Show simple item record

dc.contributor.authorHarakasim, Rudolf
dc.contributor.authorRamos Castro, Daniel 
dc.contributor.authorMeuwly, Didier
dc.contributor.otherUAM. Departamento de Tecnología Electrónica y de las Comunicacioneses_ES
dc.date.accessioned2017-05-16T16:22:22Z
dc.date.available2017-05-16T16:22:22Z
dc.date.issued2017-03
dc.identifier.citationIET Biometrics 2.6 (2017): 61-69en_US
dc.identifier.issn2047-4938 (print)en_US
dc.identifier.issn2047-4946 (online)en_US
dc.identifier.urihttp://hdl.handle.net/10486/678216
dc.descriptionThis paper is a postprint of a paper submitted to and accepted for publication in IET Biometrics and is subject to Institution of Engineering and Technology Copyright. The copy of record is available at IET Digital Libraryen_US
dc.description.abstractThis article presents a method for computing Likelihood Ratios (LR) from multimodal score distributions produced by an Automated Fingerprint Identification System (AFIS) feature extraction and comparison algorithm. The AFIS algorithm used to compare fingermarks and fingerprints was primarily developed for forensic investigation rather than for forensic evaluation. The computation of the scores is speed-optimized and performed on three different stages, each of which outputs discriminating scores of different magnitudes together forming a multimodal score distribution. It is worthy mentioning that each fingermark to fingerprint comparison performed by the AFIS algorithm results in one single similarity score (e.g. one score per comparison). The multimodal nature of the similarity scores can be typical for other biometric systems and the method proposed in this work can be applied in similar cases, where the multimodal nature in similarity scores is observed. In this work we address some of the problems related to modelling such distributions and propose solutions to issues like data sparsity, dataset shift and over-fitting. The issues mentioned affect the methods traditionally used in the situation when a multimodal nature in the similarity scores is observed (a Kernel Density Functions (KDF) was used to illustrate these issues in our case). Furthermore, the method proposed produces interpretable results in the situations when the similarity scores are sparse and traditional approaches lead to erroneous LRs of huge magnitudesen_US
dc.description.sponsorshipThe research was conducted in scope of the BBfor2 – Marie Curie Initial Training Network (FP7-PEOPLE-ITN-2008 under the Grant Agreement 238803) at the Netherlands Forensic Institute in cooperation with the ATVS Biometric Recognition Group at the Universidad Autonoma de Madrid and the National Police Services Agency of the Netherlandsen_US
dc.format.extent15 pag.en
dc.format.mimetypeapplication/pdfen
dc.language.isoengen_US
dc.publisherThe Institution of Engineering and Technologyen_US
dc.relation.ispartofIET Biometricsen_US
dc.rights© The Institution of Engineering and Technologyen_US
dc.subject.otherValidationen_US
dc.subject.otherMultimodal Score Distributionen_US
dc.subject.otherCalibrationen_US
dc.subject.otherAFISen_US
dc.subject.otherForensic Evaluationen_US
dc.subject.otherFingermarken_US
dc.subject.otherLikelihood Ratioen_US
dc.subject.otherRobustnessen_US
dc.subject.otherReproducibilityen_US
dc.subject.otherAccuracyen_US
dc.titleValidation of likelihood ratio methods for forensic evidence evaluation handling multimodal score distributionsen_US
dc.typearticleen
dc.subject.ecienciaTelecomunicacioneses_ES
dc.accessRightsopenAccessen_US
dc.identifier.doi10.1049/iet-bmt.2015.0059es_ES
dc.identifier.publicationfirstpage61es_ES
dc.identifier.publicationissue2es_ES
dc.identifier.publicationlastpage69es_ES
dc.identifier.publicationvolume6es_ES
dc.relation.projectIDinfo:eu-repo/grantAgreement/EC/FP7/238803en
dc.type.versioninfo:eu-repo/semantics/acceptedVersionen
dc.facultadUAMEscuela Politécnica Superior


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record