• DocumentCode
    2504080
  • Title

    Computer Assisted Transcription of Text Images: Results on the GERMANA Corpus and Analysis of Improvements Needed for Practical Use

  • Author

    Romero, Verónica ; Toselli, Alejandro H. ; Vidal, Enrique

  • Author_Institution
    Inst. Tecnol. de Inf., Univ. Politec. de Valencia, Valencia, Spain
  • fYear
    2010
  • fDate
    23-26 Aug. 2010
  • Firstpage
    2017
  • Lastpage
    2020
  • Abstract
    We present a study of the application of Computer Assisted Transcription of Text Images (CATTI) to a task which is much closer to real applications than other tasks previously studied. The new task consists in the transcription of a new publicly available historic handwritten document, called GERMANA. A detailed analysis of the main factors influencing the system performance are exposed and some strategies to circumvent them are proposed.
  • Keywords
    document image processing; handwritten character recognition; text analysis; GERMANA corpus; computer assisted transcription; handwritten document; text images; Context; Erbium; Feature extraction; Hidden Markov models; Humans; Training; Vocabulary; Handwritten text image recognition; interactive predictive framework;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Pattern Recognition (ICPR), 2010 20th International Conference on
  • Conference_Location
    Istanbul
  • ISSN
    1051-4651
  • Print_ISBN
    978-1-4244-7542-1
  • Type

    conf

  • DOI
    10.1109/ICPR.2010.497
  • Filename
    5597257
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=2504080