Driver drowsiness is one of the main causes of motor vehicle accidents. According to National Sleep Foundation records, about 32% of drivers have at least one drowsy driving experience per month. About 25% of traffic accidents are caused by drowsiness while driving each year. The purpose of this study is to design a system that can detect driver sleepiness based on the aspect ratio of the eye with certain parameters using a webcam placed in the car's speedometer area. The methods used are Histogram Oriented Gradients (HOG) and Linear SVM which are in the dlib library which includes machine learning algorithms and uses real time applications. A pre-trained facial landmark detector from the dlib library is used to predict the location of the 68 x-y coordinates that map the facial landmarks to the face zones. The results of this study indicate that the system can be used in real time to detect driver drowsiness with the camera position in the speedometer area at a distance of 50 cm with an average accuracy of 90.4%.