Analysis of the Effects and Relationship of Perceived Handwritten Signature's Size, Graphical Complexity, and Legibility with Dynamic Parameters for Forged and Genuine Samples

Abstract

This article presents an analysis of handwritten signature dynamics belonging to two authentication groups, namely genuine and forged signature samples. Genuine signatures are initially classified based on their relative size, graphical complexity, and legibility as perceived by human examiners. A pool of dynamic features is then extracted for each signature sample in the two groups. A two-way analysis of variance (ANOVA) is carried out to investigate the effects and the relationship between the perceived classifications and the authentication groups. Homogeneity of variance was ensured through Bartlett's test prior to ANOVA testing. The results demonstrated that among all the investigated dynamic features, pen pressure is the most distinctive which is significantly different for the two authentication groups as well as for the different perceived classifications. In addition, all the relationships investigated, namely authenticity group versus size, graphical complexity, and legibility, were found to be positive for pen pressure.

Feature-based dynamic signature verification under forensic scenarios

“…3) represents that overall pen down duration for genuine signatures are lower compared with forgers. This results agrees with previous works [5].…”

“…In this work, we analyze an extended set of 117 features, of which 100 were used in previous works [6], and here we propose 17 new features (see Table 1). Most of the new features are pressure-related, while some others have been extracted from related works [5]. The whole set of 117 features can be divided in five categories corresponding to the following magnitudes (the numbering of the first 100 features is the same as in [6]): Mahalanobis distance is used to compare the similarity between a signature and a claimed user model.…”

“…A similar statistical analysis was carried out in [5] for a different set of features. Only the overall pen down duration is considered in both studies showing different time durations, but the main reason for that is that in [5] signatures belong to a Malaysian population, while in BioSecure an European population is considered.…”

“…This is starting to change as nowadays digital signature devices are spreading in the commercial sector to facilitate payments and also in banking to facilitate the digital storage of all the signed paperwork. Therefore, forensic document examiners (FDEs) are being required to provide forensic evidence to determine the authenticity of handwritten signatures written on digitizing tablets [5], which can provide an static image of the signature but also, and most importantly, contain the dynamic information of at least the X and Y spatial coordinates.…”

e-BioSign tool: Towards scientific assessment of dynamic signatures under forensic conditions

“…However, there are very few research works in the field of dynamic signature for forensic examinations [1,16,8]. The majority of relevant literature regarding dynamic signature analysis is in the field of biometric recognition [4], which make use of algorithms such as Hidden Markov Models [5,18] or Dynamic Time Warping [13,17].…”