Abstract

On wearable and Virtual Reality (VR) platforms, user authentication is a basic function, but usually a keyboard or touchscreen cannot be provided to type a password. Hand gesture and especially in-air-handwriting can be potentially used for user authentication because a gesture input interface is readily available on these platforms. However, determining whether a login request is from the legitimate user based on a piece of hand movement is challenging in both signal processing and matching, which leads to limited performance in existing systems. In this paper, we propose a multifactor user authentication framework using both the motion signal of a piece of in-air-handwriting and the geometry of hand skeleton captured by a depth camera. To demonstrate this framework, we invented a signal matching algorithm, implemented a prototype, and conducted experiments on a dataset of 100 users collected by us. Our system achieves 0.6% Equal Error Rate (EER) without spoofing attack and 3.4% EER with spoofing only data, which is a significant improvement compared to existing systems using the Dynamic Time Warping (DTW) algorithm. In addition, we presented an in-depth analysis of the utilized features to explain the reason for the performance boost.

Original languageEnglish (US)
Title of host publicationProceedings - 2018 International Conference on Biometrics, ICB 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages255-262
Number of pages8
ISBN (Electronic)9781538642856
DOIs
StatePublished - Jul 13 2018
Event11th IAPR International Conference on Biometrics, ICB 2018 - Gold Coast, Australia
Duration: Feb 20 2018Feb 23 2018

Other

Other11th IAPR International Conference on Biometrics, ICB 2018
CountryAustralia
CityGold Coast
Period2/20/182/23/18

Fingerprint

handwriting
Handwriting
Authentication
Gestures
platforms
Hand
Air
virtual reality
Geometry
air
geometry
acceleration (physics)
musculoskeletal system
attack
signal processing
Touch screens
cameras
prototypes
Skeleton
Virtual reality

Keywords

  • Hand Geometry
  • In Air Handwriting
  • User Authentication

ASJC Scopus subject areas

  • Instrumentation
  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Pathology and Forensic Medicine

Cite this

Lu, D., Huang, D., Deng, Y., & Alshamrani, A. (2018). Multifactor user authentication with in-air-handwriting and hand geometry. In Proceedings - 2018 International Conference on Biometrics, ICB 2018 (pp. 255-262). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICB2018.2018.00046

Multifactor user authentication with in-air-handwriting and hand geometry. / Lu, Duo; Huang, Dijiang; Deng, Yuli; Alshamrani, Adel.

Proceedings - 2018 International Conference on Biometrics, ICB 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 255-262.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Lu, D, Huang, D, Deng, Y & Alshamrani, A 2018, Multifactor user authentication with in-air-handwriting and hand geometry. in Proceedings - 2018 International Conference on Biometrics, ICB 2018. Institute of Electrical and Electronics Engineers Inc., pp. 255-262, 11th IAPR International Conference on Biometrics, ICB 2018, Gold Coast, Australia, 2/20/18. https://doi.org/10.1109/ICB2018.2018.00046
Lu D, Huang D, Deng Y, Alshamrani A. Multifactor user authentication with in-air-handwriting and hand geometry. In Proceedings - 2018 International Conference on Biometrics, ICB 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 255-262 https://doi.org/10.1109/ICB2018.2018.00046
Lu, Duo ; Huang, Dijiang ; Deng, Yuli ; Alshamrani, Adel. / Multifactor user authentication with in-air-handwriting and hand geometry. Proceedings - 2018 International Conference on Biometrics, ICB 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 255-262
@inproceedings{087ea8fecc9c4e3a928807a7832b9ad0,
title = "Multifactor user authentication with in-air-handwriting and hand geometry",
abstract = "On wearable and Virtual Reality (VR) platforms, user authentication is a basic function, but usually a keyboard or touchscreen cannot be provided to type a password. Hand gesture and especially in-air-handwriting can be potentially used for user authentication because a gesture input interface is readily available on these platforms. However, determining whether a login request is from the legitimate user based on a piece of hand movement is challenging in both signal processing and matching, which leads to limited performance in existing systems. In this paper, we propose a multifactor user authentication framework using both the motion signal of a piece of in-air-handwriting and the geometry of hand skeleton captured by a depth camera. To demonstrate this framework, we invented a signal matching algorithm, implemented a prototype, and conducted experiments on a dataset of 100 users collected by us. Our system achieves 0.6{\%} Equal Error Rate (EER) without spoofing attack and 3.4{\%} EER with spoofing only data, which is a significant improvement compared to existing systems using the Dynamic Time Warping (DTW) algorithm. In addition, we presented an in-depth analysis of the utilized features to explain the reason for the performance boost.",
keywords = "Hand Geometry, In Air Handwriting, User Authentication",
author = "Duo Lu and Dijiang Huang and Yuli Deng and Adel Alshamrani",
year = "2018",
month = "7",
day = "13",
doi = "10.1109/ICB2018.2018.00046",
language = "English (US)",
pages = "255--262",
booktitle = "Proceedings - 2018 International Conference on Biometrics, ICB 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Multifactor user authentication with in-air-handwriting and hand geometry

AU - Lu, Duo

AU - Huang, Dijiang

AU - Deng, Yuli

AU - Alshamrani, Adel

PY - 2018/7/13

Y1 - 2018/7/13

N2 - On wearable and Virtual Reality (VR) platforms, user authentication is a basic function, but usually a keyboard or touchscreen cannot be provided to type a password. Hand gesture and especially in-air-handwriting can be potentially used for user authentication because a gesture input interface is readily available on these platforms. However, determining whether a login request is from the legitimate user based on a piece of hand movement is challenging in both signal processing and matching, which leads to limited performance in existing systems. In this paper, we propose a multifactor user authentication framework using both the motion signal of a piece of in-air-handwriting and the geometry of hand skeleton captured by a depth camera. To demonstrate this framework, we invented a signal matching algorithm, implemented a prototype, and conducted experiments on a dataset of 100 users collected by us. Our system achieves 0.6% Equal Error Rate (EER) without spoofing attack and 3.4% EER with spoofing only data, which is a significant improvement compared to existing systems using the Dynamic Time Warping (DTW) algorithm. In addition, we presented an in-depth analysis of the utilized features to explain the reason for the performance boost.

AB - On wearable and Virtual Reality (VR) platforms, user authentication is a basic function, but usually a keyboard or touchscreen cannot be provided to type a password. Hand gesture and especially in-air-handwriting can be potentially used for user authentication because a gesture input interface is readily available on these platforms. However, determining whether a login request is from the legitimate user based on a piece of hand movement is challenging in both signal processing and matching, which leads to limited performance in existing systems. In this paper, we propose a multifactor user authentication framework using both the motion signal of a piece of in-air-handwriting and the geometry of hand skeleton captured by a depth camera. To demonstrate this framework, we invented a signal matching algorithm, implemented a prototype, and conducted experiments on a dataset of 100 users collected by us. Our system achieves 0.6% Equal Error Rate (EER) without spoofing attack and 3.4% EER with spoofing only data, which is a significant improvement compared to existing systems using the Dynamic Time Warping (DTW) algorithm. In addition, we presented an in-depth analysis of the utilized features to explain the reason for the performance boost.

KW - Hand Geometry

KW - In Air Handwriting

KW - User Authentication

UR - http://www.scopus.com/inward/record.url?scp=85050985163&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050985163&partnerID=8YFLogxK

U2 - 10.1109/ICB2018.2018.00046

DO - 10.1109/ICB2018.2018.00046

M3 - Conference contribution

AN - SCOPUS:85050985163

SP - 255

EP - 262

BT - Proceedings - 2018 International Conference on Biometrics, ICB 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -