simple-latex-ocr's Introduction

Simple-LaTeX-OCR

Performance

BLEU score	normed edit distance	token accuracy
0.92	0.05	0.75

Online experience

https://huggingface.co/spaces/chaodreaming/Simple-LaTeX-OCR

https://www.modelscope.cn/studios/chaodreaming/Simple-LaTeX-OCR/summary

Install the package simple_latex_ocr:

pip install simple_latex_ocr

Use from within Python

from simple_latex_ocr.models import Latex_OCR
model = Latex_OCR()
img_path = "tests/test_files/5.png"
result = model.predict(img_path)
print(result['formula'])
print(result['confidence'])
print(result['elapse'])

Used by command line

$ simple_latex_ocr tests/test_files/2.png

Used by api

$ python -m simple_latex_ocr.api.run

#You can use test.py to initiate a request for verification

Using streamlit has a nice interface, but you can only select files locally.

streamlit run streamlit_app.py

A simple interface for uploading files can be used to edit the results using latexlive.```

python flask_app.py

Contribution

Contributions of any kind are welcome.

Acknowledgment

Code taken and modified from lukas-blecher, RapidAI,ultralytics

simple-latex-ocr's People

Contributors

Stargazers

Watchers

Forkers

yrq66

simple-latex-ocr's Issues

LaTeX without style components

Hi @chaodreaming
Thank you for this repository.

Is possible make API to predict image to without LaTeX style components

for example now from this input image :

output LaTeX is :

(\mathfrak{a}+\mathfrak{b})^{2}=\mathfrak{a}^{2}+2\mathfrak{a}\mathfrak{b}+\mathfrak{b}^{2}

without style components is :

({a}+{b})^{2}={a}^{2}+2{a}{b}+{b}^{2}

OCR failure example

result:
$$
\left[\dot{i}{d}\right]=\frac{2}{3}(\left[-\frac{Z}{L}\quad\omega\right]\left[i{d}\right]+\left[\frac{V_{d c}}{L}\quad0\right]\left[D_{d}\right])
$$