Schrapel, MaximilianGrannemann, DennisRohs, MichaelMühlhäuser, MaxReuter, ChristianPfleging, BastianKosch, ThomasMatviienko, AndriiGerling, Kathrin|Mayer, SvenHeuten, WilkoDöring, TanjaMüller, FlorianSchmitz, Martin2022-08-312022-08-312022https://dl.gi.de/handle/20.500.12116/39215Although in many cases contracts can be made or ended digitally, laws require handwritten signatures in certain cases. Forgeries are a major challenge with digital contracts, as their validity is not always immediately apparent without forensic methods. Illiteracy or disabilities may result in a person being unable to write their full name. In this case x-mark signatures are used, which require a witness for validity. In cases of suspected fraud, the relationship of the witnesses must be questioned, which involves a great amount of effort. In this paper we use audio and motion data from a digital pen to identify users via handwritten symbols. We evaluated the performance our approach for 19 symbols in a study with 30 participants. We found that x-marks offer fewer individual features than other symbols like arrows or circles. By training on three samples and averaging three predictions we reach a mean F1-score of F 1 = 0.87, using statistical and spectral features fed into SVMsenDigital PensSignature AuthenticationSigning DocumentsPattern RecognitionHandwriting RecognitionMotor ImpairmentsAccessibilityText/Conference Paper10.1145/3543758.3543764