Script identification in the wild via discriminative convolutional neural network
详细信息 查看全文
- 作者：Baoguang Shi shibaoguang@gmail.com" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Xiang Bai ; xbai@hust.edu.cn" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Cong Yao yaocong2010@gmail.com" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae
- 关键词：Script identification ; Convolutional neural network ; Mid-level representation ; Discriminative clustering ; Dataset
- 刊名：Pattern Recognition
- 出版年：2016
- 出版时间：April 2016
- 年：2016
- 卷：52
- 期：Complete
- 页码：448-458
- 全文大小：3838 K
文摘
- •
We study a new and important topic: script identification in scene text images.
- •
The proposed DiscCNN combines deep features and the mid-level representation.
- •
DiscCNN learns special characteristics of scripts from training data automatically.
- •
DiscCNN achieves state-of-the-art performances on scene, video and document scripts.
- •
A large-scale in-the-wild script identification dataset is proposed.