Deep BLSTM neural networks for unconstrained continuous handwritten text recognition

Volkmar Frinken, Seiichi Uchida

研究成果: Chapter in Book/Report/Conference proceedingConference contribution

18 被引用数 (Scopus)

抄録

Recently, two different trends in neural network-based machine learning could be observed. The first one are the introduction of Bidirectional Long Short-Term Memory (BLSTM) neural networks (NN) which made sequences with long-distant dependencies amenable for neural network-based processing. The second one are deep learning techniques, which greatly increased the performance of neural networks, by making use of many hidden layers. In this paper, we propose to combine these two ideas for the task of unconstrained handwriting recognition. Extensive experimental evaluation on the IAM database demonstrate an increase of the recognition performance when using deep learning approaches over commonly used BLSTM neural networks, as well as insight into how different types of hidden layers affect the recognition accuracy.

本文言語英語
ホスト出版物のタイトル13th IAPR International Conference on Document Analysis and Recognition, ICDAR 2015 - Conference Proceedings
出版社IEEE Computer Society
ページ911-915
ページ数5
ISBN(電子版)9781479918058
DOI
出版ステータス出版済み - 11 20 2015
イベント13th International Conference on Document Analysis and Recognition, ICDAR 2015 - Nancy, フランス
継続期間: 8 23 20158 26 2015

出版物シリーズ

名前Proceedings of the International Conference on Document Analysis and Recognition, ICDAR
2015-November
ISSN(印刷版)1520-5363

その他

その他13th International Conference on Document Analysis and Recognition, ICDAR 2015
国/地域フランス
CityNancy
Period8/23/158/26/15

All Science Journal Classification (ASJC) codes

  • コンピュータ ビジョンおよびパターン認識

フィンガープリント

「Deep BLSTM neural networks for unconstrained continuous handwritten text recognition」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