A Python-based OCR API for extracting 4×4 tile values from 2048 game screenshots using OpenCV and Tesseract. It includes a FastAPI backend and a browser-based HTML frontend.

• Python 3.9+
• A modern web browser (for the frontend)
• Tesseract OCR installed and available in your system path

Install dependencies:

pip install -r requirements.txt

Start the FastAPI backend:

uvicorn ocr_api:app --reload

Serve index.html with a simple HTTP server:

python -m http.server

Then open the page in your browser.

Upload a screenshot of the 2048 game using the browser interface served by index.html.

Input	Output
	🧩 OCR 2048 Board: 2 4 4 8 32 16 4 2 2 64 16 4 32 8 4 2

.
├── index.html         # Frontend interface
├── ocr_api.py         # FastAPI backend
├── requirements.txt   # Python dependencies

• FastAPI — backend framework
• OpenCV-Python — board detection and image processing
• pytesseract — Python wrapper for Tesseract OCR
• Tesseract OCR — text recognition engine
• Python Imaging Library (Pillow) — image format handling