An Off-line Character Recognition Method based on an Elastic Membrane Model

• YANAGIDA Tadashi

  Department of Computer Science Tokyo University of Agriculture and Technology

• NAGASAKI Takeshi

  Department of Computer Science Tokyo University of Agriculture and Technology

• NAKAGAWA Masaki

  Department of Computer Science Tokyo University of Agriculture and Technology

Bibliographic Information

Other Title

• 弾性膜モデルに基づくオフライン手書き文字認識

Abstract

This paper presents a model dependent pattern normalization method based on an Elastic Membrane Model which adsorbs local deformation or variation in handwritten Japanese character patterns. In experimental results, the 98.3% recognition rate has been obtained for the ETL9B Hiragana characters. Moreover, a high recognition rate has been achieved for on-line handwritten Hiragana patterns written without any writings.

Journal

• Technical report of IEICE. PRMU

  Technical report of IEICE. PRMU 97 (558), 45-52, 1998-02-19

  The Institute of Electronics, Information and Communication Engineers

Keywords

• off-line character recognition
• pattern normalization
• dynamic relaxation
• elastic membrane model

Details

• CRID: 1573950402205553664
• NII Article ID: 110003274337
• NII Book ID: AN10541106
• Text Lang: ja
• Data Source:
  • CiNii Articles