This is a research I started through a collaboration with forensic handwriting examiners of the Italian Graphological Association (AGI).
Dynamic signature analysis in forensic settings
Technological advances have brought digital assistants into various areas of human life. Portable devices now support natural input methods and offer improved options for digitizing handwritten content. Finger writing on touch screens and electronic pen movements can be recorded. This opens up possibilities for integrating data protection and automatic signature verification in pen-based devices. However, the research and development of signature verification lack synchronization between forensic and biometric communities.
Publications
Diaz, M., Ferrer, M.A. & Vessio, G. Explainable offline automatic signature verifier to support forensic handwriting examiners. Neural Computing and Applications (2024)
Mazzolini, D., Mignone, P., Pavan, P. & Vessio, G. An easy-to-explain decision support framework for forensic analysis of dynamic signatures. Forensic Science International: Digital Investigation (2021)
Mazzolini, D., Pavan, P., Pirlo, G. & Vessio, G. Towards a Decision Support Framework for Forensic Analysis of Dynamic Signatures. IRCDL (2020)
Impedovo, D., Pirlo, G., Sarcinella, L. & Vessio, G. An Evolutionary Approach to address Interoperability Issues in Multi-Device Signature Verification. SMC (2019)
In October 2020, the third edition of the "Dynamic Signature Analysis" training course, organized by the Italian Graphological Association in collaboration with Arigrafmilano, was completed. During the course, I presented a method to assist forensic handwriting examiners in dynamic signature verification that is effective and easy to explain in a work environment. The technique aims to provide experts with an objective assessment tool to make reproducible and less questionable inferences, which would not be perceived as a black box, as is usually the case with more sophisticated biometric verification systems. Indeed, we want to promote synergies between the forensic and biometric communities, which need to be improved.