FaceMask-CNN_Detection is a machine learning project focused on detecting face masks in real-time using Convolutional Neural Networks (CNN). This project is a part of the General Assembly (GA) Capstone, supervised by Ms. Shu Min and Dr. Mogana Darshini.
This face mask detection model is developed as a Capstone project under the guidance and supervision of Ms. Shu Min and Dr. Mogana Darshini at General Assembly. The project aims to explore and implement machine learning and deep learning techniques to address the real-world challenge of detecting face masks in real-time.
The dataset folder contains the data used for training and testing the model. A diverse and well-labeled dataset ensures the model's accuracy and effectiveness.
Here are the Jupyter notebooks included in the project, each with a specific purpose and focus:
-
eda.ipynb - This notebook contains exploratory data analysis (EDA) to understand the dataset's structure, characteristics, and distributions.
-
model_test-prep.ipynb - Preparation and testing of the face mask detection model, including data preprocessing, model training, and evaluation.
-
mtcnn_model.ipynb - Implementation and evaluation of the MTCNN model for face detection and mask classification.
-
opencv_model.ipynb - Utilizing OpenCV for real-time face mask detection, including model implementation, testing, and performance evaluation.
A documentation detailing the real-time face detection system's design, implementation, and performance.
This project is open source and available under the MIT License.