Sökning: onr:"swepub:oai:DiVA.org:ltu-87642" >
CasTabDetectoRS: Ca...
CasTabDetectoRS: Cascade Network for Table Detection in Document Images with Recursive Feature Pyramid and Switchable Atrous Convolution
-
- Hashmi, Khurram Azeem (författare)
- Department of Computer Science, Technical University of Kaiserslautern, 67663 Kaiserslautern, Germany; Mindgarage, Technical University of Kaiserslautern, 67663 Kaiserslautern, Germany; German Research Institute for Artificial Intelligence (DFKI), 67663 Kaiserslautern, Germany
-
- Pagani, Alain (författare)
- German Research Institute for Artificial Intelligence (DFKI), 67663 Kaiserslautern, Germany
-
- Liwicki, Marcus (författare)
- Luleå tekniska universitet,EISLAB
-
visa fler...
-
- Stricker, Didier (författare)
- Department of Computer Science, Technical University of Kaiserslautern, 67663 Kaiserslautern, Germany; German Research Institute for Artificial Intelligence (DFKI), 67663 Kaiserslautern, Germany
-
- Afzal, Muhammad Zeshan (författare)
- Department of Computer Science, Technical University of Kaiserslautern, 67663 Kaiserslautern, Germany; Mindgarage, Technical University of Kaiserslautern, 67663 Kaiserslautern, Germany; German Research Institute for Artificial Intelligence (DFKI), 67663 Kaiserslautern, Germany
-
visa färre...
-
(creator_code:org_t)
- 2021-10-16
- 2021
- Engelska.
-
Ingår i: Journal of Imaging. - : MDPI. - 2313-433X. ; 7:10
- Relaterad länk:
-
https://doi.org/10.3...
-
visa fler...
-
https://ltu.diva-por... (primary) (Raw object)
-
https://europepmc.or...
-
https://urn.kb.se/re...
-
https://doi.org/10.3...
-
visa färre...
Abstract
Ämnesord
Stäng
- Table detection is a preliminary step in extracting reliable information from tables in scanned document images. We present CasTabDetectoRS, a novel end-to-end trainable table detection framework that operates on Cascade Mask R-CNN, including Recursive Feature Pyramid network and Switchable Atrous Convolution in the existing backbone architecture. By utilizing a comparativelyightweight backbone of ResNet-50, this paper demonstrates that superior results are attainable without relying on pre- and post-processing methods, heavier backbone networks (ResNet-101, ResNeXt-152), and memory-intensive deformable convolutions. We evaluate the proposed approach on five different publicly available table detection datasets. Our CasTabDetectoRS outperforms the previous state-of-the-art results on four datasets (ICDAR-19, TableBank, UNLV, and Marmot) and accomplishes comparable results on ICDAR-17 POD. Upon comparing with previous state-of-the-art results, we obtain a significant relative error reduction of 56.36%, 20%, 4.5%, and 3.5% on the datasets of ICDAR-19, TableBank, UNLV, and Marmot, respectively. Furthermore, this paper sets a new benchmark by performing exhaustive cross-datasets evaluations to exhibit the generalization capabilities of the proposed method
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
Nyckelord
- table detection
- table recognition
- cascade Mask R-CNN
- atrous convolution
- recursive feature pyramid networks
- document image analysis
- deep neural networks
- computer vision
- object detection
- Maskininlärning
- Machine Learning
Publikations- och innehållstyp
- ref (ämneskategori)
- art (ämneskategori)
Hitta via bibliotek
Till lärosätets databas