Detecting Text in Natural Image with Connectionist Text Proposal Network
文献类型：会议论文
| 作者 | Zhi Tian; Weilin Huang; Tong He; Pan He; Yu Qiao |
| 出版日期 | 2016 |
| 会议名称 | ECCV2016 |
| 会议地点 | 荷兰阿姆斯特丹 |
| 英文摘要 | We propose a novel Connectionist Text Proposal Network (CTPN) that accurately localizes text lines in natural image. The CTPN detects a text line in a sequence of ne-scale text proposals directly in convolutional feature maps. We develop a vertical anchor mechanism that jointly predicts location and text/non-text score of each xed-width proposal, considerably improving localization accuracy. The sequential proposals are naturally connected by a recurrent neural network, which is seamlessly incorporated into the convolutional network, resulting in an end-to-end trainable model. This allows the CTPN to explore rich context information of image, making it powerful to detect extremely ambiguous text. The CTPN works reliably on multi-scale and multi- language text without further post-processing, departing from previous bottom-up methods requiring multi-step post ltering. It achieves 0.88 and 0.61 F-measure on the ICDAR 2013 and 2015 benchmarks, surpass- ing recent results [8, 35] by a large margin. The CTPN is computationally e cient with 0:14s=image, by using the very deep VGG16 model [27]. Online demo is available: http://textdet.com/. |
| 收录类别 | EI |
| 语种 | 英语 |
| 源URL | [http://ir.siat.ac.cn:8080/handle/172644/10011]  |
| 专题 | 深圳先进技术研究院_集成所 |
| 作者单位 | 2016 |
| 推荐引用方式 GB/T 7714 | Zhi Tian,Weilin Huang,Tong He,et al. Detecting Text in Natural Image with Connectionist Text Proposal Network[C]. 见:ECCV2016. 荷兰阿姆斯特丹. |
入库方式： OAI收割
来源：深圳先进技术研究院
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。