A Table Detection Method for PDF Documents Based on Convolutional Neural Networks | |
Hao, Leipeng ; Gao, Liangcai ; Yi, Xiaohan ; Tang, Zhi | |
2016 | |
关键词 | table detection convolutional neural networks deep learning document analysis RECOGNITION |
英文摘要 | Because of the better performance of deep learning on many computer vision tasks, researchers in the area of document analysis and recognition begin to adopt this technique into their work. In this paper, we propose a novel method for table detection in PDF documents based on convolutional neutral networks, one of the most popular deep learning models. In the proposed method, some table-like areas are selected first by some loose rules, and then the convolutional networks are built and refined to determine whether the selected areas are tables or not. Besides, the visual features of table areas are directly extracted and utilized through the convolutional networks, while the non-visual information (e.g. characters, rendering instructions) contained in original PDF documents is also taken into consideration to help achieve better recognition results. The primary experimental results show that the approach is effective in table detection.; EI; CPCI-S(ISTP); haoleipeng@pku.edu.cn; glc@pku.edu.cn; chlxyd@pku.edu.cn; tangzhi@pku.edu.cn; 287-292 |
语种 | 英语 |
出处 | 12th IAPR International Workshop on Document Analysis Systems (DAS) |
DOI标识 | 10.1109/DAS.2016.23 |
内容类型 | 其他 |
源URL | [http://ir.pku.edu.cn/handle/20.500.11897/449455] |
专题 | 信息科学技术学院 |
推荐引用方式 GB/T 7714 | Hao, Leipeng,Gao, Liangcai,Yi, Xiaohan,et al. A Table Detection Method for PDF Documents Based on Convolutional Neural Networks. 2016-01-01. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论