Identificador persistente para citar o vincular este elemento: http://hdl.handle.net/10553/136826
Título: Online signature verification based on the lagrange formulation with 2D and 3D robotic models
Autores/as: Diaz, Moises 
Ferrer, Miguel A. 
Gil, Juan M. 
Rodriguez, Rafael 
Zhang, Peirong
Jin, Lianwen
Clasificación UNESCO: 331117 Equipos de verificación
330405 Sistemas de reconocimiento de caracteres
Palabras clave: Online signature verification
Generalized coordinates
Torques
Biometrics
Fecha de publicación: 2025
Proyectos: Robusteciendo Las Biometrías Del Movimiento de la Mano Mediante la Síntesis de Su Timbre Usando Métodos Computacionalesy Robóticos 
Detección de Movimientos Generados por Humanos y Máquinas. 
Publicación seriada: Pattern Recognition 
Resumen: Online Signature Verification commonly relies on function-based features, such as time-sampled horizontal and vertical coordinates, as well as the pressure exerted by the writer, obtained through a digitizer. Although inferring additional information about the writer's arm pose, kinematics, and dynamics based on digitizer data can be useful, it constitutes a challenge. In this paper, we tackle this challenge by proposing a new set of features based on the dynamics of online signatures. These new features are inferred through a Lagrangian formulation, obtaining the sequences of generalized coordinates and torques for 2D and 3D robotic arm models. By combining kinematic and dynamic robotic features, our results demonstrate their significant effectiveness for online automatic signature verification and achieving state-of-the-art results when integrated into deep learning models.
URI: http://hdl.handle.net/10553/136826
ISSN: 0031-3203
DOI: 10.1016/j.patcog.2025.111581
Fuente: Pattern Recognition [ISSN 0031-3203], v. 164, (Agosto 2025)
Colección:Artículos
Adobe PDF (2,6 MB)
Vista completa

Google ScholarTM

Verifica

Altmetric


Comparte



Exporta metadatos



Los elementos en ULPGC accedaCRIS están protegidos por derechos de autor con todos los derechos reservados, a menos que se indique lo contrario.