Text Detection in Manga by Deep Region Proposal, Classification, and Regression

Wei Ta Chu, Chih Chi Yu

研究成果: Conference contribution

2 引文 斯高帕斯(Scopus)

摘要

Text in manga presents high variations and different contextual information, and existing scene text detection methods are not directly applicable. We propose two approaches based on deep networks to detect text in manga. In the first approach, features extracted from multiple CNNs are joined and then fed to a combination of a classification network and a regression network. In the second approach, region proposal, feature extraction, and classification/regression, are taken together in a single deep network. The evaluation results show that the first approach achieves performance comparable to the current state of the art, while the second approach yields a big performance leap over existing ones.

原文English
主出版物標題VCIP 2018 - IEEE International Conference on Visual Communications and Image Processing
發行者Institute of Electrical and Electronics Engineers Inc.
ISBN(電子)9781538644584
DOIs
出版狀態Published - 2018 七月 2
事件33rd IEEE International Conference on Visual Communications and Image Processing, VCIP 2018 - Taichung, Taiwan
持續時間: 2018 十二月 92018 十二月 12

出版系列

名字VCIP 2018 - IEEE International Conference on Visual Communications and Image Processing

Conference

Conference33rd IEEE International Conference on Visual Communications and Image Processing, VCIP 2018
國家/地區Taiwan
城市Taichung
期間18-12-0918-12-12

All Science Journal Classification (ASJC) codes

  • 電腦網路與通信
  • 訊號處理

指紋

深入研究「Text Detection in Manga by Deep Region Proposal, Classification, and Regression」主題。共同形成了獨特的指紋。

引用此