Show simple item record

dc.contributor.authorAlsaade, F.
dc.contributor.authorAriyaeeinia, A.
dc.contributor.authorMeng, Li
dc.contributor.authorMalegaonkar, A.
dc.date.accessioned2015-02-25T12:33:26Z
dc.date.available2015-02-25T12:33:26Z
dc.date.issued2006
dc.identifier.citationAlsaade , F , Ariyaeeinia , A , Meng , Li & Malegaonkar , A 2006 , Multimodal Authentication using Qualitative Support Vector Machines . in INTERSPEECH 2006 AND 9th Int Conf on Spoken Language Processing . ISCA-INST SPEECH COMMUNICATION ASSOC , pp. 2454-2457 .en
dc.identifier.isbn978-1-60423-449-7
dc.identifier.otherPURE: 788971
dc.identifier.otherPURE UUID: c8125b8c-f3c8-47d5-9206-a7e5b3d4012d
dc.identifier.otherWOS: 000269965901351
dc.identifier.otherScopus: 35448938859
dc.identifier.urihttp://hdl.handle.net/2299/15475
dc.description.abstractThis paper proposes an approach to enhancing the accuracy of multimodal biometrics in uncontrolled environments. Variation in operating conditions results in mismatch between the training and test material, and thereby affects the biometric authentication performance regardless of this being unimodal or multimodal. ne paper proposes a technique to reduce the effects of such variations in multimodal fusion. The proposed technique is based on estimating the quality aspect of the test scores and then passing these aspects into the Support Vector Machine either as features or weights. Since the fusion process is based on the learning classifier of Support Vector Machine, the technique is termed Support Vector Machine with Quality Measurement (SVM-QM). The experimental investigation is conducted using face and speech modalities. The results clearly show the benefits gained from learning the quality aspects of the biometric data used for authentication.en
dc.format.extent4en
dc.language.isoeng
dc.publisherISCA-INST SPEECH COMMUNICATION ASSOC
dc.relation.ispartofINTERSPEECH 2006 AND 9th Int Conf on Spoken Language Processingen
dc.rightsen
dc.subjectMultimodal biometric authenticationen
dc.subjectscore level fusionen
dc.subjectquality measurementen
dc.subjectsupport vector machineen
dc.titleMultimodal Authentication using Qualitative Support Vector Machinesen
dc.contributor.institutionSchool of Engineering and Technologyen
dc.contributor.institutionScience & Technology Research Instituteen
dc.contributor.institutionCentre for Engineering Researchen
dc.relation.schoolSchool of Engineering and Technology
herts.preservation.rarelyaccessedtrue


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record