A Segmentation Method for Touching Handwritten Japanese Characters

  • Hiromitsu Nishimura
  • Hisashi Ikeda
  • Yasuaki Nakano
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1655)


The purpose of this paper is the segmentation of touching handwritten Japanese characters to enable each segmented character to be recognized. Though segmentation methods cooperating with recognition for the simple characters are known, they are not applicable to complicated characters such as kanji. To estimate the ability of segmentation itself, our method does not use any results of character recognition but segments touching characters using some specific features of character patterns. Linear components in patterns are extracted as features and a segmentation method based on them is proposed. A database, which contains character pattern and ground truth is constructed. In the database the ground truth data describe the correct areas of touching points judged by plural human subjects. As a result of the segmentation experiments, about 64% of touching patterns can be segmented at appropriate points. This correct segmentation rate is automatically calculated consulting the ground truths.


Ground Truth Segmentation Method Character Recognition Linear Component Ground Truth Data 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    H. Fujisawa, Y. Nakano and K. Kurino: Segmentation Methods for Character Recognition: From Segmentation to Document Structure Analysis. Proc. of IEEE. 80-7 (1992) 1079–1092CrossRefGoogle Scholar
  2. 2.
    Hidefumi Ino, Kazuki Saruta, Nei Kato and Yoshiaki Nemoto: Handwritten Address Segmentation Algorithm Based on Stroke Information. ISSN. 38-2 1997Google Scholar
  3. 3.
    Hirobumi Yamada and Yasuaki Nakano: Cursive Handwritten Word Recognition Using Multiple Segmentation Determined by Contour Analysis. IEICE. Trans. INF&SYSTE. E79-D-5 (1996)Google Scholar
  4. 4.
    Masaomi Nakajima and Yuji Yonekura: Handwritten Character Segmentation Using Smoothing Histgram and Discriminant Analysys. IEICE. Trans. INF&SYSTE. ???J78-D-2-7 (1995)Google Scholar
  5. 5.
    Yayoi Kobayashi and Jun Tsukumo: Handwritten Characters Recognition Using Contexts. IEICE. Trans. ???PRU91-67 (1991) 39–46 (In Japanese)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1999

Authors and Affiliations

  • Hiromitsu Nishimura
    • 1
  • Hisashi Ikeda
    • 2
  • Yasuaki Nakano
    • 1
  1. 1.Dept. of Information EngineeringShinshu UniversityNaganoJapan
  2. 2.Central Research LaboratoryHitachi Ltd.KokubunjiJapan

Personalised recommendations