Publication:
Study on the effect of number of training samples on HMM based offline and online signature verification systems

Simple item page
dc.citedby6
dc.contributor.authorAhmad S.M.S.en_US
dc.contributor.authorShakil A.en_US
dc.contributor.authorBalbed M.A.M.en_US
dc.contributor.authorid24721182400en_US
dc.contributor.authorid24722081200en_US
dc.contributor.authorid24721384800en_US
dc.date.accessioned2023-12-28T07:41:44Z
dc.date.available2023-12-28T07:41:44Z
dc.date.issued2008
dc.description.abstractThis paper reports on the effect that the number of samples used in training a signature verification system has on the system's accuracy which is describes by the pair combination of the system False Acceptance Rate (FAR) and False Rejection Rate (FRR). This paper also describes such an effect on the system Failure to Capture Rate (FCR), which is often neglected by biometrics study. The paper covers both online and offline signature verification systems developed using Hidden Markov Models (HMMs). Experimental results are based on Sigma - a database of Malaysian signatures with over 6,000 genuine samples and 2,000 skilled forgeries collected in a real life environment. � 2008 IEEE.en_US
dc.description.natureFinalen_US
dc.identifier.ArtNo4631615
dc.identifier.doi10.1109/ITSIM.2008.4631615
dc.identifier.scopus2-s2.0-57349197246
dc.identifier.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-57349197246&doi=10.1109%2fITSIM.2008.4631615&partnerID=40&md5=8b70a56b060e5a24a1ceb40076f8b561
dc.identifier.urihttps://irepository.uniten.edu.my/handle/123456789/29707
dc.identifier.volume1
dc.sourceScopus
dc.sourcetitleProceedings - International Symposium on Information Technology 2008, ITSim
dc.subjectBiometrics
dc.subjectHidden Markov models
dc.subjectInformation technology
dc.subjectMarkov processes
dc.subjectPaper
dc.subjectSpeech recognition
dc.subjectSystems engineering
dc.subjectCapture rates
dc.subjectFalse acceptance rates
dc.subjectFalse rejection rates
dc.subjectMalaysians
dc.subjectOffline
dc.subjectOffline signature verifications
dc.subjectOnline signature verification systems
dc.subjectSignature verifications
dc.subjectSystem failures
dc.subjectTraining samples
dc.subjectOnline systems
dc.titleStudy on the effect of number of training samples on HMM based offline and online signature verification systemsen_US
dc.typeConference paperen_US
dspace.entity.typePublication
Files
Collections
SCOPUS