The Dynamic Character of Disguise Behavior for Text‐based, Mixed, and Stylized Signatures

Abstract

The aims of this study were to determine if dynamic parameters (duration, size, velocity, jerk, and pen pressure) differed for signing style (text-based, stylized, and mixed) and if signing style influences handwriting dynamics equally across three signature conditions (genuine, disguised, and auto-simulation). Ninety writers provided 10 genuine signatures, five disguised signatures, and five auto-simulated signatures. All 1800 signatures were collected using a digitizing tablet resulting in a database of each signature's dynamic characteristics. With genuine signatures, there were significant differences between styles for size, velocity, and pen pressure, and there were significant differences between genuine signatures and at least one of the un-natural signature conditions for all parameters. For velocity and size, these changes with condition were dependent on style. Changes with condition for the other parameters were similar for the three styles. This study shows that there are differences among natural signature styles and disguise behaviors that may be relevant in forensic signature examinations.

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

“…With the advancement of current technologies, signature images can also be captured through the online mechanism. The online system often involves the use of digitizing tablets and pens which are used to capture the dynamic signing information (5,(8)(9)(10)(11)(12)(13)(14)(15). Signature dynamics can be processed further to provide features such as the signing velocity, acceleration, pen pressure, and strokes along the signing trajectory.…”

Dynamic signatures: A review of dynamic feature variation and forensic methodology

“…Velocity and acceleration in simulations are often lower than in the genuine signatures. Jerk appears to be lower in text-based genuine signatures [35,36] in comparison with the simulations, although the other signature styles do not show significant…”

“…Several studies indicate that velocity and acceleration, as well as their variations are interesting features in simulation detection [34][35][36][37][38]. Velocity and acceleration in simulations are often lower than in the genuine signatures.…”

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

“…For the initial release of e-BioSign Tool five global features have been selected. Three of them are common in feature based dynamic signature recognition systems [21,18]: total duration of the signature, average velocity and average acceleration. The other two parameters are commonly used in offline signature forensic analysis [6,7,3,24,9]: time fluency and spatial tremor.…”

“…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].…”