🖋️ AI-Powered Signature Verification System

An advanced AI-based Signature Verification System using Siamese Neural Networks to detect and verify handwritten signatures. With a clean Gradio web interface, users can simply upload two signatures to find out if they match — perfect for banking, legal, and security use cases.

---

📖 Overview

This project applies deep learning to compare two handwritten signatures and determine if they belong to the same person. It uses a Siamese CNN model trained to learn feature similarity between genuine and forged signatures.

The app provides:

• Match / No Match decision
• Confidence score
• Similarity percentage

---

🔧 Features

• 🧠 Siamese Neural Network for similarity learning
• 🖼️ Compare two signature images
• 📊 Confidence and similarity score
• 🌐 Gradio UI (browser-based, mobile-friendly)
• 💾 Pretrained model support (best_signature_model.h5)
• 🔄 Data Augmentation during training
• 📈 Real-time training visualizations

---

📦 Tech Stack

---

🚀 Setup & Usage

✅ Option 1: Google Colab (Recommended)

1. Upload signature_verification.py to your Colab session
2. Install the required libraries:

!pip install gradio tensorflow opencv-python-headless pillow numpy matplotlib scikit-learn

3. Run the app:

%run signature_verification.py

A public link will appear — click to open the app in your browser.

---

💻 Option 2: Local Setup

git clone https://github.com/shahram8708/AI-Based-Signature-Verification-System.git
cd AI-Based-Signature-Verification-System

python -m venv signature_env
# For Windows:
signature_env\Scripts\activate
# For Mac/Linux:
source signature_env/bin/activate

pip install -r requirements.txt
python signature_verification.py

Open browser at: http://localhost:7860

---

📂 Project Structure

AI-Based-Signature-Verification-System/
├── signature_verification.py      # Main application file
├── best_signature_model.h5        # Trained model (auto-generated after training)
├── requirements.txt               # Dependencies
├── demo.PNG                       # Demo screenshot
├── README.md                      # Documentation
└── signature_data/                # Signature dataset directory
    ├── genuine/                   # Real signatures
    └── forged/                    # Fake signatures

---

🎨 Gradio UI Components

• 📤 Upload areas for both signatures
• 🔍 "Verify Signatures" button
• 📊 Output: Match/No Match, Confidence, Similarity
• 📋 Tips section for better results

---

📈 Model Details

---

✅ Best Results Tips

• Use clear and centered signature images
• Prefer white/light backgrounds
• Avoid low-resolution or blurred images
• Use PNG/JPG/JPEG formats

---

🛠️ To-Do / Future Enhancements

• 📁 CEDAR/MCYT dataset integration
• 🧾 Support for vector/PDF signatures
• 📡 API & database integration
• 📱 Mobile App (React Native / Flutter)
• 📊 ROC/AUC metrics and analysis
• 🐳 Docker & cloud deployment (AWS/GCP)

---

📄 License

This project is licensed under the MIT License.
You are free to use, modify, and distribute it with credit to the author.

---

👨‍💻 Author

Shah Ram — AI/ML Engineer & Deep Learning Enthusiast
Connect with me on GitHub

---

"The best way to predict the future is to create it." – Peter Drucker

---

🌟 Like the Project?

• ⭐ Star the repository
• 🍴 Fork it for experiments
• 🐞 Report issues
• 💬 Suggest features
• 📢 Share it with others!

---

Built with ❤️ using TensorFlow & Gradio