Cascading modular U-nets for document image binarization

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

抜粋

In recent years, U-Net has achieved good results in various image processing tasks. However, conventional U-Nets need to be re-trained for individual tasks with enough amount of images with ground-truth. This requirement makes U-Net not applicable to tasks with small amounts of data. In this paper, we propose to use 'modular' U-Nets, each of which is pre-trained to perform an existing image processing task, such as dilation, erosion, and histogram equalization. Then, to accomplish a specific image processing task, such as binarization of historical document images, the modular U-Nets are cascaded with inter-module skip connections and fine-tuned to the target task. We verified the proposed model using the Document Image Binarization Competition (DIBCO) 2017 dataset.

元の言語英語
ホスト出版物のタイトルProceedings - 15th IAPR International Conference on Document Analysis and Recognition, ICDAR 2019
出版者IEEE Computer Society
ページ675-680
ページ数6
ISBN(電子版)9781728128610
DOI
出版物ステータス出版済み - 9 2019
イベント15th IAPR International Conference on Document Analysis and Recognition, ICDAR 2019 - Sydney, オーストラリア
継続期間: 9 20 20199 25 2019

出版物シリーズ

名前Proceedings of the International Conference on Document Analysis and Recognition, ICDAR
ISSN(印刷物)1520-5363

会議

会議15th IAPR International Conference on Document Analysis and Recognition, ICDAR 2019
オーストラリア
Sydney
期間9/20/199/25/19

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

フィンガープリント Cascading modular U-nets for document image binarization' の研究トピックを掘り下げます。これらはともに一意のフィンガープリントを構成します。

  • これを引用

    Kang, S., Iwana, B. K., & Uchida, S. (2019). Cascading modular U-nets for document image binarization. : Proceedings - 15th IAPR International Conference on Document Analysis and Recognition, ICDAR 2019 (pp. 675-680). [8977991] (Proceedings of the International Conference on Document Analysis and Recognition, ICDAR). IEEE Computer Society. https://doi.org/10.1109/ICDAR.2019.00113