✨ Mask Detection with Mask R-CNN ✨

📊 Project Overview

This project leverages the power of Mask R-CNN to perform instance segmentation and classification of face masks in images. The system can identify:

• 👷‍♂️ Faces with masks
• 🚫 Faces without masks
• 😕 Faces with incorrectly worn masks

The solution is implemented in Python and built upon the Mask R-CNN framework. It is designed for real-world applications like monitoring public spaces during a pandemic.

---

🎯 Features

• 🔍 Instance Segmentation: Identifies mask-wearing status and segments faces in images.
• 🎨 Customizable Classes: Extensible to detect other classes.
• ⚙️ Pre-trained Weights: Utilizes COCO weights for transfer learning.
• 🎮 Visualizations: Overlay predictions with bounding boxes and segmentation masks.
• ⏳ Real-time Applications: Can be integrated with OpenCV for live detection.

---

🛠️ Tools & Technologies

• 🧬 Framework: Mask R-CNN
• 🚀 Deep Learning: TensorFlow, Keras
• 📊 Dataset Handling: XML Annotations, Numpy
• 📚 Visualization: Matplotlib, Seaborn
• ⚙️ Image Processing: OpenCV, Skimage
• 📈 Training Data: Custom Dataset (Face Mask Detection)

---

🔢 Installation

Clone the Repository

$ git clone https://github.com/your-username/mask-detection-mask-rcnn.git
$ cd mask-detection-mask-rcnn

Install Dependencies

$ pip install -r requirements.txt

Download Pre-trained Weights

$ wget https://github.com/matterport/Mask_RCNN/releases/download/v2.0/mask_rcnn_coco.h5

---

🔄 Training Pipeline

1. Dataset Preparation: Ensure images and XML annotations are placed in /images and /annotations directories, respectively.
2. Configure Model: Update parameters in MaskConfig.
3. Train Model:

   $ python train_model.py

4. Fine-tune Model:

   $ python tune_model.py

---

🎨 Visualization

After training, visualize results on test images:

$ python visualize_results.py

---

🌐 Applications

• 🔒 Public Safety: Monitoring mask compliance in public spaces.
• 🔧 Access Control: Ensuring mask-wearing in restricted areas.
• 🎮 AI Solutions: Integration with real-time systems like OpenCV.

---

⚖️ License

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

---

📢 Contact

For any questions or feedback, feel free to reach out:

• ✉ Email: ayemenbaig26@gmail.com
• 🔗 GitHub: Aymen016

---

Thank you for checking out this project! 🚀