• DocumentCode
    1841423
  • Title

    High-level verification of handwritten numeral strings

  • Author

    Oliveira, L.S. ; Sabourin, R. ; Bortolozzi, F. ; Suen, C.Y.

  • Author_Institution
    Pontificia Univ. Catolica do Parana, Curitiba, Brazil
  • fYear
    2001
  • fDate
    37165
  • Firstpage
    36
  • Lastpage
    43
  • Abstract
    In this paper we discuss the use of high-level verification on handwritten numeral strings. First of all, we introduce the concept of levels of verification and present the baseline system used to carry out the experiments. Two different strategies were developed: absolute and one-to-one verifiers. A thorough error analysis is also presented in order to identify under which conditions high-level verification is more appropiate. Experimental results are presented on NIST SD19 database
  • Keywords
    error analysis; handwritten character recognition; pattern classification; NIST SDI 9 database; absolute verifiers; error analysis; handwritten numeral strings; high-level verification; one-to-one verifiers; pattern classification; Computer vision; Costs; Databases; Error analysis; Focusing; Handwriting recognition; Image segmentation; Machine intelligence; NIST; Pattern recognition;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computer Graphics and Image Processing, 2001 Proceedings of XIV Brazilian Symposium on
  • Conference_Location
    Florianopolis
  • Print_ISBN
    0-7695-1330-1
  • Type

    conf

  • DOI
    10.1109/SIBGRAPI.2001.963035
  • Filename
    963035