Awesome

CDeC-Net

CDeC-Net: Composite Deformable Cascade Network for Table Detection in Document Images

Paper Link: ieeexplore | arXiv | Research Gate | CVIT, IIIT-H

Introduction

CDeC-Net is an end-to-end network for detecting tables in document images. The network consists of a multistage extension of Mask R-CNN with a dual backbone having deformable convolution for detecting tables varying in scale with high detection accuracy at higher IoU threshold. CDeC-Net achieves state-of-the-art results on various publicly available benchmark datasets. The code is implemented in PyTorch using <a href="https://github.com/open-mmlab/mmdetection">MMdetection</a> framework (Version 2.0.0).

Release Notes:

Oct 10, 2020: Our paper has been accepted to ICPR 2020 as oral paper.

Setup

<b>Dependencies</b><br> Python = 3.6+ <br> PyTorch = 1.4.0<br> Torchvision = 0.5.0<br> Cuda = 10.0<br> MMdetection = 2.0.0<br> mmcv = 0.5.4<br>

1. Clone this repository

git clone https://github.com/mdv3101/CDeCNet

2. Install the require dependencies

pip install torch==1.4.0 torchvision==0.5.0

cd CDecNet/
pip install -r requirements/build.txt
pip install "git+https://github.com/open-mmlab/cocoapi.git#subdirectory=pycocotools"
pip install -v -e .

Please follow install.md for detailed installation steps.

Training

1. Create a folder 'dataset' in the CDeCNet and put your data into this folder. Your dataset must be in MS-Coco format. The directory structure should be:

dataset
  ├── coco
  | ├── annotations
  | ├── train2014
  | ├── val2014
  | ├── logs

2. Create a folder 'model' in the CDeCNet and put the pre-trained model on MS-Coco into this directory. The model file can be downloaded from the drive

3. Set load_from= /path/of/pre-trained/model in default_runtime.py

4. To train a model on CDeC-Net, use the following commnand

python -u tools/train.py configs/dcn/db_cascade_mask_rcnn_x101_fpn_dconv_c3-c5_1x_coco.py --work-dir dataset/coco/logs/

Evaluation

To evaluate the trained model, run the following command

python tools/test.py configs/dcn/db_cascade_mask_rcnn_x101_fpn_dconv_c3-c5_1x_coco.py dataset/coco/logs/latest.pth \
    --format-only --options "jsonfile_prefix=evaluation_result"

Details about various training and evaluation methods can be found in getting_started.md

Demo

To run inference on single image, use the image_demo.py file by running the following command

python demo/image_demo.py demo_image.jpg configs/dcn/db_cascade_mask_rcnn_x101_fpn_dconv_c3-c5_1x_coco.py dataset/coco/logs/latest.pth \
    --score-thr 0.95 --output-img 'output_demo.jpg'

CDeCNet Results

1. Comparison between CDeC-Net and state-of-the-art techniques on the existing benchmark datasets.

2. Comparison between our single model CDeC-Net‡ and state-of-the-art techniques on existing benchmark datasets.

Note: Our single model CDeC-Net‡ is trained on IIIT-AR-13K dataset and fine-tuned with training set of respective datasets (if available). The base model trained on IIIT-AR-13K dataset can be downloaded from the drive

Qualitative Results: Table Detection by CDeC-Net

<img src="imgs/qualitative_13_19.png" height="350"/> <br> <img src="imgs/qualitative_17_marmot.png" height="350"/> <br>

Issue

Kindly go through the various tutorails and documentation provided in docs folder. <br> Most of the common issues were already solved in MMdetection official repo's Issue Page. We strongly suggest to go through it before raising a new issue.

Citation

If you find this work useful for your research, please cite our paper

@inproceedings{agarwal2021cdec,
  title={Cdec-net: Composite deformable cascade network for table detection in document images},
  author={Agarwal, Madhav and Mondal, Ajoy and Jawahar, CV},
  booktitle={2020 25th International Conference on Pattern Recognition (ICPR)},
  pages={9491--9498},
  year={2021},
  organization={IEEE}
}

Contact

CDeCNet was developed by Madhav Agarwal, Dr. Ajoy Mondal and Dr. C.V. Jawahar. <br> For any query, feel free to drop a mail to Madhav Agarwal by explicitly mentioning 'CDeCNet' in the subject.