Accident prevention systems are essential in transportation and industrial safety, where operator drowsiness can lead to dangerous outcomes. This study proposes a non-intrusive drowsiness detection system using Haar Cascade classifiers for real-time facial and eye detection. The system monitors eye closure to assess fatigue, triggering an audio alarm using Pygame when prolonged eye closure is detected. The results showed that the system can effectively detect drowsiness, providing an efficient solution to prevent accidents caused by driver fatigue or operator negligence.