Handwriting Prediction Considering Inter-Class Bifurcation Structures

Masaki Yamagata, Hideaki Hayashi, Seiichi Uchida

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)


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.

Original languageEnglish
Title of host publicationProceedings - 2020 17th International Conference on Frontiers in Handwriting Recognition, ICFHR 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages6
ISBN (Electronic)9781728199665
Publication statusPublished - Sept 2020
Event17th International Conference on Frontiers in Handwriting Recognition, ICFHR 2020 - Dortmund, Germany
Duration: Sept 7 2020Sept 10 2020

Publication series

NameProceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR
ISSN (Print)2167-6445
ISSN (Electronic)2167-6453


Conference17th International Conference on Frontiers in Handwriting Recognition, ICFHR 2020

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Computer Vision and Pattern Recognition


Dive into the research topics of 'Handwriting Prediction Considering Inter-Class Bifurcation Structures'. Together they form a unique fingerprint.

Cite this