Sign H3re: Symbol and X-Mark Writer Identification Using Audio and Motion Data from a Digital Pen

Publikation: Beitrag in Buch/Bericht/Sammelwerk/KonferenzbandAufsatz in KonferenzbandForschungPeer-Review

Autoren

  • Maximilian Schrapel
  • Dennis Grannemann
  • Michael Rohs
Forschungs-netzwerk anzeigen

Details

OriginalspracheEnglisch
Titel des SammelwerksMensch und Computer 2022
UntertitelFacing Realities, MuC 2022 - Proceedings
Herausgeber/-innenMax Muhlhauser, Christian Reuter, Bastian Pfleging, Thomas Kosch, Andrii Matviienko, Kathrin Gerling, Sven Mayer, Wilko Heuten, Tanja Doring
Herausgeber (Verlag)Association for Computing Machinery (ACM)
Seiten209-218
Seitenumfang10
ISBN (elektronisch)9781450396905
PublikationsstatusVeröffentlicht - 15 Sept. 2022
Veranstaltung2022 Mensch und Computer Conference: Facing Realities, MuC 2022 - 2022 Conference on Humans and Computers, MuC 2022 - Darmstadt, Deutschland
Dauer: 4 Sept. 20227 Sept. 2022

Publikationsreihe

NameACM International Conference Proceeding Series

Abstract

Although in many cases contracts can be made or ended digitally, laws require handwritten signatures in certain cases. Forgeries are a major challenge with digital contracts, as their validity is not always immediately apparent without forensic methods. Illiteracy or disabilities may result in a person being unable to write their full name. In this case x-mark signatures are used, which require a witness for validity. In cases of suspected fraud, the relationship of the witnesses must be questioned, which involves a great amount of effort. In this paper we use audio and motion data from a digital pen to identify users via handwritten symbols. We evaluated the performance our approach for 19 symbols in a study with 30 participants. We found that x-marks offer fewer individual features than other symbols like arrows or circles. By training on three samples and averaging three predictions we reach a mean F1-score of F1 = 0.87, using statistical and spectral features fed into SVMs.

ASJC Scopus Sachgebiete

Zitieren

Sign H3re: Symbol and X-Mark Writer Identification Using Audio and Motion Data from a Digital Pen. / Schrapel, Maximilian; Grannemann, Dennis; Rohs, Michael.
Mensch und Computer 2022: Facing Realities, MuC 2022 - Proceedings. Hrsg. / Max Muhlhauser; Christian Reuter; Bastian Pfleging; Thomas Kosch; Andrii Matviienko; Kathrin Gerling; Sven Mayer; Wilko Heuten; Tanja Doring. Association for Computing Machinery (ACM), 2022. S. 209-218 (ACM International Conference Proceeding Series).

Publikation: Beitrag in Buch/Bericht/Sammelwerk/KonferenzbandAufsatz in KonferenzbandForschungPeer-Review

Schrapel, M, Grannemann, D & Rohs, M 2022, Sign H3re: Symbol and X-Mark Writer Identification Using Audio and Motion Data from a Digital Pen. in M Muhlhauser, C Reuter, B Pfleging, T Kosch, A Matviienko, K Gerling, S Mayer, W Heuten & T Doring (Hrsg.), Mensch und Computer 2022: Facing Realities, MuC 2022 - Proceedings. ACM International Conference Proceeding Series, Association for Computing Machinery (ACM), S. 209-218, 2022 Mensch und Computer Conference: Facing Realities, MuC 2022 - 2022 Conference on Humans and Computers, MuC 2022, Darmstadt, Deutschland, 4 Sept. 2022. https://doi.org/10.1145/3543758.3543764
Schrapel, M., Grannemann, D., & Rohs, M. (2022). Sign H3re: Symbol and X-Mark Writer Identification Using Audio and Motion Data from a Digital Pen. In M. Muhlhauser, C. Reuter, B. Pfleging, T. Kosch, A. Matviienko, K. Gerling, S. Mayer, W. Heuten, & T. Doring (Hrsg.), Mensch und Computer 2022: Facing Realities, MuC 2022 - Proceedings (S. 209-218). (ACM International Conference Proceeding Series). Association for Computing Machinery (ACM). https://doi.org/10.1145/3543758.3543764
Schrapel M, Grannemann D, Rohs M. Sign H3re: Symbol and X-Mark Writer Identification Using Audio and Motion Data from a Digital Pen. in Muhlhauser M, Reuter C, Pfleging B, Kosch T, Matviienko A, Gerling K, Mayer S, Heuten W, Doring T, Hrsg., Mensch und Computer 2022: Facing Realities, MuC 2022 - Proceedings. Association for Computing Machinery (ACM). 2022. S. 209-218. (ACM International Conference Proceeding Series). doi: 10.1145/3543758.3543764
Schrapel, Maximilian ; Grannemann, Dennis ; Rohs, Michael. / Sign H3re : Symbol and X-Mark Writer Identification Using Audio and Motion Data from a Digital Pen. Mensch und Computer 2022: Facing Realities, MuC 2022 - Proceedings. Hrsg. / Max Muhlhauser ; Christian Reuter ; Bastian Pfleging ; Thomas Kosch ; Andrii Matviienko ; Kathrin Gerling ; Sven Mayer ; Wilko Heuten ; Tanja Doring. Association for Computing Machinery (ACM), 2022. S. 209-218 (ACM International Conference Proceeding Series).
Download
@inproceedings{4e5f822999db4dd9b1f4fd73f7cae189,
title = "Sign H3re: Symbol and X-Mark Writer Identification Using Audio and Motion Data from a Digital Pen",
abstract = "Although in many cases contracts can be made or ended digitally, laws require handwritten signatures in certain cases. Forgeries are a major challenge with digital contracts, as their validity is not always immediately apparent without forensic methods. Illiteracy or disabilities may result in a person being unable to write their full name. In this case x-mark signatures are used, which require a witness for validity. In cases of suspected fraud, the relationship of the witnesses must be questioned, which involves a great amount of effort. In this paper we use audio and motion data from a digital pen to identify users via handwritten symbols. We evaluated the performance our approach for 19 symbols in a study with 30 participants. We found that x-marks offer fewer individual features than other symbols like arrows or circles. By training on three samples and averaging three predictions we reach a mean F1-score of F1 = 0.87, using statistical and spectral features fed into SVMs.",
keywords = "accessibility, digital pens, handwriting recognition, motor impairments, pattern recognition, signature authentication, signing documents",
author = "Maximilian Schrapel and Dennis Grannemann and Michael Rohs",
year = "2022",
month = sep,
day = "15",
doi = "10.1145/3543758.3543764",
language = "English",
series = "ACM International Conference Proceeding Series",
publisher = "Association for Computing Machinery (ACM)",
pages = "209--218",
editor = "Max Muhlhauser and Christian Reuter and Bastian Pfleging and Thomas Kosch and Andrii Matviienko and Kathrin Gerling and Sven Mayer and Wilko Heuten and Tanja Doring",
booktitle = "Mensch und Computer 2022",
address = "United States",
note = "2022 Mensch und Computer Conference: Facing Realities, MuC 2022 - 2022 Conference on Humans and Computers, MuC 2022 ; Conference date: 04-09-2022 Through 07-09-2022",

}

Download

TY - GEN

T1 - Sign H3re

T2 - 2022 Mensch und Computer Conference: Facing Realities, MuC 2022 - 2022 Conference on Humans and Computers, MuC 2022

AU - Schrapel, Maximilian

AU - Grannemann, Dennis

AU - Rohs, Michael

PY - 2022/9/15

Y1 - 2022/9/15

N2 - Although in many cases contracts can be made or ended digitally, laws require handwritten signatures in certain cases. Forgeries are a major challenge with digital contracts, as their validity is not always immediately apparent without forensic methods. Illiteracy or disabilities may result in a person being unable to write their full name. In this case x-mark signatures are used, which require a witness for validity. In cases of suspected fraud, the relationship of the witnesses must be questioned, which involves a great amount of effort. In this paper we use audio and motion data from a digital pen to identify users via handwritten symbols. We evaluated the performance our approach for 19 symbols in a study with 30 participants. We found that x-marks offer fewer individual features than other symbols like arrows or circles. By training on three samples and averaging three predictions we reach a mean F1-score of F1 = 0.87, using statistical and spectral features fed into SVMs.

AB - Although in many cases contracts can be made or ended digitally, laws require handwritten signatures in certain cases. Forgeries are a major challenge with digital contracts, as their validity is not always immediately apparent without forensic methods. Illiteracy or disabilities may result in a person being unable to write their full name. In this case x-mark signatures are used, which require a witness for validity. In cases of suspected fraud, the relationship of the witnesses must be questioned, which involves a great amount of effort. In this paper we use audio and motion data from a digital pen to identify users via handwritten symbols. We evaluated the performance our approach for 19 symbols in a study with 30 participants. We found that x-marks offer fewer individual features than other symbols like arrows or circles. By training on three samples and averaging three predictions we reach a mean F1-score of F1 = 0.87, using statistical and spectral features fed into SVMs.

KW - accessibility

KW - digital pens

KW - handwriting recognition

KW - motor impairments

KW - pattern recognition

KW - signature authentication

KW - signing documents

UR - http://www.scopus.com/inward/record.url?scp=85139105541&partnerID=8YFLogxK

U2 - 10.1145/3543758.3543764

DO - 10.1145/3543758.3543764

M3 - Conference contribution

AN - SCOPUS:85139105541

T3 - ACM International Conference Proceeding Series

SP - 209

EP - 218

BT - Mensch und Computer 2022

A2 - Muhlhauser, Max

A2 - Reuter, Christian

A2 - Pfleging, Bastian

A2 - Kosch, Thomas

A2 - Matviienko, Andrii

A2 - Gerling, Kathrin

A2 - Mayer, Sven

A2 - Heuten, Wilko

A2 - Doring, Tanja

PB - Association for Computing Machinery (ACM)

Y2 - 4 September 2022 through 7 September 2022

ER -