How Does a CNN Manage Different Printing Types?

Shota Ide, Seiichi Uchida

研究成果: 著書/レポートタイプへの貢献会議での発言

1 引用 (Scopus)

抜粋

In past OCR research, different OCR engines are used for different printing types, i.e., machine-printed characters, handwritten characters, and decorated fonts. A recent research, however, reveals that convolutional neural networks (CNN) can realize a universal OCR, which can deal with any printing types without pre-classification into individual types. In this paper, we analyze how CNN for universal OCR manage the different printing types. More specifically, we try to find where a handwritten character of a class and a machine-printed character of the same class are 'fused' in CNN. For analysis, we use two different approaches. The first approach is statistical analysis for detecting the CNN units which are sensitive (or insensitive) to type difference. The second approach is network-based visualization of pattern distribution in each layer. Both analyses suggest the same trend that types are not fully fused in convolutional layers but the distributions of the same class from different types become closer in upper layers.

元の言語英語
ホスト出版物のタイトルProceedings - 14th IAPR International Conference on Document Analysis and Recognition, ICDAR 2017
出版者IEEE Computer Society
ページ1004-1009
ページ数6
ISBN(電子版)9781538635865
DOI
出版物ステータス出版済み - 7 2 2017
イベント14th IAPR International Conference on Document Analysis and Recognition, ICDAR 2017 - Kyoto, 日本
継続期間: 11 9 201711 15 2017

出版物シリーズ

名前Proceedings of the International Conference on Document Analysis and Recognition, ICDAR
1
ISSN(印刷物)1520-5363

その他

その他14th IAPR International Conference on Document Analysis and Recognition, ICDAR 2017
日本
Kyoto
期間11/9/1711/15/17

    フィンガープリント

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

これを引用

Ide, S., & Uchida, S. (2017). How Does a CNN Manage Different Printing Types?Proceedings - 14th IAPR International Conference on Document Analysis and Recognition, ICDAR 2017 (pp. 1004-1009). (Proceedings of the International Conference on Document Analysis and Recognition, ICDAR; 巻数 1). IEEE Computer Society. https://doi.org/10.1109/ICDAR.2017.167