E-biosign: stylus- and finger-input multi-device database for dynamic signature recognition

Abstract

This paper describes the design, acquisition process and a baseline evaluation of e-BioSign, a new database of dynamic signature and handwriting. e-BioSign is comprised of 5 devices in total, three Wacom devices (DTU-500, DTU-530 and STU 1031) specifically designed to capture dynamic signatures and handwriting, and two Samsung general purpose tablets (Samsung Galaxy Note 10.1 and Samsung ATIV). For these two Samsung tablets data is collected using a pen stylus but also the finger to study the performance of signature verification in a mobile scenario. Data was collected in two sessions for 70 subjects, and includes dynamic information of the signature, the full name and number sequences. For signature and the full name skilled forgeries were also performed. A signature baseline evaluation is carried out for a predefined recognition system based on DTW, achieving a benchmark performance for each of the devices. The use of finger for signing achieves good results for the case of random forgeries (less than 1% EER), but the performance is degraded significantly for the case of skilled forgeries compared to the case using the pen stylus.