The TextBlock600 Dataset used in PLRN for the research of irregular text block recognition is released by DLVC Lab of SCUT. The dataset can be downloaded through the following link:
Baidu Cloud: https://pan.baidu.com/s/11VonkxTqjumY6_BG0BHnmA
Note: The TextBlock600 dataset can only be used for non-commercial research purpose. The dataset is available now. For scholars or organization who wants to use the TextBlock600 database, please first fill in this Application Form and send it via email to us (eezyli@foxmail.com, cc to eelwjin@scut.edu.cn). Your Email MUST be set from a valid University account. When submiting the application form to us, please list or attached 1-2 of your publications in recent 6 years to indicate that you (or your team) do research in the related research fields of OCR, scene text recognition, and so on. We will give you the password after your letter has been received and approved.
Please consider to cite the paper when you use our dataset:
@article{li2024irregular,
title={Irregular text block recognition via decoupling visual, linguistic, and positional information},
author={Li, Ziyan and Jin, Lianwen and Zhang, Chengquan and Zhang, Jiaxin and Xie, Zecheng and Lyu, Pengyuan and Yao, Kun},
journal={Pattern Recognition},
volume={153},
pages={110516},
year={2024},
publisher={Elsevier}
}