Business Registration OCR

Extract data from business registration documents using OCR.

Setup

1. Clone this repository
2. Create virtual environment:

   python3 -m venv venv
   source venv/bin/activate

3. Install dependencies:

   brew install tesseract
   pip install -r requirements.txt

Usage

1. Place document images in data/sample_documents/
2. Run:

   python src/main.py

3. Check results in output/ folder

Project Structure

business-reg-ocr/
├── src/
│   ├── main.py              # Main application
│   ├── image_processor.py   # Image preprocessing
│   ├── ocr_engine.py        # OCR engine
│   └── parser.py            # Data extraction
├── tests/
├── data/sample_documents/   # Input images
└── output/                  # Results