Bayesian MCMC for biometric person authentication incorporating on-line signature trajectories

Mitsuru Kondo, Daigo Muramatsu, Masahiro Sasaki, Takashi Matsumoto

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

Abstract

Authentication of individuals is rapidly becoming an important issue. The authors have previously proposed a pen-input online signature verification algorithm. The algorithm considers writer's signature as a trajectory of pen-position, pen-pressure and pen-inclination which evolves over time, so that it is dynamic and biometric. In our previous work, genuine signatures were separated from forgery signatures in a linear manner. This paper proposes a new algorithm which performs nonlinear separation using Bayesian MCMC (Markov Chain Monte Carlo). A preliminary experiment is performed on a database consisting of 1825 genuine signatures and 4117 skilled forgery signatures from fourteen individuals. FRR 0.81% and FAR 0.87% are achieved. Since no fine tuning was done, this preliminary result looks very promising.

Original languageEnglish
Title of host publicationProceedings of the IASTED International Conference on Signal Processing, Pattern Reconition, and Applications
EditorsM.H. Hamza
Pages269-273
Number of pages5
Publication statusPublished - 2003
Externally publishedYes
EventProceedings of the IASTED International Conference on Signal Processing, Pattern Recognition and Applications - Rhodes
Duration: 2003 Jun 302003 Jul 2

Other

OtherProceedings of the IASTED International Conference on Signal Processing, Pattern Recognition and Applications
CityRhodes
Period03/6/3003/7/2

Fingerprint

biometry
Markov chain
Biometrics
Markov processes
Authentication
trajectory
Trajectories
human being
Tuning
writer
experiment
biometrics
Experiments

Keywords

  • Bayes
  • Biometrics
  • Markov Chain Monte Carlo
  • Pattern recognition
  • Person authentication
  • Signature verification

ASJC Scopus subject areas

  • Development
  • Signal Processing
  • Computer Vision and Pattern Recognition

Cite this

Kondo, M., Muramatsu, D., Sasaki, M., & Matsumoto, T. (2003). Bayesian MCMC for biometric person authentication incorporating on-line signature trajectories. In M. H. Hamza (Ed.), Proceedings of the IASTED International Conference on Signal Processing, Pattern Reconition, and Applications (pp. 269-273)

Bayesian MCMC for biometric person authentication incorporating on-line signature trajectories. / Kondo, Mitsuru; Muramatsu, Daigo; Sasaki, Masahiro; Matsumoto, Takashi.

Proceedings of the IASTED International Conference on Signal Processing, Pattern Reconition, and Applications. ed. / M.H. Hamza. 2003. p. 269-273.

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

Kondo, M, Muramatsu, D, Sasaki, M & Matsumoto, T 2003, Bayesian MCMC for biometric person authentication incorporating on-line signature trajectories. in MH Hamza (ed.), Proceedings of the IASTED International Conference on Signal Processing, Pattern Reconition, and Applications. pp. 269-273, Proceedings of the IASTED International Conference on Signal Processing, Pattern Recognition and Applications, Rhodes, 03/6/30.
Kondo M, Muramatsu D, Sasaki M, Matsumoto T. Bayesian MCMC for biometric person authentication incorporating on-line signature trajectories. In Hamza MH, editor, Proceedings of the IASTED International Conference on Signal Processing, Pattern Reconition, and Applications. 2003. p. 269-273
Kondo, Mitsuru ; Muramatsu, Daigo ; Sasaki, Masahiro ; Matsumoto, Takashi. / Bayesian MCMC for biometric person authentication incorporating on-line signature trajectories. Proceedings of the IASTED International Conference on Signal Processing, Pattern Reconition, and Applications. editor / M.H. Hamza. 2003. pp. 269-273
@inproceedings{9f4739847b084f84b79a6dda12122beb,
title = "Bayesian MCMC for biometric person authentication incorporating on-line signature trajectories",
abstract = "Authentication of individuals is rapidly becoming an important issue. The authors have previously proposed a pen-input online signature verification algorithm. The algorithm considers writer's signature as a trajectory of pen-position, pen-pressure and pen-inclination which evolves over time, so that it is dynamic and biometric. In our previous work, genuine signatures were separated from forgery signatures in a linear manner. This paper proposes a new algorithm which performs nonlinear separation using Bayesian MCMC (Markov Chain Monte Carlo). A preliminary experiment is performed on a database consisting of 1825 genuine signatures and 4117 skilled forgery signatures from fourteen individuals. FRR 0.81{\%} and FAR 0.87{\%} are achieved. Since no fine tuning was done, this preliminary result looks very promising.",
keywords = "Bayes, Biometrics, Markov Chain Monte Carlo, Pattern recognition, Person authentication, Signature verification",
author = "Mitsuru Kondo and Daigo Muramatsu and Masahiro Sasaki and Takashi Matsumoto",
year = "2003",
language = "English",
isbn = "0889863784",
pages = "269--273",
editor = "M.H. Hamza",
booktitle = "Proceedings of the IASTED International Conference on Signal Processing, Pattern Reconition, and Applications",

}

TY - GEN

T1 - Bayesian MCMC for biometric person authentication incorporating on-line signature trajectories

AU - Kondo, Mitsuru

AU - Muramatsu, Daigo

AU - Sasaki, Masahiro

AU - Matsumoto, Takashi

PY - 2003

Y1 - 2003

N2 - Authentication of individuals is rapidly becoming an important issue. The authors have previously proposed a pen-input online signature verification algorithm. The algorithm considers writer's signature as a trajectory of pen-position, pen-pressure and pen-inclination which evolves over time, so that it is dynamic and biometric. In our previous work, genuine signatures were separated from forgery signatures in a linear manner. This paper proposes a new algorithm which performs nonlinear separation using Bayesian MCMC (Markov Chain Monte Carlo). A preliminary experiment is performed on a database consisting of 1825 genuine signatures and 4117 skilled forgery signatures from fourteen individuals. FRR 0.81% and FAR 0.87% are achieved. Since no fine tuning was done, this preliminary result looks very promising.

AB - Authentication of individuals is rapidly becoming an important issue. The authors have previously proposed a pen-input online signature verification algorithm. The algorithm considers writer's signature as a trajectory of pen-position, pen-pressure and pen-inclination which evolves over time, so that it is dynamic and biometric. In our previous work, genuine signatures were separated from forgery signatures in a linear manner. This paper proposes a new algorithm which performs nonlinear separation using Bayesian MCMC (Markov Chain Monte Carlo). A preliminary experiment is performed on a database consisting of 1825 genuine signatures and 4117 skilled forgery signatures from fourteen individuals. FRR 0.81% and FAR 0.87% are achieved. Since no fine tuning was done, this preliminary result looks very promising.

KW - Bayes

KW - Biometrics

KW - Markov Chain Monte Carlo

KW - Pattern recognition

KW - Person authentication

KW - Signature verification

UR - http://www.scopus.com/inward/record.url?scp=1542433788&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=1542433788&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0889863784

SP - 269

EP - 273

BT - Proceedings of the IASTED International Conference on Signal Processing, Pattern Reconition, and Applications

A2 - Hamza, M.H.

ER -