Recently, accidents caused by drowsy driving have emerged as a significant concern for society, often resulting in severe consequences for victims, including fatalities. Lives are the most valuable asset in the world and deserve greater safety on the road. Given the urgency, it is essential to develop an effective drowsiness detection system that can identify drowsiness in drivers and take necessary steps to alert them before any unfortunate incident occurs. Dlib and MediaPipe Face Mesh have shown promising results. However, most previous studies have relied solely on blinking patterns to detect drowsiness, while some have combined blinking with yawning patterns. The proposed research focuses on creating a straightforward drowsy driver detection system using Python, incorporating OpenCV and MediaPipe Face Mesh. The shape detector provided by MediaPipe Face Mesh assists in finding critical facial coordinates, allowing for the calculation of the driver's eye aspect ratio, mouth aspect ratio, and head tilt angle from video input. The system's performance evaluation utilizes standardized public datasets and real-time video footage. Notably, in both scenarios, the system exhibited remarkable recognition accuracy. A performance comparison was undertaken, demonstrating the proposed method's effectiveness. The proposed system has the potential to enhance travel safety and efficiency when integrated with vehicles' supplementary safety features and automation technology.