Data Augmentation for Historical Documents via Cascade Variational Auto-Encoder

Guanyu Cao, Sei Ichiro Kamata

研究成果: Conference contribution

抄録

In this paper, we introduce a novel model based on Variational Auto-Encoder (VAE) that is able to find subclasses of categories and generate new samples with fidelity to the subclass in an unsupervised way. In generating characters from historical documents, this model helps generated characters to avoid ambiguity in the case where there are multiple writing styles of one character without being labeled. With this model we augment historical Japanese document dataset to make it more balanced. The model is trained in two steps. In the first step, the model learns the data distribution and learns to map character images into basic shape vectors. In the second step, the model learns to generate new samples conditioned on the basic shape vectors. The generated samples are more robust against intra-class multi-modality. With the usage of augmented dataset, the recognition rate is improved. Ablation study is performed to evaluate the effectiveness of data augmentation.

本文言語English
ホスト出版物のタイトルProceedings of the 2019 IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2019
出版社Institute of Electrical and Electronics Engineers Inc.
ページ340-345
ページ数6
ISBN(電子版)9781728133775
DOI
出版ステータスPublished - 2019 9
イベント2019 IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2019 - Kuala Lumpur, Malaysia
継続期間: 2019 9 172019 9 19

出版物シリーズ

名前Proceedings of the 2019 IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2019

Conference

Conference2019 IEEE International Conference on Signal and Image Processing Applications, ICSIPA 2019
CountryMalaysia
CityKuala Lumpur
Period19/9/1719/9/19

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Health Informatics
  • Artificial Intelligence

フィンガープリント 「Data Augmentation for Historical Documents via Cascade Variational Auto-Encoder」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。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