I’m sharing an open-source watermark removal project powered by OpenCV image inpainting.
GitHub Repository: gosailing2028/WatermarkRemoval
This learning-oriented tool comes with both a browser web interface and a command-line script. You can manually draw watermark regions or use auto-detection to erase light-colored text overlays on images.
Key Features
Flask web UI with canvas markup: rectangle, brush and eraser
One-click auto detection for white/light watermarks
Two inpainting algorithms: TELEA and Navier-Stokes
Standalone CLI supporting headless automated processing
Simple REST API for further integration
Get Started
bash
git clone https://github.com/gosailing2028/WatermarkRemoval.git
cd WatermarkRemoval
pip install -r requirements.txt
python app.py
Open http://127.0.0.1:5000 in your browser to test the web demo.
⚠️ Important reminder: Use this tool only on images you own or have explicit permission to modify. Classical OpenCV inpainting performs well on simple backgrounds. For complex scenes, deep learning models such as LaMa are better choices.
If you are looking for ready-to-use online image utilities:
👉 imagetool.io
Feel free to fork the repo, and drop a star ⭐ if it helps you!
For further actions, you may consider blocking this person and/or reporting abuse
Top comments (0)