Driver Somnolence is one of the leading causes of road crash with consequent serious injury and economic loss. This design creates drowsiness detection and warning system whose function is to promote automobile safety by conducting real-time inspection and intervention. The system employs image processing and machine learning techniques to achieve real-time tracking of the driver’s facial features via an in-car camera. All the typical features of drowsiness such as slow eye movement, increased blink rate, yawning, and bobbing of the head are recognized with the aid of the HOG (Histogram of Oriented Gradients) algorithm and decision trees. The visual, audio, and tactile notifications are provided by the system at every instance when drowsiness signs exceed predetermined limits. It integrates with existing vehicle sensors, offering a cost-effective solution for enhancing driver safety. Additionally, it can be linked with advanced driver-assistance systems (ADAS) for a comprehensive safety approach. The system can also send alerts via email and WhatsApp notifications for added convenience. Including unique alert system and drivers mood enhancement approach sound waves. With a accuracy rate of 84.5 for eye, 91.5 for mouth, 97.8 for mouth and with a overall of 93.5 accuracy rate.