Analysis of the effect of different features' performance on hidden markov modeling based online and offline signature verification systems

Asma Shakil, Sharifah Mumtazah Syed Ahmad, Rina Md. Anwar, Mustafa Agil Muhamad Balbed

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

6 Citations (Scopus)

Abstract

This paper presents a study on the performance of different features in distinguishing between genuine and forged signatures for HMM based online and offline signature verification systems. The online features considered in the study include speed, angle along the trajectory, pen pressure and acceleration. The offline features include pixel density, centre of gravity, distance and angle. All features considered are local in nature Two analysis techniques are considered - ANOVA based and Equal Error rate (EER) based. Experimental results show that all online features have a high distinguishing capability while for the offline case, angle and distance are good for distinguishing between genuine and skilled forgeries for an HMM based signature verification system while pixel density and centre of gravity are not.

Original languageEnglish
Title of host publicationProceedings - Digital Image Computing
Subtitle of host publicationTechniques and Applications, DICTA 2008
Pages572-577
Number of pages6
DOIs
Publication statusPublished - 2008
EventDigital Image Computing: Techniques and Applications, DICTA 2008 - Canberra, ACT, Australia
Duration: 01 Dec 200803 Dec 2008

Other

OtherDigital Image Computing: Techniques and Applications, DICTA 2008
CountryAustralia
CityCanberra, ACT
Period01/12/0803/12/08

Fingerprint

Gravitation
Pixels
Analysis of variance (ANOVA)
Trajectories

All Science Journal Classification (ASJC) codes

  • Computer Graphics and Computer-Aided Design
  • Computer Science Applications

Cite this

Shakil, A., Ahmad, S. M. S., Md. Anwar, R., & Balbed, M. A. M. (2008). Analysis of the effect of different features' performance on hidden markov modeling based online and offline signature verification systems. In Proceedings - Digital Image Computing: Techniques and Applications, DICTA 2008 (pp. 572-577). [4700073] https://doi.org/10.1109/DICTA.2008.76
Shakil, Asma ; Ahmad, Sharifah Mumtazah Syed ; Md. Anwar, Rina ; Balbed, Mustafa Agil Muhamad. / Analysis of the effect of different features' performance on hidden markov modeling based online and offline signature verification systems. Proceedings - Digital Image Computing: Techniques and Applications, DICTA 2008. 2008. pp. 572-577
@inproceedings{f1756b79d93e4d3fa638712be5df1c14,
title = "Analysis of the effect of different features' performance on hidden markov modeling based online and offline signature verification systems",
abstract = "This paper presents a study on the performance of different features in distinguishing between genuine and forged signatures for HMM based online and offline signature verification systems. The online features considered in the study include speed, angle along the trajectory, pen pressure and acceleration. The offline features include pixel density, centre of gravity, distance and angle. All features considered are local in nature Two analysis techniques are considered - ANOVA based and Equal Error rate (EER) based. Experimental results show that all online features have a high distinguishing capability while for the offline case, angle and distance are good for distinguishing between genuine and skilled forgeries for an HMM based signature verification system while pixel density and centre of gravity are not.",
author = "Asma Shakil and Ahmad, {Sharifah Mumtazah Syed} and {Md. Anwar}, Rina and Balbed, {Mustafa Agil Muhamad}",
year = "2008",
doi = "10.1109/DICTA.2008.76",
language = "English",
isbn = "9780769534565",
pages = "572--577",
booktitle = "Proceedings - Digital Image Computing",

}

Shakil, A, Ahmad, SMS, Md. Anwar, R & Balbed, MAM 2008, Analysis of the effect of different features' performance on hidden markov modeling based online and offline signature verification systems. in Proceedings - Digital Image Computing: Techniques and Applications, DICTA 2008., 4700073, pp. 572-577, Digital Image Computing: Techniques and Applications, DICTA 2008, Canberra, ACT, Australia, 01/12/08. https://doi.org/10.1109/DICTA.2008.76

Analysis of the effect of different features' performance on hidden markov modeling based online and offline signature verification systems. / Shakil, Asma; Ahmad, Sharifah Mumtazah Syed; Md. Anwar, Rina; Balbed, Mustafa Agil Muhamad.

Proceedings - Digital Image Computing: Techniques and Applications, DICTA 2008. 2008. p. 572-577 4700073.

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

TY - GEN

T1 - Analysis of the effect of different features' performance on hidden markov modeling based online and offline signature verification systems

AU - Shakil, Asma

AU - Ahmad, Sharifah Mumtazah Syed

AU - Md. Anwar, Rina

AU - Balbed, Mustafa Agil Muhamad

PY - 2008

Y1 - 2008

N2 - This paper presents a study on the performance of different features in distinguishing between genuine and forged signatures for HMM based online and offline signature verification systems. The online features considered in the study include speed, angle along the trajectory, pen pressure and acceleration. The offline features include pixel density, centre of gravity, distance and angle. All features considered are local in nature Two analysis techniques are considered - ANOVA based and Equal Error rate (EER) based. Experimental results show that all online features have a high distinguishing capability while for the offline case, angle and distance are good for distinguishing between genuine and skilled forgeries for an HMM based signature verification system while pixel density and centre of gravity are not.

AB - This paper presents a study on the performance of different features in distinguishing between genuine and forged signatures for HMM based online and offline signature verification systems. The online features considered in the study include speed, angle along the trajectory, pen pressure and acceleration. The offline features include pixel density, centre of gravity, distance and angle. All features considered are local in nature Two analysis techniques are considered - ANOVA based and Equal Error rate (EER) based. Experimental results show that all online features have a high distinguishing capability while for the offline case, angle and distance are good for distinguishing between genuine and skilled forgeries for an HMM based signature verification system while pixel density and centre of gravity are not.

UR - http://www.scopus.com/inward/record.url?scp=67549137657&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67549137657&partnerID=8YFLogxK

U2 - 10.1109/DICTA.2008.76

DO - 10.1109/DICTA.2008.76

M3 - Conference contribution

SN - 9780769534565

SP - 572

EP - 577

BT - Proceedings - Digital Image Computing

ER -

Shakil A, Ahmad SMS, Md. Anwar R, Balbed MAM. Analysis of the effect of different features' performance on hidden markov modeling based online and offline signature verification systems. In Proceedings - Digital Image Computing: Techniques and Applications, DICTA 2008. 2008. p. 572-577. 4700073 https://doi.org/10.1109/DICTA.2008.76