skip to main content
Language:
Search Limited to: Search Limited to: Resource type Show Results with: Show Results with: Search type Index

HybridTabNet: Towards Better Table Detection in Scanned Document Images

Applied sciences, 2021-09, Vol.11 (18), p.8396 [Peer Reviewed Journal]

2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. ;ISSN: 2076-3417 ;EISSN: 2076-3417 ;DOI: 10.3390/app11188396

Full text available

Citations Cited by
  • Title:
    HybridTabNet: Towards Better Table Detection in Scanned Document Images
  • Author: Nazir, Danish ; Hashmi, Khurram Azeem ; Pagani, Alain ; Liwicki, Marcus ; Stricker, Didier ; Afzal, Muhammad Zeshan
  • Subjects: Algorithms ; computer vision ; Datasets ; deep learning ; deep neural networks ; deformable convolution ; document image analysis ; Feature extraction ; Heuristic ; hybrid task cascade ; Information retrieval ; Latex ; Machine Learning ; Maskininlärning ; Methods ; object detection ; Post-production processing ; scanned document images ; table detection ; table localization
  • Is Part Of: Applied sciences, 2021-09, Vol.11 (18), p.8396
  • Description: 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 27.57% on ICDAR-2019-TrackA-Modern, 42.64% on TableBank (Latex), 41.33% on TableBank (Word), 55.73% on TableBank (Latex + Word), 10% on Marmot, and 9.67% on the UNLV dataset. The achieved results reflect the superior performance of the proposed method.
  • Publisher: Basel: MDPI AG
  • Language: English
  • Identifier: ISSN: 2076-3417
    EISSN: 2076-3417
    DOI: 10.3390/app11188396
  • Source: Open Access: DOAJ Directory of Open Access Journals
    AUTh Library subscriptions: ProQuest Central
    SWEPUB Freely available online
    ROAD: Directory of Open Access Scholarly Resources
Back to results list
INSPIRE LIBRARY - TON DUC THANG UNIVERSITY (84-028) 37 755 057 Feedback
19 Nguyen Huu Tho St. Dist.7, HCM thuvien@tdtu.edu.vn

Copyright © 2017 INSPIRE LIBRARY - TON DUC THANG UNIVERSITY

Searching Remote Databases, Please Wait