The document describes a real-time drowsiness detection system that uses a webcam to monitor a driver's face. It detects drowsiness by analyzing features like eye aspect ratio (EAR) and mouth aspect ratio (MAR) over time. The system first locates the face, then eyes and mouth. It calculates EAR by measuring eye closure distances and MAR by measuring mouth opening distances. If EAR and MAR fall below thresholds for a certain number of frames, an alert is triggered by displaying text, sound or sending an SMS message to a designated emergency number. The system was tested over 20 days on people with and without things like glasses or facial hair. It provides a non-intrusive way to detect drowsiness