It's the code for the paper A holistic representation guided attention network for scene text recognition, Neurocomputing 2020. Test in Python2.7.
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
sh ./train.sh
sh ./val.sh
python pre_img.py YOUR/MODEL/PATH YOUR/IMAGE/PATH
@article{yang2020holistic,
title={A Holistic Representation Guided Attention Network for Scene Text Recognition},
author={Yang, Lu and Wang, Peng and Li, Hui and Li, Zhen and Zhang, Yanning},
journal={Neurocomputing},
year={2020},
publisher={Elsevier}
}
This code is based on MORAN by Canjie-Luo. Thanks for your contribution.