Handwriting Prediction Considering Inter-Class Bifurcation Structures

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

抄録

Temporal prediction is a still difficult task due to the chaotic behavior, non-Markovian characteristics, and nonstationary noise of temporal signals. Handwriting prediction is also challenging because of uncertainty arising from inter-class bifurcation structures, in addition to the above problems. For example, the classes '0' and '6' are very similar in terms of their beginning parts; therefore it is nearly impossible to predict their subsequent parts from the beginning part. In other words, '0' and '6' have a bifurcation structure due to ambiguity between classes, and we cannot make a long-term prediction in this context. In this paper, we propose a temporal prediction model that can deal with this bifurcation structure. Specifically, the proposed model learns the bifurcation structure explicitly as a Gaussian mixture model (GMM) for each class as well as the posterior probability of the classes. The final result of prediction is represented as the weighted sum of GMMs using the class probabilities as weights. When multiple classes have large weights, the model can handle a bifurcation and thus avoid an inaccurate prediction. The proposed model is formulated as a neural network including long short-term memories and is thus trained in an end-to-end manner. The proposed model was evaluated on the UNIPEN online handwritten character dataset, and the results show that the model can catch and deal with the bifurcation structures.

本文言語英語
ホスト出版物のタイトルProceedings - 2020 17th International Conference on Frontiers in Handwriting Recognition, ICFHR 2020
出版社Institute of Electrical and Electronics Engineers Inc.
ページ103-108
ページ数6
ISBN(電子版)9781728199665
DOI
出版ステータス出版済み - 9 2020
イベント17th International Conference on Frontiers in Handwriting Recognition, ICFHR 2020 - Dortmund, ドイツ
継続期間: 9 7 20209 10 2020

出版物シリーズ

名前Proceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR
2020-September
ISSN(印刷版)2167-6445
ISSN(電子版)2167-6453

会議

会議17th International Conference on Frontiers in Handwriting Recognition, ICFHR 2020
国/地域ドイツ
CityDortmund
Period9/7/209/10/20

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

「Handwriting Prediction Considering Inter-Class Bifurcation Structures」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