The application of signature recognition to transparent handwriting verification for mobile devices

Abstract

PurposeThe popularity of mobile devices and the evolving nature of the services and information they can delivery make them increasingly desirable targets for misuse. The ability to provide effective authentication of the user becomes imperative if protection against misuse of personally and financially sensitive information is to be provided. This paper discusses the application of biometrics to a mobile device in a transparent and continuous fashion and the subsequent advantages and disadvantages that are in contention with various biometric techniques.Design/methodology/approachAn investigation was conducted to evaluate the feasibility of utilising signature recognition, to verify users based upon written words and not signatures, thereby enabling transparent handwriting verification. Participants were required to write a number of common words, such as “hello” “sorry” and “thank you”. The ability to correctly verify against their own template and to reject impostors was then established.FindingsTotally, 20 users participated in the study and an average FAR and FRR of 0 and 1.2 per cent, respectively, were experienced across eight common words.Research limitations/implicationsThe initial study has proven very successful, however, further investigations need to be established with a larger population of users and a wider vocabulary of words.Originality/valueThis study has verified the feasibility of applying an existing signature recognition technique to transparent handwriting verification.