img: Image for OCR. It can be an ndarray, img_path, or a list of ndarrays.
det: Use text detection or not. If False, only text recognition will be executed. Default is True.
rec: Use text recognition or not. If False, only text detection will be executed. Default is True.
cls: Use angle classifier or not. Default is True. If True, the text with a rotation of 180 degrees can be recognized. If no text is rotated by 180 degrees, use cls=False to get better performance.
bin: Binarize image to black and white. Default is False.
inv: Invert image colors. Default is False.
alpha_color: Set RGB color Tuple for transparent parts replacement. Default is pure white.
slice: Use sliding window inference for large images. Both det and rec must be True. Requires int values for slice["horizontal_stride"], slice["vertical_stride"], slice["merge_x_thres"], slice["merge_y_thres"] (See doc/doc_en/slice_en.md). Default is {}.
Returns:
If both det and rec are True, returns a list of OCR results for each image. Each OCR result is a list of bounding boxes and recognized text for each detected text region.
If det is True and rec is False, returns a list of detected bounding boxes for each image.
If det is False and rec is True, returns a list of recognized text for each image.
If both det and rec are False, returns a list of angle classification results for each image.
Raises:
AssertionError: If the input image is not of type ndarray, list, str, or bytes.
SystemExit: If det is True and the input is a list of images.
Note:
- If the angle classifier is not initialized (use_angle_cls=False), it will not be used during the forward process.
- For PDF files, if the input is a list of images and the page_num is specified, only the first page_num images will be processed.
- The preprocess_image function is used to preprocess the input image by applying alpha color replacement, inversion, and binarization if specified.
"""
assertisinstance(img,(np.ndarray,list,str,bytes))
ifisinstance(img,list)anddet==True:
logger.error("When input a list of images, det must be false")
exit(0)
ifcls==Trueandself.use_angle_cls==False:
logger.warning(
"Since the angle classifier is not initialized, it will not be used during the forward process"
<ahref="https://github.com/opendatalab/PDF-Extract-Kit">PDF-Extract-Kit: High-Quality PDF Extraction Toolkit</a>🔥🔥🔥
</p>
<!-- join us -->
<palign="center">
👋 join us on <ahref="https://discord.gg/Tdedn9GTXq"target="_blank">Discord</a> and <ahref="https://cdn.vansin.top/internlm/mineru.jpg"target="_blank">WeChat</a>
</p>
<!-- read the docs -->
<palign="center">
read more docs on <ahref="https://mineru.readthedocs.io/en/latest/"> Read The Docs </a>
</p>
</div>
# Changelog
- 2024/11/06 0.9.2 released. Integrated the [StructTable-InternVL2-1B](https://huggingface.co/U4R/StructTable-InternVL2-1B) model for table recognition functionality.
- 2024/10/31 0.9.0 released. This is a major new version with extensive code refactoring, addressing numerous issues, improving performance, reducing hardware requirements, and enhancing usability:
- Refactored the sorting module code to use [layoutreader](https://github.com/ppaanngggg/layoutreader) for reading order sorting, ensuring high accuracy in various layouts.
- Refactored the paragraph concatenation module to achieve good results in cross-column, cross-page, cross-figure, and cross-table scenarios.
- Refactored the list and table of contents recognition functions, significantly improving the accuracy of list blocks and table of contents blocks, as well as the parsing of corresponding text paragraphs.
- Refactored the matching logic for figures, tables, and descriptive text, greatly enhancing the accuracy of matching captions and footnotes to figures and tables, and reducing the loss rate of descriptive text to near zero.
- Added multi-language support for OCR, supporting detection and recognition of 84 languages.For the list of supported languages, see [OCR Language Support List](https://paddlepaddle.github.io/PaddleOCR/latest/en/ppocr/blog/multi_languages.html#5-support-languages-and-abbreviations).
- Added memory recycling logic and other memory optimization measures, significantly reducing memory usage. The memory requirement for enabling all acceleration features except table acceleration (layout/formula/OCR) has been reduced from 16GB to 8GB, and the memory requirement for enabling all acceleration features has been reduced from 24GB to 10GB.
- Optimized configuration file feature switches, adding an independent formula detection switch to significantly improve speed and parsing results when formula detection is not needed.
- Added the self-developed `doclayout_yolo` model, which speeds up processing by more than 10 times compared to the original solution while maintaining similar parsing effects, and can be freely switched with `layoutlmv3` via the configuration file.
- Upgraded formula parsing to `unimernet 0.2.1`, improving formula parsing accuracy while significantly reducing memory usage.
- Due to the repository change for `PDF-Extract-Kit 1.0`, you need to re-download the model. Please refer to [How to Download Models](docs/how_to_download_models_en.md) for detailed steps.
- 2024/09/27 Version 0.8.1 released, Fixed some bugs, and providing a [localized deployment version](projects/web_demo/README.md) of the [online demo](https://opendatalab.com/OpenSourceTools/Extractor/PDF/) and the [front-end interface](projects/web/README.md).
- 2024/09/09: Version 0.8.0 released, supporting fast deployment with Dockerfile, and launching demos on Huggingface and Modelscope.
MinerU is a tool that converts PDFs into machine-readable formats (e.g., markdown, JSON), allowing for easy extraction into any format.
MinerU was born during the pre-training process of [InternLM](https://github.com/InternLM/InternLM). We focus on solving symbol conversion issues in scientific literature and hope to contribute to technological development in the era of large models.
Compared to well-known commercial products, MinerU is still young. If you encounter any issues or if the results are not as expected, please submit an issue on [issue](https://github.com/opendatalab/MinerU/issues) and **attach the relevant PDF**.
Refer to [How to Download Model Files](docs/how_to_download_models_en.md) for detailed instructions.
#### 3. Modify the Configuration File for Additional Configuration
After completing the [2. Download model weight files](#2-download-model-weight-files) step, the script will automatically generate a `magic-pdf.json` file in the user directory and configure the default model path.
You can find the `magic-pdf.json` file in your 【user directory】.
> [!TIP]
> The user directory for Windows is "C:\\Users\\username", for Linux it is "/home/username", and for macOS it is "/Users/username".
You can modify certain configurations in this file to enable or disable features, such as table recognition:
> [!NOTE]
> If the following items are not present in the JSON, please manually add the required items and remove the comment content (standard JSON does not support comments).
-[magic_pdf_parse_main.py More Detailed Processing Workflow](demo/magic_pdf_parse_main.py)
### Deploy Derived Projects
Derived projects include secondary development projects based on MinerU by project developers and community developers,
such as application interfaces based on Gradio, RAG based on llama, web demos similar to the official website, lightweight multi-GPU load balancing client/server ends, etc.
These projects may offer more features and a better user experience.
For specific deployment methods, please refer to the [Derived Project README](projects/README.md)
### Development Guide
TODO
# TODO
- [x] Reading order based on the model
- [x] Recognition of `index` and `list` in the main text
- [x] Table recognition
- [ ] Code block recognition in the main text
-[ ] [Chemical formula recognition](docs/chemical_knowledge_introduction/introduction.pdf)
This project currently uses PyMuPDF to achieve advanced functionality. However, since it adheres to the AGPL license, it may impose restrictions on certain usage scenarios. In future iterations, we plan to explore and replace it with a more permissive PDF processing library to enhance user-friendliness and flexibility.
title={MinerU: An Open-Source Solution for Precise Document Content Extraction},
author={Bin Wang and Chao Xu and Xiaomeng Zhao and Linke Ouyang and Fan Wu and Zhiyuan Zhao and Rui Xu and Kaiwen Liu and Yuan Qu and Fukai Shang and Bo Zhang and Liqun Wei and Zhihao Sui and Wei Li and Botian Shi and Yu Qiao and Dahua Lin and Conghui He},
year={2024},
eprint={2409.18839},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2409.18839},
}
@article{he2024opendatalab,
title={Opendatalab: Empowering general artificial intelligence with open datasets},
author={He, Conghui and Li, Wei and Jin, Zhenjiang and Xu, Chao and Wang, Bin and Lin, Dahua},
👋 join us on <ahref="https://discord.gg/Tdedn9GTXq"target="_blank">Discord</a> and <ahref="https://cdn.vansin.top/internlm/mineru.jpg"target="_blank">WeChat</a>
</p>
<!-- read the docs -->
<palign="center">
read more docs on <ahref="https://mineru.readthedocs.io/zh-cn/latest/"> Read The Docs </a>
title={MinerU: An Open-Source Solution for Precise Document Content Extraction},
author={Bin Wang and Chao Xu and Xiaomeng Zhao and Linke Ouyang and Fan Wu and Zhiyuan Zhao and Rui Xu and Kaiwen Liu and Yuan Qu and Fukai Shang and Bo Zhang and Liqun Wei and Zhihao Sui and Wei Li and Botian Shi and Yu Qiao and Dahua Lin and Conghui He},
year={2024},
eprint={2409.18839},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2409.18839},
}
@article{he2024opendatalab,
title={Opendatalab: Empowering general artificial intelligence with open datasets},
author={He, Conghui and Li, Wei and Jin, Zhenjiang and Xu, Chao and Wang, Bin and Lin, Dahua},
