Distinctiveness, complexity, and repeatability of online signature templates

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.

Investigating the Common Authorship of Signatures by Off-Line Automatic Signature Verification Without the Use of Reference Signatures

“…In [66] the authors propose to take into account the signature lengths, the number of pronounced directional changes in the line, or overwritings, the length of the pen-downs and complex pen patterns. However, quantifying the complexity in signatures remains an open challenge [50], although significant advances have been recently made for on-line signatures [61], [62], [63].…”

A Secure Live Signature Verification with Aho-Corasick Histogram Algorithm for Mobile Smart Pad

“…Sabourin and Plamondon [15] presented a new version of the centroidal linkage region growing with a merge algorithm. Sae-Bae et al [16] proposed an online signature template method named distinctiveness, complexity, and repeatability to assess the characteristics of signature samples.…”

“…Figures [13][14][15][16] show that the accuracy is not good enough for identification if the four elements are processed separately. Therefore, we used the merging algorithm, which is discussed in Section 3.5, to merge these four elements into one vector in an attempt to obtain better accuracy.…”

Exploiting complexity in pen- and touch-based signature biometrics

“…Their approach achieved a final 78% success rate. Finally, Sae-Bae et al carried out in [30] a recent study proposing three different measures to quantify the characteristics of on-line signature templates in terms of distinctiveness, complexity, and repeatability. In particular, the complexity score of a signature is a security measure against skilled forgery attempts.…”