Please use this identifier to cite or link to this item: http://hdl.handle.net/10553/60152
DC FieldValueLanguage
dc.contributor.authorDiaz, Moisesen_US
dc.contributor.authorFerrer, Miguel A.en_US
dc.contributor.authorRamalingam, Soodamanien_US
dc.contributor.authorGuest, Richarden_US
dc.date.accessioned2020-01-14T22:34:07Z-
dc.date.available2020-01-14T22:34:07Z-
dc.date.issued2020en_US
dc.identifier.issn1556-6013en_US
dc.identifier.otherScopus-
dc.identifier.urihttp://hdl.handle.net/10553/60152-
dc.description.abstractIn automatic signature verification, questioned specimens are usually compared with reference signatures. In writer-dependent schemes, a number of reference signatures are required to build up the individual signer model while a writer-independent system requires a set of reference signatures from several signers to develop the model of the system. This paper addresses the problem of automatic signature verification when no reference signatures are available. The scenario we explore consists of a set of signatures, which could be signed by the same author or by multiple signers. As such, we discuss three methods which estimate automatically the common authorship of a set of off-line signatures. The first method develops a score similarity matrix, worked out with the assistance of duplicated signatures; the second uses a feature-distance matrix for each pair of signatures; and the last method introduces pre-classification based on the complexity of each signature. Publicly available signatures were used in the experiments, which gave encouraging results. As a baseline for the performance obtained by our approaches, we carried out a visual Turing Test where forensic and non-forensic human volunteers, carrying out the same task, performed less well than the automatic schemes.en_US
dc.languageengen_US
dc.relation.ispartofIEEE Transactions on Information Forensics and Securityen_US
dc.sourceIEEE Transactions on Information Forensics and Security [ISSN 1556-6013], v. 15 (8742639), p. 487-499en_US
dc.subject530602 Innovación tecnológicaen_US
dc.subject120304 Inteligencia artificialen_US
dc.subject.otherOff-line signature verificationen_US
dc.subject.otherBiometricsen_US
dc.subject.otherNo reference signaturesen_US
dc.subject.otherFeature-distance matrixen_US
dc.subject.otherSignature complexityen_US
dc.titleInvestigating the Common Authorship of Signatures by Off-Line Automatic Signature Verification without the Use of Reference Signaturesen_US
dc.typeinfo:eu-repo/semantics/Articleen_US
dc.typeArticleen_US
dc.identifier.doi10.1109/TIFS.2019.2924195
dc.identifier.scopus85077337450
dc.identifier.isi000487189200018
dc.contributor.authorscopusid57212322956
dc.contributor.authorscopusid55636321172
dc.contributor.authorscopusid36626452700
dc.contributor.authorscopusid35612740300
dc.description.lastpage499-
dc.identifier.issue8742639-
dc.description.firstpage487-
dc.relation.volume15-
dc.investigacionIngeniería y Arquitecturaen_US
dc.type2Artículoen_US
dc.contributor.daisngid31498511
dc.contributor.daisngid233119
dc.contributor.daisngid2350406
dc.contributor.daisngid534470
dc.contributor.wosstandardWOS:Diaz, M
dc.contributor.wosstandardWOS:Ferrer, MA
dc.contributor.wosstandardWOS:Ramalingam, S
dc.contributor.wosstandardWOS:Guest, R
dc.date.coverdate2020
item.grantfulltextnone-
item.fulltextSin texto completo-
crisitem.author.deptDepartamento de Señales y Comunicaciones-
crisitem.author.deptIDeTIC: División de Procesado Digital de Señales-
crisitem.author.deptIU para el Desarrollo Tecnológico y la Innovación-
crisitem.author.orcid0000-0003-3878-3867-
crisitem.author.orcid0000-0002-2924-1225-
crisitem.author.parentorgIU para el Desarrollo Tecnológico y la Innovación-
crisitem.author.fullNameDiaz Cabrera, Moises-
crisitem.author.fullNameFerrer Ballester, Miguel Ángel-
crisitem.author.departamentoSeñales y Comunicaciones-
Appears in Collections:Artículos
Show simple item record

Page view(s)

34
checked on May 23, 2020

Google ScholarTM

Check

Altmetric


Share



Export metadata



Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.