A Table Detection Method for PDF Documents Based on Convolutional Neural Networks
Authors:
- Leipeng HaoLHLeipeng Hao
- Liangcai GaoLGLiangcai Gao
- Xiaohan YiXYXiaohan Yi
- Zhi TangZTZhi Tang
- 1 April 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 287-292
Abstract
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.Keywords
This publication has 10 references indexed in Scilit:
- Recognition of Handwritten Characters in Chinese Legal Amounts by Stacked Autoencoders2014
- Dataset, Ground-Truth and Performance Metrics for Table Detection Evaluation2012
- A Table Detection Method for Multipage PDF Documents via Visual Seperators and Tabular Structures2011
- PDF-TREX: An Approach for Recognizing and Extracting Tables from PDF Documents2009
- Table Recognition and Understanding from PDF FilesNinth International Conference on Document Analysis and Recognition (ICDAR 2007), 2007
- TableSeer2007
- Design of an end-to-end method to extract information from tablesInternational Journal on Document Analysis and Recognition (IJDAR), 2006
- Applying the T-Recs table recognition system to the business letter domain2002
- Two Geometric Algorithms for Layout Analysis2002
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998