README.md

MORAN: A Multi-Object Rectified Attention Network for Scene Text Recognition

MORAN is a network with rectification mechanism for general scene text recognition. The paper (accepted to appear in Pattern Recognition, 2019) in arXiv, online version is available now.

Here is a brief introduction in Chinese.

Improvements of MORAN v2:

• More stable rectification network for one-stage training
• Replace VGG backbone by ResNet
• Use bidirectional decoder (a trick borrowed from ASTER)

*The results of v1 were reported in our paper. If this project is helpful for your research, please cite our Pattern Recognition paper.

Requirements

• PyTorch 0.3.*
• TorchVision
• Python 2.7.*
• OpenCV 2.4.*
• PIL (Pillow)

Use pip to install the following libraries.

    pip install -r requirements.txt

• Colour
• LMDB
• matplotlib

Data Preparation

Please convert your own dataset to LMDB format by using the tool provided by @Baoguang Shi.

You can also download the training (NIPS 2014, CVPR 2016) and testing datasets prepared by us.

• about 20G training datasets and testing datasets in LMDB format, password: l8em

The raw pictures of testing datasets can be found here.

Training and Testing

Modify the path to dataset folder in train_MORAN.sh:

	--train_nips path_to_dataset \
	--train_cvpr path_to_dataset \
	--valroot path_to_dataset \

And start training: (manually decrease the learning rate for your task)

	sh train_MORAN.sh

Demo

Download the model parameter file demo.pth.

• BaiduYun (password: l8em)
• Google Drive
• OneDrive

Put it into root folder. Then, execute the demo.py for more visualizations.

	python demo.py

Citation

@article{cluo2019moran,
  author  = {Canjie Luo, Lianwen Jin, Zenghui Sun},
  title   = {MORAN: A Multi-Object Rectified Attention Network for Scene Text Recognition},
  journal = {Pattern Recognition}, 
  volume  = {}, 
  number  = {}, 
  pages   = {},
  year    = {2019}, 
}

Acknowledgment

The repo is developed based on @Jieru Mei's crnn.pytorch and @marvis' ocr_attention. Thanks for your contribution.

Attention

The project is only free for academic research purposes.