Text Image Super Resolution Using Deep Attention Neural Network

Yun Liu, Remina Yano, Hiroshi Watanabe, Takuya Suzuki, Takeshi Chujoh, Tomohiro Ikai

研究成果: Conference contribution

抄録

In this paper, we propose a super-resolution method for text images to improve the accuracy of optical character recognition (OCR). The accuracy of OCR is closely related to the resolution of the image, and when OCR is applied to low resolution text images, satisfactory results are often not obtained. In the proposed method, we extract more representative feature information from text images by combining channel and spatial attention. Furthermore, we propose a new loss function called 'edge loss'. Experimental results show that the recognition accuracy of text images by our SR method is 5.87% higher than that of the original low-resolution images, and also higher than the results of BICUBIC and the baseline model.

本文言語English
ホスト出版物のタイトル2021 IEEE 10th Global Conference on Consumer Electronics, GCCE 2021
出版社Institute of Electrical and Electronics Engineers Inc.
ページ280-282
ページ数3
ISBN(電子版)9781665436762
DOI
出版ステータスPublished - 2021
イベント10th IEEE Global Conference on Consumer Electronics, GCCE 2021 - Kyoto, Japan
継続期間: 2021 10月 122021 10月 15

出版物シリーズ

名前2021 IEEE 10th Global Conference on Consumer Electronics, GCCE 2021

Conference

Conference10th IEEE Global Conference on Consumer Electronics, GCCE 2021
国/地域Japan
CityKyoto
Period21/10/1221/10/15

ASJC Scopus subject areas

  • コンピュータ サイエンスの応用
  • 信号処理
  • 生体医工学
  • 電子工学および電気工学
  • メディア記述
  • 器械工学

フィンガープリント

「Text Image Super Resolution Using Deep Attention Neural Network」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