Driver drowsiness is one of the most important aspects of road safety, and the fact that a tired driver can negatively impact his driving performance, and create an accident with severe consequences, definitely entails the need for effective detection methods. The proposed research leveraged image processing through a Convolutional Neural Network (CNN) and YOLOv8 algorithm to introduce a novel technique for driver drowsiness detection. We provide an innovative methodology for the detection of driver drowsiness using a Convolutional Neural Network and YOLOv8 algorithm. Our model is capable of producing real-time results for detecting drowsiness indications of a driver using image processing techniques. This work will highlight the metrics achieved with the proposed system which has achieved very promising metrics with mAP (Mean Average Precision) of 85.6%, Precision of 82.5%, Recall of 82.4%, and F1 Score of 82.4%. It concludes the potential of the efficient, reliable, and implementable tool and provides a promising avenue for the development of highly efficient practical systems for identifying drowsiness indications of drivers, thus avoiding fatal road accidents caused by such reasons.