Using Stroke-Number-Characteristics for Improving Efficiency of Combined Online and Offline Japanese Character Classifiers

  • Ondrej Velek
  • Masaki Nakagawa
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2423)


We propose a new technique for normalizing likelihood of multiple classifiers prior to their combination. During a combination process we utilize the information about their efficiency correctly recognize a character with a given stroke number. In the beginning, we show that this recognizer’s efficiency based on a stroke number is different for a common on-line and offline recognizer. Later, we demonstrate on elementary combination rules, such as sum-rule and max-rule that using this information increases a recognition rate.


  1. [1]
    H. Tanaka, K. Nakajima, K. Ishigaki, K. Akiyama, M. Nakagawa, Hybrid Pen-Input Character Recognition System Based on Integration of On-Line — Off-Line Recognition, 5th ICDAR (1999) 209–212Google Scholar
  2. [2]
    K. Matsumoto, T. Fukushima, M. Nakagawa, Collection and analysis of on-line handwritten Japanese character patterns, Proc. 6th ICDAR, Seattle, 2001, pp.496–500.Google Scholar
  3. [3]
    O. Velek, S. Jaeger, M. Nakagawa, A warping technique for normalizing likelihood of multiple classi-fiers and its effectiveness in combined on-line/off-line Jap. char.recognition, accepted for IWFHR 2002Google Scholar
  4. [4]
    O. Velek, Ch. Liu, M. Nakagawa, Generating Realistic Kanji Character Images from Online Patterns, Proc. 6th ICDAR (2001) 556–560Google Scholar
  5. [5]
    J. Kittler, M. Hatef, R. Duin, J. Matas, On Combining Classifiers, IEEE PAMI 20(3) (1998) 222–239Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Ondrej Velek
    • 1
  • Masaki Nakagawa
    • 1
  1. 1.Tokyo University of Agr. & TechTokyoJapan

Personalised recommendations