A Driver Drowsiness Detection System using Cascaded Adaboost

With the progress of science technology and the vehicle industry, there are more and more vehicles on the road. As a result, the heavy traffic often leads to more and more traffic accidents. In common traffic accident, the driver’s inattention is usually a main reason. To avoid this situation, this paper proposes a sleepy eye's recognition system for drowsiness detection. First, a cascaded Adaboost classifier with the Haar-like features is utilized to find out the face region. Second, the eyes region is located by Active Shape Models (ASM) search algorithm. Then the binary pattern and edge detection are adopted to extract the eyes feature and determine the eye’s state. Experimental results demonstrate the comparative performance, even without the training stage, with other methods. KeywordsFace Detection; Eye's State; Drowsiness.