HAFE

It's the code for the paper HAFE: A Hierarchical Awareness and Feature Enhancement Network for Scene Text Recognition, Knowledge-Based Systems 2024.

Install the enviroment

pip install -r requirements.txt

Please convert your own dataset to LMDB format by create_dataset.py. (Borrowed from https://github.com/bgshih/crnn/blob/master/tool/create_dataset.py, provided by Baoguang Shi)

There are converted Synth90K and SynthText LMDB dataset by luyang-NWPU: [Here], password: tw3x

Training

sh ./train.sh

Testing

sh ./val.sh

Recognize a image

python  pre_img.py  YOUR/MODEL/PATH  YOUR/IMAGE/PATH

Citation

@article{Ethereal2023HAFE,
  title={HAFE: A Hierarchical Awareness and Feature Enhancement Network for Scene Text Recognition},
  author={Kai HE, Jinlong TANG, Zikang LIU , Ziqi YANG},
  journal={Knowledge-Based Systems},
  year={2024},
  publisher={Elsevier}
}

Acknowledgment

This code is based on HGA-STR by luyang-NWPU. Thanks for your contribution.