Face Mask Detection is a computer vision project aimed at detecting whether a person is wearing a face mask or not. The project utilizes deep learning techniques to classify faces into two categories: "With Mask" and "Without Mask." The motivation behind this project is to help enforce mask-wearing policies in public places and contribute to public health and safety during pandemics like COVID-19.
- Real-time face mask detection from images or live video streams.
- High accuracy due to the deep learning model used.
- Easy-to-use interface for both developers and end-users.
- Streamlit WebApp, Simple and accurate.
To set up the Face Mask Detection project, follow these steps:
- Clone the repository:
git clone https://github.com/p2kalita/Face_Mask_Detection.git
- Navigate to the project directory:
cd FaceMaskDetection
- Open Ternimal as Conda Base environment and Environment create
conda create -p env python==3.10.0
conda activate env/
- Install dependencies
pip install -r requirements.txt
- Run the WebApp
streamlit run app.py
https://www.kaggle.com/datasets/ahmedabdelraouf/face-datasets
The deep learning model used for this project is a custom convolutional neural network (CNN) architecture. It was trained on the dataset mentioned above to detect face masks accurately. The model is implemented using popular deep learning frameworks like TensorFlow/Keras.
├── artifacts - here's the models stored.
│ └── Mask_detection_model.h5
│ └── Face Models
│ └── res10_300x300_ssd_iter_140000.caffemodel
│ └── deploy.prototxt
The model achieved an accuracy of 96% on the test dataset. The performance may vary depending on the dataset and the quality of the images used for detection.
Contributions to this project are welcome. If you find any issues or want to enhance the functionality, feel free to open a pull request. Please make sure to follow the coding conventions and provide detailed information about the changes.