#234 · Primary category: Computer Vision

MixTeX-Latex-OCR

computer-vision deep-learning latex machine-learning ocr onnx python

MixTeX multimodal LaTeX, ZhEn, and, Table OCR. It performs efficient CPU-based inference in a local offline on Windows.

Project last updated:04/24/25

GitHub Stars

1.6K

Forks

97

Contributors

8

License

AGPL-3.0

Why we included this project

MixTeX pulls equations, tables, and mixed text out of images and hands back LaTeX code, all computed locally on the CPU. A researcher writing papers or a student transcribing notes can screenshot a formula and get editable LaTeX in a few seconds, with no cloud service and no GPU involved. Everything runs offline on an ordinary Windows laptop, which matters for people handling material too sensitive to upload anywhere. It handles both Chinese and English, so it fits teams that mix languages, and it ships as a packaged GUI rather than a bare library, so people who do not code can still use it. The ONNX-based models keep the project reasonably easy to rebuild or extend if you want to tinker.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category