📷 Image Denoising Using DnCNN

📌 Overview

This project demonstrates image denoising using the DnCNN (Denoising Convolutional Neural Network) model. The implementation is done in MATLAB, featuring a GUI-based application and a pre-trained deep learning model to remove noise from images effectively.

📂 Project Structure

📦 Image-Denoising-Using-DnCNN
├── 📄 DnCNN Model Denoising.png              # Sample denoising output
├── 📄 Doge.jpeg                              # Noisy test image
├── 📄 EE441_CEP_Presentation.pptx            # Project presentation slides
├── 📄 EE441_CEP_Application(Matlab_App_Designer).m  # MATLAB GUI application
├── 📄 EE441_CEP_Report_Final.pdf             # Final project report
├── 📄 Grey Cameraman.jpg                     # Test image for experiments
├── 📄 Image Denoising App Interface.png      # Screenshot of MATLAB GUI
├── 📄 Pre_trained_Model_DnCNN_Code.m         # MATLAB script for DnCNN model
└── 📄 README.md                              # Project documentation

⚙️ Features

✅ Deep learning-based image denoising using DnCNN
✅ MATLAB-based GUI for interactive image processing
✅ Supports multiple noisy image inputs
✅ Pre-trained model for fast and accurate denoising

🚀 Installation

1. Ensure MATLAB is installed (preferably with the Deep Learning Toolbox).

2. Clone this repository:

   git clone (https://github.com/UsmanAbbasi2002/Image_Denoising_Matlab_Application)
   cd Image-Denoising-Using-DnCNN

3. Open MATLAB and load the project files.

📖 Usage

🖥️ Running the Pre-Trained Model

1. Open Pre_trained_Model_DnCNN_Code.m in MATLAB.
2. Load a noisy image (e.g., Doge.jpeg or Grey Cameraman.jpg).
3. Run the script to apply the DnCNN model and observe the results.

🎨 Using the GUI Application

1. Open EE441_CEP_Application(Matlab_App_Designer).m in MATLAB.
2. Use the graphical interface to upload a noisy image.
3. Apply the denoising filter and save the output.

🛠️ Requirements

• MATLAB (with Deep Learning Toolbox)
• Pre-trained DnCNN model
• Image Processing Toolbox (optional)

📊 Results

• The DnCNN model successfully removes noise while preserving details.
• GUI-based application simplifies user interaction for non-coders.

🤝 Contributing

Contributions are welcome! To contribute:

1. Fork the repository
2. Create a new branch (git checkout -b feature-branch)
3. Make changes and commit (git commit -m "Add new feature")
4. Push to your fork and submit a Pull Request

📜 License

This project is licensed under the MIT License. Feel free to use and modify it!

📧 Contact

👤 Usman Abbasi
📩 Email: [usmanabbasia10@gmail.com.com]
🔗 GitHub: UsmanAbbasi2002