Overview / Usage

​

The Face Mask Detection System is an AI-powered solution that identifies whether individuals are wearing face masks in images or real-time video feeds. It addresses the need for automated monitoring in public spaces, workplaces, and healthcare facilities to promote health and safety compliance.

Using a CNN-based deep learning model, the system classifies faces as “With Mask” or “Without Mask” and can be integrated into CCTV cameras, mobile apps, or access control systems. It enhances public safety, workplace policy enforcement, and pandemic control measures.

In production, this technology can be used for real-time surveillance, providing alerts for non-compliance and ensuring adherence to safety guidelines. Future enhancements may include detecting improper mask usage, thermal screening, and cloud-based monitoring.

Methodology / Approach

The Face Mask Detection System uses a CNN-based model to classify faces as masked or unmasked. It preprocesses datasets with image augmentation and normalizes inputs. The model, built with TensorFlow/Keras, is trained using categorical cross-entropy loss and optimized with the Adam optimizer. Performance is evaluated using accuracy, precision, recall, and F1-score, with hyperparameter tuning to improve results.

​

Technologies Used

​

• Programming Language: Python
• Libraries & Frameworks: TensorFlow, Keras, OpenCV, NumPy, Matplotlib
• Tools & Software: Jupyter Notebook, Google Colab, Anaconda
• Hardware: GPU (NVIDIA for faster training), Webcam (for real-time detection)
• Intel Technologies (if applicable): Intel OpenVINO (for optimized inference on Intel hardware)