🔒 PII Detection & Redaction App

A powerful Python-based web application built with Streamlit for detecting and redacting Personally Identifiable Information (PII) in documents. Supports multiple file formats including PDFs, images, and text files with intelligent pattern recognition for Indian identity documents.

🌟 Features

• 🔍 Smart PII Detection: Automatically detects Aadhaar numbers, PAN numbers, Driving Licenses, and Voter IDs using advanced regular expressions
• 🎭 Intelligent Masking: Replaces detected PII with 'X' characters while preserving document structure
• 📄 PDF Redaction: Creates professionally redacted PDFs with PII information blacked out
• 📁 Multi-format Support: Processes PDF, PNG, JPG, JPEG, and TXT files seamlessly
• 🖥️ User-friendly Interface: Clean, intuitive Streamlit web interface
• ⚡ Real-time Processing: Instant PII detection and masking results

🚀 Quick Start

Prerequisites

• Python 3.7 or higher
• Git (for cloning the repository)

Installation

1. Clone the repository

   git clone https://github.com/yourusername/pii-detection-app.git
   cd pii-detection-app

2. Install Python dependencies

   pip install -r requirements.txt

3. Install Tesseract OCR (Optional - for image processing)

   • Windows: Download from Tesseract OCR
   • macOS: brew install tesseract
   • Linux: sudo apt-get install tesseract-ocr

4. Run the application

   streamlit run main.py

5. Open your browser and navigate to http://localhost:8501

Note: The app works with PDF and TXT files even without Tesseract. Image processing requires Tesseract OCR installation.

📖 How It Works

1. Upload Document

• Drag and drop or browse to select your document
• Supports PDF, PNG, JPG, JPEG, and TXT formats

2. Automatic PII Detection

• Advanced regex patterns scan for:
  • Aadhaar Numbers: 12-digit unique identification numbers
  • PAN Numbers: 10-character alphanumeric tax identification
  • Driving License: State-specific license number patterns
  • Voter ID: Election Commission identification numbers

3. Smart Processing

• PDFs: Direct text extraction and redaction
• Images: OCR-based text recognition (requires Tesseract)
• Text Files: Direct content analysis

4. Secure Output

• View detected PII in organized format
• Download redacted PDFs with PII blacked out
• See masked versions with 'X' replacements

🎯 Usage Example

1. Launch the app: streamlit run main.py
2. Open browser: Navigate to http://localhost:8501
3. Upload file: Choose your document
4. Review results: See detected PII and masked versions
5. Download: Get redacted PDF if applicable

🛡️ Supported PII Types

PII Type	Pattern	Example
Aadhaar	12 digits (with/without spaces)	1234 5678 9012
PAN	5 letters + 4 digits + 1 letter	ABCDE1234F
Driving License	State code + digits	MH1234567890
Voter ID	3 letters + 7 digits	ABC1234567

⚠️ Important Notes

• Privacy First: All processing happens locally on your machine
• No Data Storage: Files are temporarily processed and automatically cleaned up
• OCR Dependency: Image processing requires Tesseract OCR installation
• Accuracy: Detection accuracy depends on document quality and text clarity
• Indian Focus: Current patterns optimized for Indian identity documents

🤝 Contributing

We welcome contributions! Please feel free to submit a Pull Request. For major changes, please open an issue first to discuss what you would like to change.

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

• Built with Streamlit for the web interface
• Uses Tesseract OCR for image text extraction
• PDF processing powered by PyMuPDF and PyPDF2

---

⭐ Star this repository if you find it helpful!