Check it out on
TSR for partially bordered tables uses the same erosion algorithm as in bordered tables to detect existing borderes, but without using them to create a grid cell, but to delete the borders from the table image to get an unbordered table. This allows for applying the algorithm for unbordered tables to create the grid-cell image and contours by analogy to the variants discussed above. A key feature of this approach is that it works with both bordered and unbordered tables: it is type-independent.
| IoU | IoU | IoU | IoU | Weighted | |
|---|---|---|---|---|---|
| Team | 0.6 | 0.7 | 0.8 | 0.9 | Average |
| CascadeTabNet | 0.438 | 0.354 | 0.19 | 0.036 | 0.232 |
| NLPR-PAL | 0.365 | 0.305 | 0.195 | 0.035 | 0.206 |
| Multi-Type-TD-TSR | 0.589 | 0.404 | 0.137 | 0.015 | 0.253 |
The source code is developed under the following library dependencies
- PyTorch = 1.7.0
- Torchvision = 0.8.1
- Cuda = 10.1
- PyYAML = 5.1
The table detection model is based on detectron2 follow this installation guide to setup.
For the image alignment pre-processing step there is one script available:
deskew.py
To apply the image alignment pre-processing algorithm to all images in one folder, you need to execute:
python3 deskew.py
with the following parameters
--folderthe input folder including document images--outputthe output folder for the deskewed images
For the table structure recognition we offer a simple script for different approaches
tsr.py
To apply a table structure recognition algorithm to all images in one folder, you need to execute:
python3 tsr.py
with the following parameters
--folderpath of the input folder including table images--typethe table structure recognition typetype in ["borderd", "unbordered", "partially", "partially_color_inv"]--img_outputoutput folder path for the processed images--xml_outputoutput folder path for the xml files including bounding boxes
To appy the table detection with a followed table structure recogniton
tdtsr.py
To apply a table structure recognitio algorithm to all images in one folder, you need to execute:
python3 tdtsr.py
with the following parameters
--folderpath of the input folder including table images--typethe table structure recognition typetype in ["borderd", "unbordered", "partially", "partially_color_inv"]--tsr_img_outputoutput folder path for the processed table images--td_img_outputoutput folder path for the produced table cutouts--xml_outputoutput folder path for the xml files for tables and cells including bounding boxes--configpath of detectron2 configuration file for table detection--yamlpath of detectron2 yaml file for table detection--weightspath of detectron2 model weights for table detection
To evaluate the table structure recognition algorithm we provide the following script:
evaluate.py
to apply the evaluation the table images and their labels in xml-format have to be the same name and should lie in a single folder. The evaluation could be started by:
python3 evaluate.py
with the following parameter
--datasetdataset folder path containing table images and labels in .xml format
- test dataset for table structure recognition including table images and annotations can be downloaded here
- table detection detectron2 model weights and configuration files can be downloaded here
@misc{fischer2021multitypetdtsr,
title={Multi-Type-TD-TSR - Extracting Tables from Document Images using a Multi-stage Pipeline for Table Detection and Table Structure Recognition: from OCR to Structured Table Representations},
author={Pascal Fischer and Alen Smajic and Alexander Mehler and Giuseppe Abrami},
year={2021},
eprint={2105.11021},
archivePrefix={arXiv},
primaryClass={cs.CV}
}