Recent developments in the study of rapid human movements with the kinematic theory: Applications to handwriting and signature synthesis

Réjean Plamondon 1 Christian O’reilly 1 Javier Galbally 2 Abdullah Almaksour 3 Éric Anquetil 3
1 Scribens - Laboratoire Scribens, École Polytechnique de Montréal, Canada
2 ATVS - Biometric Recognition Group
ATVS - ATVS - Biometric Recognition Group
3 IntuiDoc - intuitive user interaction for document
IRISA-D6 - MEDIA ET INTERACTIONS
Abstract : Human movement modeling can be of great interest for the design of pattern recognition systems relying on the understanding of the fine motor control (such as on-line handwriting recognition or signature verification) as well as for the development of intelligent systems involving in a way or another the processing of human movements. In this paper, we briefly list the different models that have been proposed in order to characterize the handwriting process and focus on a representation involving a vectorial summation of lognormal functions: the Sigma-lognormal model. Then, from a practical perspective, we describe a new stroke extraction algorithm suitable for the reverse engineering of handwriting signals. In the following section it is shown how the resulting representation can be used to study the writer and signer variability. We then report on two joint projects dealing with the automatic generation of synthetic specimens for the creation of large databases. The first application concerns the automatic generation of totally synthetic signature specimens for the training and evaluation of verification performances of automatic signature recognition systems. The second application deals with the synthesis of handwritten gestures for speeding up the learning process in customizable on-line recognition systems to be integrated in electronic pen pads.
Keywords : Human movement modeling Kinematic theory Motor control Sigma-lognormal model Customizable on-line recognition systems Signature verification Handwriting recognition Gesture synthesis Signature synthesis
Type de document :
Article dans une revue
Pattern Recognition Letters, Elsevier, 2014, 35, pp.225-235. 〈10.1016/j.patrec.2012.06.004〉
Liste complète des métadonnées

Littérature citée [29 références]  Voir  Masquer  Télécharger
https://hal.archives-ouvertes.fr/hal-00801866
Contributeur : Eric Anquetil <>
Soumis le : jeudi 4 décembre 2014 - 16:23:52
Dernière modification le : vendredi 25 mai 2018 - 01:07:47
Document(s) archivé(s) le : lundi 9 mars 2015 - 05:55:35

Fichier

Article PRL_v10_AfterReviews2....
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

IRISA | IRISA-D6 | INRIA | UR1-UFR-ISTIC | UNIV-RENNES

Citation

Réjean Plamondon, Christian O’reilly, Javier Galbally, Abdullah Almaksour, Éric Anquetil. Recent developments in the study of rapid human movements with the kinematic theory: Applications to handwriting and signature synthesis. Pattern Recognition Letters, Elsevier, 2014, 35, pp.225-235. 〈10.1016/j.patrec.2012.06.004〉. 〈hal-00801866〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

547

Téléchargements de fichiers

452

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD