ABSTRACT:It is a known fact that many accidents occur due to driver's fatigue and sometimes due to inattention factor. Driver's Fatigue and drowsiness problems are one of the important reasons that create many road accidents across the world. Many different types of methods have been carried out to avoid road accidents, however in this paper, a real time vision-based method is proposed to monitor driver fatigue. This paper approach adopts the Viola-Jones classifier to detect the driver's facial features. One of the mostly used method is the color space model for face detection and thus by cropping of face area the eye localization is been done. The first common drawback of color space model is that the non-face area is also detected as face. The second drawback is lacking in modesty of eyes localization by cropping face area of tilted faces in real time. In reality the face can be tilted in any direction due to road condition. So to overcome this problem a new design system is proposed. This papers deals with some proposed methods available for drowsiness and fatigue detection along with their drawbacks and propose a new design to get a better accuracy.