- -

Training of On-line Handwriting Text Recognizers with Synthetic Text Generated Using the Kinematic Theory of Rapid Human Movements

RiuNet: Repositorio Institucional de la Universidad Politécnica de Valencia

Compartir/Enviar a

Citas

Estadísticas

  • Estadisticas de Uso

Training of On-line Handwriting Text Recognizers with Synthetic Text Generated Using the Kinematic Theory of Rapid Human Movements

Mostrar el registro sencillo del ítem

Ficheros en el ítem

Thumbnail
Nombre: writer_adapt.pdf
Tamaño: 368.0Kb
Formato: PDF
Descripción: Versión del Autor.
Abrir
[Cerrado]
Nombre: icfhr2014.pdf
Tamaño: 287.7Kb
Formato: PDF
Descripción: Versión editorial
Solicitar una copia al autor
dc.contributor.author Martín-Albo Simón, Daniel es_ES
dc.contributor.author Plamondon, Réjean es_ES
dc.contributor.author Vidal Ruiz, Enrique es_ES
dc.date.accessioned 2016-12-16T12:14:46Z
dc.date.available 2016-12-16T12:14:46Z
dc.date.issued 2014-09-01
dc.identifier.isbn 978-1-4799-4335-7
dc.identifier.issn 2167-6445
dc.identifier.uri http://hdl.handle.net/10251/75295
dc.description ©2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. es_ES
dc.description.abstract A method for automatic generation of synthetic handwritten words is presented which is based in the Kinematic Theory and its Sigma-lognormal model. To generate a new synthetic sample, first a real word is modelled using the Sigmalognormal model. Then the Sigma-lognormal parameters are randomly perturbed within a range, introducing human-like variations in the sample. Finally, the velocity function is recalculated taking into account the new parameters. The synthetic words are then used as training data for a Hidden Markov Model based on-line handwritten recognizer. The experimental results confirm the great potential of the Kinematic Theory of rapid human movements applied to writer adaptation. es_ES
dc.description.sponsorship This work was partially supported by the Universitat Politècnica de València under the PMIA-2013 scholarship, the Spanish MEC under FPU scholarship AP2010-0575, the EU’s 7th Framework Programme (FP7/2007-2013) under grant agreement n. 600707 (tranScriptorium) and n. 287576 (CasMaCat) and the Natural Sciences and Engineering Research Council of Canada (NSERC) under grant RGPIN-915. es_ES
dc.format.extent 6 es_ES
dc.language Inglés es_ES
dc.publisher IEEE es_ES
dc.rights Reserva de todos los derechos es_ES
dc.subject.classification LENGUAJES Y SISTEMAS INFORMATICOS es_ES
dc.title Training of On-line Handwriting Text Recognizers with Synthetic Text Generated Using the Kinematic Theory of Rapid Human Movements es_ES
dc.type Comunicación en congreso es_ES
dc.identifier.doi 10.1109/ICFHR.2014.97
dc.relation.projectID info:eu-repo/grantAgreement/EC/FP7/600707/EU/tranScriptorium/ es_ES
dc.relation.projectID info:eu-repo/grantAgreement/ME//AP2010-0575/ES/AP2010-0575/ es_ES
dc.relation.projectID info:eu-repo/grantAgreement/EC/FP7/287576/EU/Cognitive Analysis and Statistical Methods for Advanced Computer Aided Translation/ es_ES
dc.relation.projectID info:eu-repo/grantAgreement/NSERC//RGPIN-915/ es_ES
dc.rights.accessRights Abierto es_ES
dc.contributor.affiliation Universitat Politècnica de València. Escola Tècnica Superior d'Enginyeria Informàtica es_ES
dc.description.bibliographicCitation Martín-Albo Simón, D.; Plamondon, R.; Vidal Ruiz, E. (2014). Training of On-line Handwriting Text Recognizers with Synthetic Text Generated Using the Kinematic Theory of Rapid Human Movements. IEEE. https://doi.org/10.1109/ICFHR.2014.97 es_ES
dc.description.accrualMethod S es_ES
dc.relation.conferencename 14th International Conference on Frontiers in Handwriting Recognition (ICFHR 2014) es_ES
dc.relation.conferencedate September 1-4, 2014 es_ES
dc.relation.conferenceplace Crete, Greece es_ES
dc.relation.publisherversion http://dx.doi.org/10.1109/ICFHR.2014.97 es_ES
dc.type.version info:eu-repo/semantics/publishedVersion es_ES
dc.relation.senia 285429 es_ES
dc.contributor.funder Universitat Politècnica de València es_ES
dc.contributor.funder Ministerio de Educación y Ciencia es_ES
dc.contributor.funder European Commission es_ES
dc.contributor.funder Natural Sciences and Engineering Research Council of Canada es_ES


Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem