Development of a pen-based note-taking system for people with acquired visual disabilities

  • Itou Kazuyuki
    Training Center, National Rehabilitation Center for Persons with Disabilities
  • Kiyota Kimiyasu
    Department of Information and Communication Engineering, Kumamoto National College of Technology
  • Ezaki Nobuo
    Information and Control Engineering Department, Toba National College of Maritime Technology
  • Itoh Kazuyuki
    Research Institute, National Rehabilitation Center for Persons with Disabilities
  • Uchimura Keiichi
    Graduate School of Science and Technology, Kumamoto University

Bibliographic Information

Other Title
  • 中途視覚障害者の文字入力を支援する手書き式文字入力システム"Pen-Talker"の開発と評価
  • チュウト シカク ショウガイシャ ノ モジ ニュウリョク オ シエン スル テガキシキ モジ ニュウリョク システム Pen Talker ノ カイハツ ト ヒョウカ

Search this article

Abstract

<p>This study is intended to produce a learning support system for middle-aged people and elderly people with acquired visual disabilities. Our investigation results related to learning tools show that the use of Braille and PCs has decreased in classes at our institution. The primary reason is that finger-reading is difficult for people with acquired visual disabilities. Secondly, the Japanese kanji transfer system is an obstacle to keyboard operation of a PC during classes. We propose a pen-based note-taking system, designated as the `Pen-Talker' on ultra mobile PCs for blind people. A novice user with an acquired visual disability is able to input Japanese characters using the proposed system without much training. The system can recognize 3,126 characters including JIS Level 1 characters. This paper describes the system design concept of the pen-based note-taking system. We also investigate a higher recognition engine based on a fusion of an on-line and off-line recognition algorithm, and a voice assistance function for users. Screen information of a display is given to the user via a built-in screen reader in the system. Our present prototype model is useful as a note pad function using a simple button operation. By applying this additional improvement method, the recognition accuracy increased to 93.7% for 20 subjects. This is a much higher accuracy score than those achieved using previous recognition systems. We also received user evaluations describing satisfaction and the quality of life impact of `Pen-Talker'. These results suggest the benefits of practical use of the proposed system.</p>

Journal

Citations (1)*help

See more

References(23)*help

See more

Related Projects

See more

Details 詳細情報について

Report a problem

Back to top