Handwritten signature verification : a hidden Markov model approach

[摘要] ENGLISH ABSTRACT:Handwritten signature verification (HSV) is the process through which handwrittensignatures are analysed in an attempt to determine whether the person who made thesignature is who he claims to be.Banks and other financial institutions lose billions of rands annually to cheque fraudand other crimes that are preventable with the aid of good signature verificationtechniques. Unfortunately, the volume of cheques that are processed precludes athorough HSV process done in the traditional manner by human operators.It is the aim of this research to investigate new methods to compare signaturesautomatically, to eventually speed up the HSV process and improve on the accuracyof existing systems.The new technology that is investigated is the use of the so-called hidden Markovmodels (HMMs). It is only quite recently that the computing power has becomecommonly available to make the real-time use of HMMs in pattern recognition apossibility.Two demonstration programs, SigGrab and Securitlheque, have been developed thatmake use of this technology, and show excellent improvements over other techniquesand competing products. HSV accuracies in excess of99% can be attained.

[发布机构] Stellenbosch University