e-BioSign Tool: Towards Scientific Assessment of Dynamic Signatures under Forensic Conditions

Abstract

This paper presents a new tool specifically designed to carry out dynamic signature forensic analysis and give sci- entific support to forensic handwriting examiners (FHEs). Traditionally FHEs have performed forensic analysis of paper-based signatures for court cases, but with the rapid evolution of the technology, nowadays they are being asked to carry out analysis based on signatures acquired by digi- tizing tablets more and more often. In some cases, an option followed has been to obtain a paper impression of these sig- natures and carry out a traditional analysis, but there are many deficiencies in this approach regarding the low spa- tial resolution of some devices compared to original off-line signatures and also the fact that the dynamic information, which has been proved to be very discriminative by the bio- metric community, is lost and not taken into account at all. The tool we present in this paper allows the FHEs to carry out a forensic analysis taking into account both the tra- ditional off-line information normally used in paper-based signature analysis, and also the dynamic information of the signatures. Additionally, the tool incorporates two impor- tant functionalities, the first is the provision of statistical support to the analysis by including population statistics for genuine and forged signatures for some selected features, and the second is the incorporation of an automatic dy- namic signature matcher, from which a likelihood ratio (LR) can be obtained from the matching comparison between the known and questioned signatures under analysis.