README.md

metadata

license: mit
language:
  - ko
  - en
base_model:
  - microsoft/trocr-base-handwritten
pipeline_tag: image-to-text
tags:
  - HandWritten
  - OCR
  - Mathmatics

📄 Easy OCR Tool

This tool is designed to easily convert images and scanned documents into editable text using Optical Character Recognition (OCR).

Using fhswf/TrOCR_Math_handwritten Model

🇰🇷 (kr)한국어로 보기

My github link

Input

Hand-Written images

Output

cos\theta=\frac{x}{\sqrt{x^{2}+y^{2}}}

Input

Hand-Written images

Output

e^{i\pi}+1=0.

✨ Features

• ✅ Simple drag-and-drop interface.
• 📷 Supports multiple image formats.
• ⚡ Quick and accurate text extraction.

🔧 Installation

-MacTex: If you're on macOS, you'll need to install MacTeX.

brew install --cask mactex

• Windows: Install MiKTeX or TeX Live. Follow their respective installation guides.

-Python Dependencies

pip install torch torchvision torchaudio

🚀 Getting Started

1. Copy and put your image file path.
2. Click the Run.
3. Download the extracted text!

Reference

Model:

TrOCR_Math_handwritten by fhswf License: afl-3.0

Paper:

Li, M., Lv, T., Cui, L., Lu, Y., Florencio, D., Zhang, C., Li, Z., & Wei, F. (2021). TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models. arXiv preprint arXiv:2109.10282.

BibTeX:

text
@misc{li2021trocr,
  title={TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models},
  author={Minghao Li and Tengchao Lv and Lei Cui and Yijuan Lu and Dinei Florencio and Cha Zhang and Zhoujun Li and Furu Wei},
  year={2021},
  eprint={2109.10282},
  archivePrefix={arXiv},
  primaryClass={cs.CL}
}

---