A web application that uses Gemma 3 to extract text from images. The application allows you to select a portion of an image and get the text content from that selection.
- Upload and select portions of images
- Extract text using Gemma 3
- Real-time processing time estimation
- Option to include/exclude context image
- Progress tracking with countdown timer
- Upload an image
- Select the area containing text
- Choose whether to include context
- Click "Analyze Selection" to extract text
- Clone the repository
- Install dependencies
- Run the Flask application
- Open in browser at
http://localhost:7000
- Python 3.x
- Flask
- Ollama with Gemma 3 model
MIT License