A new approach to automatic signature complexity assessment

Abstract

Abstract-Understanding signature complexity has been shown to be a crucial facet for both forensic and biometric applications. The signature complexity can be defined as the difficulty that forgers have when imitating the dynamics (constructional aspects) of other users signatures. Knowledge of complexity along with others facets such stability and signature length can lead to more robust and secure automatic signature verification systems. The work presented in this paper investigates the creation of a novel mathematical model for the automatic assessment of the signature complexity, analysing a wider set of dynamic signature features and also incorporating a new layer of detail, investigating the complexity of individual signature strokes. To demonstrate the effectiveness of the model this work will attempt to reproduce the signature complexity assessment made by experienced FDEs on a dataset of 150 signature samples.

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

“…It involves dividing the entire problem into several sub problems depending on the complexity of the signatures being questioned and developing different strategies for each complexity level. This proposal is reasonable, as it is well known that the quality of forgeries depends on the complexity of the signature, among other properties [9], [59], [60], [61], [62], [63].…”

“…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 Perspective Analysis of Handwritten Signature Technology

“…A complete framework for statistical assessment of signature complexity has been also defined. This is based on static and dynamic features, for example, the number of strokes (defined in terms of lognormals in [248]), the total number of intra-/interstroke intersections, the means of intra-/interstroke intersections, the maximum of intra-/interstroke intersections, the number of x-axis intersections, the sums of the horizontal and vertical components of the velocity and acceleration at zero-crossings, and the signature length [154].…”

Exploiting complexity in pen- and touch-based signature biometrics

“…More recently, Miguel-Hurtado et al proposed in [29] a new approach to automatic signature complexity assessment. They proposed to extract a set of 14 global features such as the total number of X-axis intersections and the signature length together with multilinear regression models to automatically detect the signature complexity level.…”