- 期刊
- OpenAccess
Deformable Convolutional Neuron Network Model for Detecting Tables and Columns from Document Images
摘要
Tables are usually used to present the main points of a document so that readers can quickly understand the content of the document. This study proposed a novel deformable convolutional neural network model for table detection to identify and extract tables from electronic document images. The model can perform table detection and table structure recognition at the same time, and more effectively detect the location of tables and columns. The proposed model is evaluated using Marmot extended dataset and the experimental results show that the table detection cycle is reduced, the computation time is shortened, and the overall efficiency is improved. Compared with other studies, the proposed model has achieved better table detection results in terms of precision, recall, and F1-score.
延伸閱讀
- Kang, H. P. (2013). Improving Convolutional Neural Networks by Separable Filters [master's thesis, National Tsing Hua University]. Airiti Library. https://doi.org/10.6843/NTHU.2013.00814
- 陳桓杰（2018）。Objects Detection Based on Deep Learning with A Convolutional Neural Network Architecture〔碩士論文，國立屏東科技大學〕。華藝線上圖書館。https://doi.org/10.6346/THE.NPUST.MIS.023.2018.F08
- 陳貽祥（2018）。Design and Implementation of Configurable Texture Unitfor Convolutional Neural Network〔碩士論文，國立臺灣大學〕。華藝線上圖書館。https://doi.org/10.6342/NTU201802799
- 郭衿懿、壽大衛（2019）。Applications of convolutional neural networks on image recognition。載於國立金門大學（主編），NCS 2019 全國計算機會議（頁677-681）。國立金門大學。https://doi.org/10.6927/NCS.201911.0132
- Liang, D., Wang, X., Ju, X., & Yang, F. (2020). Deeply Integrated Convolutional Neural Networks. 電腦學刊, 31(1), 46-56. https://doi.org/10.3966/199115992020023101004