Loading...
Please wait, while we are loading the content...
Similar Documents
HybridTabNet: Towards Better Table Detection in Scanned Document Images
| Content Provider | MDPI |
|---|---|
| Author | Nazir, Danish Hashmi, Khurram Azeem Pagani, Alain Liwicki, Marcus Stricker, Didier Afzal, Muhammad Zeshan |
| Copyright Year | 2021 |
| Abstract | Tables in document images are an important entity since they contain crucial information. Therefore, accurate table detection can significantly improve the information extraction from documents. In this work, we present a novel end-to-end trainable pipeline, HybridTabNet, for table detection in scanned document images. Our two-stage table detector uses the ResNeXt-101 backbone for feature extraction and Hybrid Task Cascade (HTC) to localize the tables in scanned document images. Moreover, we replace conventional convolutions with deformable convolutions in the backbone network. This enables our network to detect tables of arbitrary layouts precisely. We evaluate our approach comprehensively on ICDAR-13, ICDAR-17 POD, ICDAR-19, TableBank, Marmot, and UNLV. Apart from the ICDAR-17 POD dataset, our proposed HybridTabNet outperformed earlier state-of-the-art results without depending on pre- and post-processing steps. Furthermore, to investigate how the proposed method generalizes unseen data, we conduct an exhaustive leave-one-out-evaluation. In comparison to prior state-of-the-art results, our method reduced the relative error by |
| Starting Page | 8396 |
| e-ISSN | 20763417 |
| DOI | 10.3390/app11188396 |
| Journal | Applied Sciences |
| Issue Number | 18 |
| Volume Number | 11 |
| Language | English |
| Publisher | MDPI |
| Publisher Date | 2021-09-11 |
| Access Restriction | Open |
| Subject Keyword | Applied Sciences Artificial Intelligence Table Detection Table Localization Deep Learning Hybrid Task Cascade Object Detection Deformable Convolution Deep Neural Networks Computer Vision Scanned Document Images Document Image Analysis |
| Content Type | Text |
| Resource Type | Article |
