Fulltext

Combining diverse systems for handwritten text line recognition

Liwicki, Marcus ; Bunke, Horst ; Pittman, James ; Knerr, Stefan

In: Machine Vision and Applications, 2011, vol. 22, no. 1, p. 39-51

Ajouter à la liste personnelle
    Titre
    • Combining diverse systems for handwritten text line recognition
    Auteur
    • Liwicki, Marcus. Institute of Computer Science and Applied Mathematics, University of Bern, Neubrückstrasse 10, 3012, Bern, Switzerland
    • Bunke, Horst. Institute of Computer Science and Applied Mathematics, University of Bern, Neubrückstrasse 10, 3012, Bern, Switzerland
    • Pittman, James. Microsoft, Redmond, USA
    • Knerr, Stefan. Vision Objects, Nantes Cedex 3, France
    Type de document
    • Postprint
    Langue
    • Anglais
    Publié dans
    • Machine Vision and Applications, 2011, vol. 22, no. 1, p. 39-51. Springer-Verlag
    Autre version électronique
    Classification
    • Technologie, Sciences de l'ingénieur
    Identifiant OAI-PMH
    • oai:doc.rero.ch:311026
    Summary
    In this paper, we present a recognition system for on-line handwritten texts acquired from a whiteboard. The system is based on the combination of several individual classifiers of diverse nature. Recognizers based on different architectures (hidden Markov models and bidirectional long short-term memory networks) and on different sets of features (extracted from on-line and off-line data) are used in the combination. In order to increase the diversity of the underlying classifiers and fully exploit the current state-of-the-art in cursive handwriting recognition, commercial recognition systems have been included in the combined system, leading to a final word level accuracy of 86.16%. This value is significantly higher than the performance of the best individual classifier (81.26%)