Urdu OCR - Text Line Detection Inference

Released as a supplement of UTRNet: High-Resolution Urdu Text Recognition

Steps to run the code

*Note - Due to several dependency issues in maskrcnn-benchmark, YoloV8 is used for text line detection. The model is finetuned on the UrduDoc dataset.

• Clone the repository
• Install the dependencies

  pip install torch==2.0.1 ultralytics==8.1.8

• Download yolov8m_UrduDoc.pt
• Put test.jpg
• Run python3 detect.py
• The output will be saved as output.jpg

Note

The code & trained model is for research purposes only and must not be used for any other purpose without the author's explicit permission.

Citation

If you use the code/model/dataset, please cite the following paper:

@article{rahman2023utrnet,
      title={UTRNet: High-Resolution Urdu Text Recognition In Printed Documents}, 
      author={Abdur Rahman and Arjun Ghosh and Chetan Arora},
      journal={arXiv preprint arXiv:2306.15782},
      year={2023},
      eprint={2306.15782},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      doi = {https://doi.org/10.48550/arXiv.2306.15782},
      url = {https://arxiv.org/abs/2306.15782}
}

License

. This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License for Noncommercial (academic & research) purposes only and must not be used for any other purpose without the author's explicit permission.