Feature-based dynamic signature verification under forensic scenarios Nowadays forensic document examiners (FDE) have to analyse more and more signatures captured by digital devices. While they can still use the static image of the signature, it has been proven that the dynamic information contains very discriminative information. This paper is focused on dynamic signature recognition applied to forensic scenarios. An automatic featured-based or global recognition system is considered as some of the features extracted by these systems could be used by FDE in their work. A system comprised of 117 global features is proposed and evaluated with BioSecure DS2 database. A subset of 40 features is selected by SFFS algorithm as the optimal feature vector in the development phase. Results of 10.6% EER are achieved for skilled forgeries which improve previous results using similar approaches. In addition, a set of selected features have been analysed statistically for genuine and forged signatures in order to obtain useful information that could be used by forensic experts in their reports.