Drivers drowsiness is the major problem that causes road accidents. Unlike normal facial expression, drowsiness is defined to be a condition of exhaustion, where the expression of the face is different from usual. The important steps in detecting drowsiness are face detection and expression detection. Many algorithms are being developed to detect face and expressions. But these algorithms give poor performance due to the extrinsic parameters of the environment. Light and position of the camera are the major problems. In this paper, different architectures were used to analyse the performance of face and drowsiness detection. Also we have proposed new detection methods using deep learning techniques. To estimate the drivers’ state we use facial regions corresponding to the entire face. The algorithms employed for face detection are i) Viola Jones ii) DLib iii) Yolo V3. For the Classification, The CNN (Convolutional Neural Network) architecture employed in the drowsiness detection is modified LeNet.