Efficient document image binarization

Efficient GANs for Document Image Binarization Based on DWT and Normalization

Citation

If you find our paper useful in your research, please consider citing:

  @article{ju2024efficient,
    title={Efficient GANs for Document Image Binarization Based on DWT and Normalization},
    author={Ju, Rui-Yang and Wong, KokSheik and Chiang, Jen-Shiun},
    journal={arXiv preprint arXiv:2407.04231},
    year={2024}
  }

Method

Datasets

• Our training set (143) includes:

  DIBCO 2009 (10), H-DIBCO 2010 (10), H-DIBCO 2012 (14), Bickley Diary (7), PHIBD (15), SMADI (87).

• Our test set (102) includes:

  DIBCO 2011 (16), DIBCO 2013 (16), H-DIBCO 2014 (10), H-DIBCO 2016 (10), DIBCO 2017 (20), H-DIBCO 2018 (10), DIBCO 2019 (20).

• Put training set into ./Trainset/, and put test set into ./Testset/.

Result (DIBCO 2019-009)

Environment

• NVIDIA GPU + CUDA CuDNN
• Creat a new Conda environment:

    conda env create -f environment.yaml
  

UNet & EfficientNetV2-S

Train

  cd unet_effnetv2
  python image_to_256.py
  python image_to_512.py
  python train_stage2_unet.py --epochs 10 --lambda_loss 25 --base_model_name tu-efficientnetv2_rw_s --batch_size 64
  python predict_for_stage3_unet.py --base_model_name tu-efficientnetv2_rw_s --lambda_loss 25
  python train_stage3_unet.py --epochs 10 --lambda_loss 25 --base_model_name tu-efficientnetv2_rw_s --batch_size 64
  python train_stage3_unet_resize.py --epochs 150 --lambda_loss 25 --base_model_name tu-efficientnetv2_rw_s --batch_size 16

Test

  python eval_stage3_all_unet.py --lambda_loss 25 --base_model_name tu-efficientnetv2_rw_s --batch_size 64

UNet++ & EfficientNetV2-S

Train

  cd unetplusplus_effnetv2
  python image_to_256.py
  python image_to_512.py
  python train_stage2.py --epochs 10 --lambda_loss 25 --base_model_name tu-efficientnetv2_rw_s --batch_size 64
  python predict_for_stage3.py --base_model_name tu-efficientnetv2_rw_s --lambda_loss 25
  python train_stage3.py --epochs 10 --lambda_loss 25 --base_model_name tu-efficientnetv2_rw_s --batch_size 64
  python train_stage3_resize.py --epochs 150 --lambda_loss 25 --base_model_name tu-efficientnetv2_rw_s --batch_size 16

Test

  python eval_stage3_all.py --lambda_loss 25 --base_model_name tu-efficientnetv2_rw_s --batch_size 64