Distinctiveness, complexity, and repeatability of online signature templates. (December 2018)

• Record Type: Journal Article
• Authors: Sae-Bae, Napa; Memon, Nasir; Sooraksa, Pitikhate
• Is Part Of: Pattern recognition. Volume 84(2018:Dec.)
• Page Start: 332
• Page End: 344
• Publication Date: 2018-12
• Subjects: Biometric -- Online signature -- Biometric template quality -- Distinctiveness -- Complexity -- Repeatability; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2018.07.024
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: The metric to measure distinctiveness, complexity, and repeatability of an online signature template are proposed. Distinctiveness could be used to infer FAR against random forgery of a particular template. Complexity could be used to infer FAR against skill forgery of a particular template. Repeatability could be used to infer FRR of a particular template. The efficacy of these three measures is demonstrated through experiments performed on three online signature and one keystroke dynamics datasets using multiple verification algorithms. Abstract: This paper proposes three measures to quantify the characteristics of online signature templates in terms of distinctiveness, complexity and repeatability. A distinctiveness measure of a signature template is computed from a set of enrolled signature samples and a statistical assumption about random signatures. Secondly, a complexity measure of the template is derived from a set of enrolled signature samples. Finally, given a signature template, a measure to quantify the repeatability of the online signature is derived from a validation set of samples. These three measures can then be used as an indicator for the performance of the system in rejecting random forgery samples and skilled forgery samples and the performance of users in providing accepted genuine samples, respectively. The effectiveness of these three measures and their applications are demonstrated through experiments performed on three online signature datasets and one keystroke dynamics dataset using different verification algorithms.