Data augmentation for ancient characters via blend-font net

Xiaolu Ren*, Sei Ichiro Kamata

*この研究の対応する著者

研究成果: Conference contribution

抄録

Historical documents record a lot of precious information through ancient characters. However, some problems like unbalanced character samples and intra-class multi-modality inside the documents are critical factors that limit the performance of existing character recognition technologies. Therefore, we propose a two-stage font generation model, Blend-Font Net, which use some easy to get modern character datasets to augment ancient character dataset and solve these mentioned problems based on blend-font strategy. The model generates new samples by extracting and modifying the font information from the character image. A font generation model learns the mapping between different fonts in the first stage, and the slightly modified model learns how to generate samples that blend two different fonts in the second stage. Extra samples are generated for balancing historical documents dataset through the proposed model. Experiments show that our results have diverse visual effects and improve the accuracy of the text recognition network. Furthermore, the proposed method shows a broad application prospect in similar works as no font label required and multi-modality problem solved.

本文言語English
ホスト出版物のタイトルThirteenth International Conference on Digital Image Processing, ICDIP 2021
編集者Xudong Jiang, Hiroshi Fujita
出版社SPIE
ISBN(電子版)9781510646001
DOI
出版ステータスPublished - 2021
イベント13th International Conference on Digital Image Processing, ICDIP 2021 - Singapore, Singapore
継続期間: 2021 5 202021 5 23

出版物シリーズ

名前Proceedings of SPIE - The International Society for Optical Engineering
11878
ISSN(印刷版)0277-786X
ISSN(電子版)1996-756X

Conference

Conference13th International Conference on Digital Image Processing, ICDIP 2021
国/地域Singapore
CitySingapore
Period21/5/2021/5/23

ASJC Scopus subject areas

  • 電子材料、光学材料、および磁性材料
  • 凝縮系物理学
  • コンピュータ サイエンスの応用
  • 応用数学
  • 電子工学および電気工学

フィンガープリント

「Data augmentation for ancient characters via blend-font net」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