Introducing local distance-based features to temporal convolutional neural networks

Brian Kenji Iwana, Minoru Mori, Akisato Kimura, Seiichi Uchida

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

2 被引用数 (Scopus)

抄録

In this paper, we propose the use of local distance-based features determined by Dynamic Time Warping (DTW) for temporal Convolutional Neural Networks (CNN). Traditionally, DTW is used as a robust distance metric for time series patterns. However, this traditional use of DTW only utilizes the scalar distance metric and discards the local distances between the dynamically matched sequence elements. This paper proposes recovering these local distances, or DTW features, and utilizing them for the input of a CNN. We demonstrate that these features can provide additional information for the classification of isolated handwritten digits and characters. Furthermore, we demonstrate that the DTW features can be combined with the spatial coordinate features in multi-modal fusion networks to achieve state-of-the-art accuracy on the Unipen online handwritten character datasets.

本文言語英語
ホスト出版物のタイトルProceedings - 2018 16th International Conference on Frontiers in Handwriting Recognition, ICFHR 2018
出版社Institute of Electrical and Electronics Engineers Inc.
ページ92-97
ページ数6
ISBN(電子版)9781538658758
DOI
出版ステータス出版済み - 12 5 2018
イベント16th International Conference on Frontiers in Handwriting Recognition, ICFHR 2018 - Niagara Falls, 米国
継続期間: 8 5 20188 8 2018

出版物シリーズ

名前Proceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR
2018-August
ISSN(印刷版)2167-6445
ISSN(電子版)2167-6453

その他

その他16th International Conference on Frontiers in Handwriting Recognition, ICFHR 2018
国/地域米国
CityNiagara Falls
Period8/5/188/8/18

All Science Journal Classification (ASJC) codes

  • コンピュータ サイエンスの応用
  • 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

「Introducing local distance-based features to temporal convolutional neural networks」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