🖼️ Face Blurring with OpenCV DNN - Advanced Version

An advanced face blurring toolkit using OpenCV's deep learning-based face detector (ResNet SSD).
Offers multiple anonymization techniques for greater flexibility and professional use cases.

---

📜 Description

This version uses OpenCV DNN with a ResNet SSD model to detect faces in images or videos, and offers four blur modes:

• Rectangular Gaussian blur
• Elliptical blur (with masks)
• Pixelation
• Hybrid (Gaussian + Pixelate)

---

🚀 Features

• DNN-based face detection (ResNet SSD)
• Four anonymization methods
• Mask-based elliptical blur
• Pixelation and hybrid options
• Works on images and videos

---

🛠️ Technologies Used

• Python 3
• OpenCV
• NumPy
• Pretrained ResNet SSD Face Detector (Caffe format)

---

📁 Project Structure

face-blurring-dnn-advanced/
│ 
├── model/
│   ├── deploy.prototxt
│   └── res10_300x300_ssd_iter_140000.caffemodel
│ 
├── assets/
│   ├── family.jpg
│   └── boy.jpg
│ 
├── output/
│   └── output_sample.png
│ 
├── main.py
├── blur_utils.py
├── mask_utils.py
│ 
├── requirements.txt
├── .gitignore
├── LICENSE
├── banner.png
└── README.md

---

⚙️ Installation & Setup

1️⃣ Clone the Repository

git clone https://github.com/HeleenaRobert/face-blurring-dnn-advanced.git
cd face-blurring-dnn-advanced

2️⃣ Create a Virtual Environment (Optional but Recommended)

python -m venv venv
source venv/bin/activate      # On Windows: venv\Scripts\activate

3️⃣ Install Dependencies

pip install -r requirements.txt

---

📥 DNN Model Files

Download and place the following in the model/ folder:

• deploy.prototxt
  https://raw.githubusercontent.com/opencv/opencv/master/samples/dnn/face_detector/deploy.prototxt

• res10_300x300_ssd_iter_140000.caffemodel
  https://github.com/opencv/opencv_3rdparty/raw/dnn_samples_face_detector_20170830/res10_300x300_ssd_iter_140000.caffemodel

📌 Note: The required model files are already included in this repository under the models/ folder, so downloading is optional.

---

▶️ Usage

1. Place your input image/video in the assets/ folder.

2. Run:

   python face_blur.py

3. Blurred output will be saved in the output/ folder.

---

🖼️ Output Sample

---

📝 License

This project is licensed under the MIT License.

---

👩‍💻 Author

Heleena Robert
GitHub