Enhanced on-line signature verification based on skilled forgery detection using Sigma-LogNormal Features

Gómez-Barrero, Marta; Galbally Herrero, Javier; Fiérrez Aguilar, Julián; Ortega García, Javier

UAM_Biblioteca

Author

Gómez-Barrero, Marta; Galbally Herrero, Javier; Fiérrez Aguilar, Julián

; Ortega García, Javier

Entity

UAM. Departamento de Tecnología Electrónica y de las Comunicaciones

Publisher

Institute of Electrical and Electronics Engineers

Date

2015

Citation

International Conference on Biometrics, ICB 2015. IEEE, 2015. 501-506

ISBN

978-1-4799-7824-3

DOI

10.1109/ICB.2015.7139065

Funded by

This work has been partially supported by project Bio- Shield (TEC2012-34881) from Spanish MINECO, BEAT (FP7-SEC-284989) from EU, Cátedra UAM-Telefónica, CECABANK, and grant RGPIN-915 from NSERC Canada. M. G.-B. is supported by a FPU Fellowship from Spanish MECD.

Project

info:eu-repo/grantAgreement/EC/FP7/284989

Editor's Version

http://dx.doi.org/10.1109/ICB.2015.7139065

Subjects

Computational modeling; Databases; Detectors; Informática; Telecomunicaciones

URI

http://hdl.handle.net/10486/667298

Note

Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. M. Gomez-Barrero, J. Galbally, J. Fierrez, and J. Ortega-Garcia, "Enhanced on-line signature verification based on skilled forgery detection using Sigma-LogNormal Features", in International Conference on Biometrics, ICB 2015, 501-506

Rights

Abstract

One of the biggest challenges in on-line signature verification is the detection of skilled forgeries. In this paper, we propose a novel scheme, based on the Kinematic Theory of rapid human movements and its associated Sigma LogNormal model, to improve the performance of on-line signature verification systems. The approach combines the high performance of DTW-based systems in verification tasks, with the high potential for skilled forgery detection of the Kinematic Theory of rapid human movements. Experiments were carried out on the publicly available BiosecurID multimodal database, comprising 400 subjects. Results show that the performance of the DTW-based system improves for both skilled and random forgeries.

Show full item record