Hidden Markov models for on-line signature verification

[摘要] ENGLISH ABSTRACT:The science of signature verification is concerned with identifying individuals by their handwrittensignatures. It is assumed that the signature as such is a unique feature amongstindividuals and the creation thereof requires a substantial amount of hidden informationwhich makes it difficult for another individual to reproduce the signature. Modern technologyhas produced devices which are able to capture information about the signing processbeyond what is visible to the naked eye. A dynamic signature verification system is concernedwith utilizing not only visible, i.e. shape related information but also invisible, hidden dynamicalcharacteristics of signatures. These signature characteristics need to be subjected toanalysis and modelling in order to automate use of signatures as an identification metric. Weinvestigate the applicability of hidden Markov models to the problem of modelling signaturecharacteristics and test their ability to distinguish between authentic signatures and forgeries.

[发布机构] Stellenbosch University