in Adaptation, Learning and Optimization, Vol. 16). doi: 10.1007/978-3-031-21678-7_10

Verification of Static Signatures using Dynamic Time Warping on Features from High Pressure Points

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this