Handwriting prediction based character recognition using recurrent neural network

Shun Nishide*, Hiroshi G. Okuno, Tetsuya Ogata, Jun Tani

*この研究の対応する著者

研究成果

9 被引用数 (Scopus)

抄録

Humans are said to unintentionally trace handwriting sequences in their brains based on handwriting experiences when recognizing written text. In this paper, we propose a model for predicting handwriting sequence for written text recognition based on handwriting experiences. The model is first trained using image sequences acquired while writing text. The image features of sequences are self-organized from the images using Self-Organizing Map. The feature sequences are used to train a neuro-dynamics learning model. For recognition, the text image is input into the model for predicting the handwriting sequence and recognition of the text. We conducted two experiments using ten Japanese characters. The results of the experiments show the effectivity of the model.

本文言語English
ホスト出版物のタイトル2011 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2011 - Conference Digest
ページ2549-2554
ページ数6
DOI
出版ステータスPublished - 2011 12 23
外部発表はい
イベント2011 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2011 - Anchorage, AK, United States
継続期間: 2011 10 92011 10 12

出版物シリーズ

名前Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics
ISSN(印刷版)1062-922X

Other

Other2011 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2011
国/地域United States
CityAnchorage, AK
Period11/10/911/10/12

ASJC Scopus subject areas

  • 電子工学および電気工学
  • 制御およびシステム工学
  • 人間とコンピュータの相互作用

フィンガープリント

「Handwriting prediction based character recognition using recurrent neural network」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル