Unsupervised Learning of Stroke Tagger for Online Kanji Handwriting Recognition

Mathieu Blondel, Kazuhiro Seki, Kuniaki UeharaICPR 2010 · OpenReview

Abstract

Traditionally, HMM-based approaches to online Kanji handwriting recognition have relied on a hand-made dictionary, mapping characters to primitives such as strokes or substrokes. We present an unsupervised way to learn a stroke tagger from data, which we eventually use to automatically generate such a dictionary. In addition to not requiring a prior hand-made dictionary, our approach can improve the recognition accuracy by exploiting unlabeled data when the amount of labeled data is limited.
BibTeX
@inproceedings{blondel2010unsupervised,
  author = {Mathieu Blondel and Kazuhiro Seki and Kuniaki Uehara},
  title = {{Unsupervised Learning of Stroke Tagger for Online Kanji Handwriting Recognition}},
  booktitle = {ICPR},
  year = {2010},
  url = {https://openreview.net/forum?id=yqyulZlD_71},
}

Loading related content...

Figure