On-line signature verification with hidden Markov models

J.G.A. Dolfing; E.H.L. Aarts; J.J.G.M. Oosterhout, van

doi:10.1109/ICPR.1998.711942

On-line signature verification with hidden Markov models

J.G.A. Dolfing, E.H.L. Aarts, J.J.G.M. Oosterhout, van

Algorithms, Geometry and Applications

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Abstract

This paper addresses the problem of online signature verification based on hidden Markov models (HMM). We use a novel type of digitizer tablet and pay special attention to the use of pen-tilt. We investigate the verification reliability based on different forgery types. We compare the discriminative value of the different features based on a linear discriminant analysis (LDA) and show that pen-tilt is important. On the basis of home-improved, over-the-shoulder and professional forgeries, we show that the amount of dynamic information available to an imposter is important and that forgeries based on paper copies are easier to detect. The results obtained with a database of almost 5000 signatures of 51 persons with highly skilled forgeries include equal-error rates between 1% and 1.9%.

Original language	English
Title of host publication	14th International Conference on Pattern Recognition (Brisbane, Queensland, Australia, August 16-20, 1998)
Place of Publication	Piscataway
Publisher	Institute of Electrical and Electronics Engineers
Pages	1309-1312
ISBN (Print)	0-8186-8512-3
DOIs	https://doi.org/10.1109/ICPR.1998.711942
Publication status	Published - 1998

Access to Document

10.1109/ICPR.1998.711942

Cite this

@inproceedings{38ad2303c2fd404da32bce51e8223ddd,

title = "On-line signature verification with hidden Markov models",

abstract = "This paper addresses the problem of online signature verification based on hidden Markov models (HMM). We use a novel type of digitizer tablet and pay special attention to the use of pen-tilt. We investigate the verification reliability based on different forgery types. We compare the discriminative value of the different features based on a linear discriminant analysis (LDA) and show that pen-tilt is important. On the basis of home-improved, over-the-shoulder and professional forgeries, we show that the amount of dynamic information available to an imposter is important and that forgeries based on paper copies are easier to detect. The results obtained with a database of almost 5000 signatures of 51 persons with highly skilled forgeries include equal-error rates between 1% and 1.9%.",

author = "J.G.A. Dolfing and E.H.L. Aarts and {Oosterhout, van}, J.J.G.M.",

year = "1998",

doi = "10.1109/ICPR.1998.711942",

language = "English",

isbn = "0-8186-8512-3",

pages = "1309--1312",

booktitle = "14th International Conference on Pattern Recognition (Brisbane, Queensland, Australia, August 16-20, 1998)",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

}

On-line signature verification with hidden Markov models. / Dolfing, J.G.A.; Aarts, E.H.L.; Oosterhout, van, J.J.G.M.

14th International Conference on Pattern Recognition (Brisbane, Queensland, Australia, August 16-20, 1998). Piscataway : Institute of Electrical and Electronics Engineers, 1998. p. 1309-1312.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - On-line signature verification with hidden Markov models

AU - Dolfing, J.G.A.

AU - Aarts, E.H.L.

AU - Oosterhout, van, J.J.G.M.

PY - 1998

Y1 - 1998

N2 - This paper addresses the problem of online signature verification based on hidden Markov models (HMM). We use a novel type of digitizer tablet and pay special attention to the use of pen-tilt. We investigate the verification reliability based on different forgery types. We compare the discriminative value of the different features based on a linear discriminant analysis (LDA) and show that pen-tilt is important. On the basis of home-improved, over-the-shoulder and professional forgeries, we show that the amount of dynamic information available to an imposter is important and that forgeries based on paper copies are easier to detect. The results obtained with a database of almost 5000 signatures of 51 persons with highly skilled forgeries include equal-error rates between 1% and 1.9%.

AB - This paper addresses the problem of online signature verification based on hidden Markov models (HMM). We use a novel type of digitizer tablet and pay special attention to the use of pen-tilt. We investigate the verification reliability based on different forgery types. We compare the discriminative value of the different features based on a linear discriminant analysis (LDA) and show that pen-tilt is important. On the basis of home-improved, over-the-shoulder and professional forgeries, we show that the amount of dynamic information available to an imposter is important and that forgeries based on paper copies are easier to detect. The results obtained with a database of almost 5000 signatures of 51 persons with highly skilled forgeries include equal-error rates between 1% and 1.9%.

U2 - 10.1109/ICPR.1998.711942

DO - 10.1109/ICPR.1998.711942

M3 - Conference contribution

SN - 0-8186-8512-3

SP - 1309

EP - 1312

BT - 14th International Conference on Pattern Recognition (Brisbane, Queensland, Australia, August 16-20, 1998)

PB - Institute of Electrical and Electronics Engineers

CY - Piscataway

ER -

On-line signature verification with hidden Markov models

Abstract

Access to Document

Fingerprint

Cite this