Active-DTW : A Generative Classifier that combines Elastic Matching with Active Shape Modeling for Online Handwritten Character Recognition - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2006

Active-DTW : A Generative Classifier that combines Elastic Matching with Active Shape Modeling for Online Handwritten Character Recognition

Résumé

Developing handwriting recognition systems that are fast and highly reliable is a challenging problem that has become increasingly relevant following the broad acceptance of hand-held devices that use pen based handwriting inputs. Generative classifiers offer a promising solution in combination with discriminative classifiers for addressing this challenge. This paper describes a novel generative classifier - Active-DTW, that combines Active Shape Models with Elastic Matching. Experimental results show that the Active-DTW classifier shows substantial promise as a generative classifier.
Fichier principal
Vignette du fichier
cr1099193116304.pdf (109.69 Ko) Télécharger le fichier
Loading...

Dates et versions

inria-00104782 , version 1 (09-10-2006)

Identifiants

  • HAL Id : inria-00104782 , version 1

Citer

Muralikrishna Sridha, Dinesh Mandalapu, Mehul Patel. Active-DTW : A Generative Classifier that combines Elastic Matching with Active Shape Modeling for Online Handwritten Character Recognition. Tenth International Workshop on Frontiers in Handwriting Recognition, Université de Rennes 1, Oct 2006, La Baule (France). ⟨inria-00104782⟩

Collections

IWFHR10
171 Consultations
324 Téléchargements

Partager

Gmail Facebook X LinkedIn More