🕵️ ImageForensics Pro

A web-based digital image forensics suite built with Python (Flask), OpenCV, and Real-ESRGAN for detecting image tampering and performing AI-powered restoration — all in your browser.

✨ Features

• Full Audit — one-click tamper-detection report with an overall risk verdict
• Forensics Core — Error Level Analysis (ELA), Noise Pattern Analysis, Clone/Copy-Move Detection, Metadata & EXIF Extraction
• Signal & Matrices — Frequency (FFT) Analysis, PCA Channel Decomposition, Luminance Gradient, Histogram / Posterisation Analysis
• AI Restoration — Real-ESRGAN upscaling
• Expose Feature — Denoise (NLM/Bilateral/Gaussian/Wavelet), Deblur (Wiener/Unsharp/Richardson-Lucy), Watermark Removal, Color Enhancement (CLAHE/EQ/White Balance/Gamma), Contour Extraction
• Local Workspace — multi-tab workspaces, pan/zoom, geometry transform (rotate/scale/shear/flip), level sweep, undo/redo

🛠️ Built With

• Flask — web framework
• OpenCV — image processing & computer vision
• NumPy / SciPy — numerical analysis
• Real-ESRGAN — AI super-resolution (PyTorch)

🎮 How to Use

1. Upload an image (JPG, PNG, TIFF, WEBP — max 10 MB)
2. Click Full Audit to get an instant manipulation-risk verdict, or drill into individual modules
3. Inspect the visualizations and findings in dedicated result tabs
4. Optionally enhance or restore the image with the processing tools

🚀 Getting Started

Run it locally

1. Create and activate a virtual environment

   python -m venv venv
   venv\Scripts\activate        # Windows
   # source venv/bin/activate   # Linux / macOS

2. Install dependencies

   pip install -r requirements.txt

3. Start the server

   python app.py

4. Open http://localhost:5000 in your browser

The Real-ESRGAN weights (~67 MB) are auto-downloaded on the first upscale request, so the repository stays lightweight.

📂 Project Structure

ImageForensicsPro/
├── assets/              # Demo images
├── app.py               # Flask web server (entry point)
├── image_forensics/     # Core engines: analysis, forensics, processing
├── static/              # Frontend assets (CSS, JavaScript)
├── templates/           # HTML templates
├── weights/             # AI model weights (auto-downloaded)
├── LICENSE
└── README.md

📝 License

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

👤 Author

Melvin (@CodeMelvin)